149 results about "Decoder architecture" patented technology

The invention provides a microcrack precise segmentation method integrating feature fusion and convolution attention, and belongs to the field of image processing. According to the method, a crack segmentation network based on an encoder-decoder architecture is constructed, a convolution block attention module is introduced at an encoder end, background noise is adaptively suppressed and obvious characteristics of cracks are enhanced through a channel and space dual attention mechanism, and the method is suitable for the adaptive segmentation of the cracks on the premise of almost not increasing the calculation overhead. The sensitivity of the model to microcracks is improved; a feature fusion module is introduced at a decoder end, and cooperation of low-layer details and high-layer semantics is realized through cross-layer fusion, so that a semantic gap is effectively bridged, detail loss caused by traditional convolution stacking is avoided, and continuity and a complete topological structure of a long and narrow crack are ensured. According to the method, through collaborative optimization of multi-scale feature extraction and an attention mechanism, accurate capture of the saliency features of the crack and effective suppression of complex background interference are realized, and the detection sensitivity and overall segmentation consistency of the micro-crack are remarkably improved.

Disclosed in the present invention is a non-autoregressive Transformer-based modeling method for a 4-level pulse amplitude modulation high-speed transmitter. The method involves establishing a deep learning model having an encoder-decoder architecture to predict the behavior of a 4-level pulse amplitude modulation transmitter. An encoder processes unordered non-sequential inputs, including an input signal parameter and link parameters, to generate a context vector and then transmit same to a decoder. The decoder uses both the context vector generated by the encoder and a transmitter output signal sequence to generate a categorical probability distribution for each point in the sequence one by one. The model is trained using a random masking strategy, and inference is performed by means of non-autoregressive decoding and filtering, so that the model can perform parallel prediction on an output sequence, and perform a filtering process to predict an output signal. Compared to traditional simulation methods, the present invention achieves a significant acceleration effect, particularly when processing multi-link systems.

The invention discloses a multi-scale point cloud pre-training method for sampling from top to bottom, equipment and a medium. According to the method, through a U-Net type asymmetric encoder-decoder architecture and in combination with a multi-scale mask, the extraction capability of local features and global information of point cloud data is enhanced. According to the method, firstly, input point cloud data is subjected to multi-scale division and mask processing, then multi-scale features are extracted through an encoder, a masked point cloud area is reconstructed through a decoder, and a masked local point cloud block is recovered through a linear projection layer. According to the invention, the problem of multi-scale information leakage in the prior art is effectively avoided, and the point cloud data processing precision is improved. After self-supervised pre-training, the model shows excellent performance in a plurality of downstream tasks, especially in applications such as 3D shape classification, object detection and partial segmentation. The method has the advantages of high robustness and wide application prospect.

The invention relates to the technical field of short-term load prediction in a power system, and discloses a short-term load prediction system based on a coder-decoder architecture, and the system is characterized in that a coder is used for extracting local features of a power load mode; and the decoder is used for converting the local features of the power load mode into predicted power load values and outputting the predicted power load values. The encoder is realized by a multi-scale expansion causal convolutional network MSDCC, and the decoder is realized by a bidirectional long short-term memory network BiLSTM. The prediction system construction method comprises the following steps: extracting related data from a historical database, preprocessing and analyzing the data, and constructing a predictor matrix; an MSDCC encoder is constructed; a BiLSTM decoder is constructed; and combining the encoder-decoder architecture to construct a short-term load prediction model. According to the method, the size of the feature map is effectively limited, model parameters are reduced, overfitting is avoided, calculation requirements are controlled, non-linear features are efficiently captured, meanwhile, time keeping complexity is low, and therefore the method has the advantages of being high in prediction efficiency and high in prediction precision.

The embodiment of the invention provides a defect detection method for an ATE wafer graph based on a double-task CNN, and the method comprises the steps: obtaining a wafer graph generated by automatic testing equipment, and carrying out the data processing of the wafer graph; constructing a network model structure which has double task branches and shares one encoder; taking the processed wafer graph data as the input of the network model structure, and carrying out multi-stage strategy training to obtain an optimal network model; and deploying the optimal network model into hardware equipment, taking a wafer graph obtained by the hardware equipment in real time as input of the optimal network model, and performing synchronous reasoning and output to obtain a defect detection result. By using a convolutional neural network model which is based on an encoder-decoder architecture and comprises classification and segmentation dual task branches, wafer defects are automatically, quickly and accurately identified and positioned, the production line process health condition is timely and effectively evaluated, and major production accidents such as large-scale yield loss are avoided.

The invention relates to the technical field of infrared light machine system thermal deformation prediction, in particular to a multi-material structure thermally induced stress deformation prediction method based on a graph neural network. The method comprises the steps of data set establishment, graph structure establishment, graph neural network model establishment and training and model and parameter optimization. Finite element nodes correspond to graph nodes, finite element edges correspond to graph edges, an encoder-message passing-decoder architecture model is established, and node states are updated through a three-layer physical symmetry message passing mechanism. Physical constraint loss including minimum displacement smoothness constraint and stress continuity constraint is innovatively added into a loss function. Compared with traditional finite element calculation, the method has the advantages that the speed is increased by more than 100 times, high hardware adaptability is achieved, the black box limitation of a data-driven neural network model is broken through, thermally induced stress deformation analysis caused by different material coefficients can be processed, the adaptability to geometric changes is high, and good engineering application value is achieved.

The invention provides an industrial defect detection method based on a multi-scale Transform, and the method comprises the steps: employing a pre-training network to extract multi-scale deep features, introducing a multi-scale Transform encoder-decoder architecture, achieving the long-distance dependence modeling through a multi-head self-attention mechanism, and obtaining the global representation capability exceeding a convolution network. Compared with CNN-U-Net, lossless jump connection is designed, 512-dimensional features generated by an encoder can be completely transmitted to a decoder, and tiny defect information loss caused by a traditional dimension reduction mode is avoided; the calculation complexity of global attention is remarkably reduced through a three-level local attention decomposition mechanism and is only 0.47% of that of a standard Transform, and the industrial real-time detection requirement is met; and self-adaptive error normalization and multi-scale smooth fusion are combined, so that false alarms at complex textures are effectively inhibited, and patch boundary artifacts are eliminated. Finally, according to the method, a pixel-level abnormal score graph is generated based on reconstruction deviation, and high-precision positioning and detection of multi-scale defects are achieved.

The invention discloses a CBCT tooth segmentation method and system based on an anatomical perception cascade network, and the method comprises the steps: a first stage, carrying out the simplified dichotomy segmentation based on an original CBCT image and a coarse segmentation network taking 3D U-Net as a trunk, outputting maxillary and mandibular tooth probability graphs, and taking the maxillary and mandibular tooth probability graphs as prior information to guide the generation of an SDM; in the second stage, the original CBCT image and the calibrated maxillary tooth probability graph and the calibrated mandibular tooth probability graph are spliced together, a formed multi-channel input tensor is input into a fine segmentation network, the fine segmentation network takes Residual U-Net as a trunk, and an improved AGBR module and an improved SDMAA module are integrated in an encoder-decoder architecture of the fine segmentation network; and the decoder fuses all refined and re-calibrated feature maps, and upsamples and reconstructs 42 types of instance segmentation results with correct topology and clear boundaries. According to the method, the problem that in the prior art, when the inherent and local boundary fuzzy defect in CBCT is overcome, an effective pertinence mechanism is lacked is solved, and precise and robust 42-class instance segmentation can be achieved.

The invention discloses a hydropower station operation state intelligent prediction method and system based on multi-source data fusion. The method comprises the steps that heterogeneous data including but not limited to water level, flow, generating capacity, equipment operation parameters, environmental meteorological data, hydrological data and the like are collected in real time from multiple data sources of a sensor network, an SCADA system, a meteorological station and a hydrological station of a hydropower station; the method comprises the following steps of: preprocessing collected original data, extracting time sequence features, fusing multi-source data, taking a fused multi-dimensional feature vector as input, and learning and training through an encoder-decoder architecture of a model so as to capture a complex dynamic mode of an operation state of a hydropower station; and inputting the data acquired and preprocessed in real time into the trained AI prediction model, and generating prediction results of key operation parameters, equipment states, residual life and potential risks of the hydropower station. The method can more accurately capture the complex nonlinear relation in the operation of the hydropower station, and significantly improves the prediction precision of key parameters and risks.

The embodiment of the invention provides an encrypted traffic classification model training method, an electronic device, a storage medium and a program product, through a self-supervised learning framework, an unmarked patch is utilized to embed and express a training encoder-decoder structure, so that the model can autonomously learn universal spatio-temporal features from an encrypted traffic grey-scale map. The mask reconstruction task promotes the model to understand the internal structure rule of the traffic data, the understanding depth of the model for the input data is enhanced, the adaptability of the model to the distributed data is improved, and the generalization ability, adaptability and robustness of the model are also improved.

The invention discloses a Conformer-based mixed self-attention and convolution improved speech recognition method and system. The recognition method comprises the steps of obtaining speech feature representation; the speech feature representation is input to a Conformer encoder for encoding processing, high-dimensional feature representation is obtained, and the Conformer encoder comprises a convolution module, an attention linear enhancement module and a feedforward network residual scaling module; according to the high-dimensional feature representation, bidirectional decoding is carried out through a bidirectional Transform decoder, and bidirectional decoding output is obtained; and carrying out merging processing on the bidirectional decoding output to obtain a speech recognition result. According to the method, the modeling capacity for long-time dependence and global context is enhanced through a bidirectional decoder architecture, the processing capacity of the model in a long sequence is improved through ALiBi relative position coding, and the model can be flexibly adjusted in a noise environment through a right decoder weighting adjustment mechanism.

The invention provides an underwater video enhancement method based on semantic guidance, and the method comprises the following steps: S1, carrying out the global feature enhancement of a multi-frame video, and obtaining a feature map after global enhancement; s2, performing region enhancement on the context features of the multi-frame video to obtain a feature map after region enhancement; s3, performing semantic guidance on the feature map after region enhancement to obtain a region enhancement feature map after semantic guidance; and S4, fusing the semantically guided region enhanced feature map and the globally enhanced feature map to obtain an output effect of the intermediate frame. According to the global feature enhancement method disclosed by the invention, an encoder-decoder architecture is mainly used, multi-frame time sequence information is fully utilized to perform spatial alignment of adjacent multi-frame features by using grouping spatial shift, context information is fully learned to suppress irrelevant noise, the robustness of feature representation is enhanced, and the effect of global feature enhancement is achieved.

The invention discloses an overhead power line icing thickness detection method and system based on a structure perception framework, and the method comprises the steps: firstly obtaining point cloud data of a power transmission line, preprocessing the point cloud data, and inputting the preprocessed point cloud data into a structure perception semantic segmentation network; the network adopts a four-level encoder-decoder architecture, an encoder extracts multi-scale features through local space encoding, cross-scale space attention fusion and local aggregation operation, and a decoder realizes feature fusion in combination with a jumper connection mechanism and outputs a lead semantic segmentation result; extracting a conductor point set based on a segmentation result and carrying out Euclidean clustering strand splitting; performing biplane projection and polynomial fitting on each strand of wire to construct a three-dimensional center line; and finally calculating the distance from the point to the center line, selecting a peripheral point set to calculate the wire envelope radius, and combining the radius of the bare wire to obtain the icing thickness. Measurement deviation caused by point cloud shielding, wire bending and asymmetric icing is effectively solved, millimeter-level precision non-contact ice thickness detection in a complex environment is achieved, and reliable technical support is provided for power grid disaster prevention.

The invention discloses a robot control system and method based on AI voice, and belongs to the technical field of robot intelligent control. The system comprises a local voice processing module, a dialogue management and context understanding module, an instruction mapping and generating module and a robot communication and control module. The local voice processing module is integrated with a 16 kHz sampling ASR engine, voice-to-text conversion is realized through a 6-layer LSTM network and beam search decoding, and the TTS engine adopts a WaveNet architecture to synthesize voice. A 7 billion parameter large language model is arranged in the dialogue management module, a 32-layer Transform decoder architecture is adopted, 10 rounds of dialogue history is maintained, and intention recognition and entity extraction are achieved through a multi-head self-attention mechanism. And the instruction mapping module performs trajectory planning by adopting quintic polynomial interpolation and quaternion spherical linear interpolation. According to the invention, full-link localization processing is realized, the speech recognition delay is 180 milliseconds, the position error is less than 0.5 mm, and the problems of high delay, high privacy risk and weak complex instruction understanding ability in the prior art are effectively solved.

The invention discloses a deep learning-based bridge scour damage identification method and system, and solves the problems of poor universality and limited scour damage identification efficiency and precision of the existing bridge scour damage identification method. The method comprises the following steps: constructing an original data set; preprocessing the data; the method comprises the following steps: constructing a sequence-to-sequence multi-parameter model of an encoder-decoder architecture by adopting a double-layer long short-term memory network, and adding a Dropout layer and a LayerNorm layer in the model for standardization; a loss function of model training and optimization is defined, an Adam optimization algorithm is adopted, L2 regularization is added, an early stop method is utilized to train and optimize the Seq2Seq multi-parameter model, and a model with the minimum verification set loss is selected as an optimal prediction model to be used for recognizing the bridge scouring damage. According to the method, the complex scouring damage condition of the multi-span bridge can be rapidly identified, the scouring damage identification efficiency and precision are improved, the universality is higher, and the identification efficiency is higher.

The invention discloses an unbalanced node classification method based on graph contrast learning, and belongs to the technical field of artificial intelligence. According to the method, a graph comparison learning framework of adaptive balance data is provided, minority classes can be automatically identified, the minority class performance is improved, and then the overall performance of the model is improved. Firstly, an Encoder-Decoder architecture is used for pre-training, and compared with a traditional pseudo tag generation method, an unbalance rate self-adaptive sampling strategy is designed, the unbalance rate of data is calculated according to pseudo tags, and the sampling strategy is selected in a self-adaptive mode. For a data set with a low unbalance rate, a simple downsampling method is adopted, and the proportion of minority class information is increased; for a data set with a relatively high unbalance rate, a mixed sampling strategy is adopted, and over-sampling and down-sampling are combined, so that the information loss of majority of nodes is reduced while the information proportion of minority of nodes is increased. In addition, the pre-training model used in the invention can provide more accurate label information, thereby improving the distinguishing ability of the model in subsequent GCL training. Then, a new data augmentation technology is designed, in the node masking process, pseudo label information is utilized, information of minority class nodes is reserved preferentially, and meanwhile majority class nodes are masked; the method is helpful for the model to better capture minority class features in an unbalanced data set. And finally, a linear classifier is used for classification. According to the method, the unbalanced node classification performance under the self-supervision condition can be effectively improved.

The embodiment of the invention relates to a processing method and device for a dense encoder realized based on a large language model, and the method comprises the steps: selecting a large language model which has completed pre-training and NLP task fine tuning and is realized based on a pure decoder architecture as a target model, the bidirectional encoders are obtained through a transformation mode of solidifying a causal mask matrix used by a target model decoder in a reasoning process into an all-one matrix, and the embedded encoding module of the target model and the plurality of bidirectional encoders are connected in sequence to form a dense encoder; performing first-stage fine adjustment on the dense encoder through a shielding word prediction task, and performing second-stage fine adjustment on the dense encoder through an unsupervised contrast learning mechanism; and after the fine tuning is finished, constructing a document vector library for a target document library appointed by the user by utilizing the dense encoder, and providing retrieval service for the target document library based on the document vector library and the dense encoder. The dense encoder is used for processing a text retrieval task, so that the retrieval accuracy can be improved.

The invention discloses a multi-person redirection walking and position prediction method based on an artificial potential field, and belongs to the technical field of virtual reality and robot navigation. Aiming at the problems of fixed repulsive force weight, high collision risk and frequent resetting in a multi-user dynamic scene in a traditional redirection walking algorithm and collision caused by insufficient short-term position prediction precision of predictive redirection, the weight distribution of repulsive force between an environment and users is adjusted in real time according to user density through a dynamic situation field weight optimization mechanism; the repulsive force intensity is enhanced when a user approaches an obstacle or a dense area, meanwhile, a safety distance and direction sensing mechanism is introduced, the user movement direction and obstacle included angle analysis is combined, deviation from a high-risk area is guided preferentially, and the invalid reset frequency is reduced. The prediction model adopts an encoder-decoder architecture, an attention mechanism is embedded in a multi-layer long-short-term memory network, key time sequence characteristics in a space-time trajectory are dynamically captured, and the short-term position prediction precision is improved.

The invention discloses an epileptic seizure video detection method based on a memory enhanced double-branch auto-encoder. The method comprises the following steps: firstly, preparing and preprocessing data; secondly, constructing an ME-DBAE model which comprises a query generation module, a multi-head memory module and a double-branch decoder module; training the model by using training set data, finally inputting a to-be-detected video into the trained model to obtain an epileptic seizure score, and judging whether the video belongs to an epileptic seizure sample or not through a threshold value. By designing the multi-head memory module, diversified normal motion prototypes are stored in parallel, and the limitation that a single memory structure is difficult to adapt to complex normal actions is broken through; and by constructing a double-branch decoder architecture, double tasks of input reconstruction and future frame prediction are cooperatively realized, and meanwhile, space structure and time trend characteristics of normal motion are captured, so that epileptic seizure actions and normal actions are effectively distinguished.

The invention discloses a Raw domain moire removing method based on Mama, and relates to the technical field of image signal processing. The invention relates to a Mamba-based Raw domain moire removal method, which comprises the following steps that: S1, a Mamba-based Raw domain moire removal model is constructed, and the model adopts a U-Net type multi-scale encoder-decoder architecture; s2, designing a selective scanning module based on time and space, and adaptively focusing on a space-time region with significant moire; s3, training the model by using a deep learning Pytorch framework, and repeatedly traversing the VDRawmoire data set until the model is converged; s4, inputting multiple frames of Raw domain moire images into the model, and outputting a single-frame RGB image reconstruction result after moire removal; according to the method disclosed by the invention, the Moire removal performance of the Raw domain is improved to a new height by utilizing proposed selective scanning based on time and space.

The invention relates to an adaptive low density parity check (LDPC) decoder architecture. An LDPC decoder architecture is provided for adaptively adjusting an LDPC control input for successfully decoding a corresponding received code block. The architecture supports a machine learning based process that facilitates learning the optimal LDPC control input required for a given channel condition and deployment scenario, such as log-likelihood (LLR) term scaling. This is accomplished by an unused LDPC decoder accelerator collecting posterior decoding metrics as a background process, the function of the accelerator being to process a tagged LLR dataset of different LDPC control input values. This optimal LDPC control input estimate may then be applied to real-time LDPC decoding based on previous learning under UE / channel conditions.

The invention discloses a large language model translation system based on an encoder and decoder architecture, which comprises the following steps: a data processing stage: collecting massive multilingual bilingual corpora for preprocessing, and constructing high-quality fine-tuning parallel corpora; constructing an encoder-decoder structure by using the pre-trained large language model, and determining the number of layers reserved at a decoder end and the connection mode of an encoder and a decoder by adopting a deep encoding-shallow decoding mode; performing model training by using massive multilingual bilingual corpora and high-quality fine-tuning parallel corpora obtained in the data processing stage to obtain a machine translation model; in the decoding stage, the encoder of the machine translation model encodes the source statement, and then the decoder decodes the source statement to generate a target language sentence. According to the method, the strong context understanding and generating capability of the large language model is utilized, the defect of low reasoning speed is overcome, the translation quality and effect of the model are improved, the convergence speed of the model is increased, the robustness of the model is improved, and the benefits brought by the pre-training method are improved.

The invention discloses a radar signal sorting method based on an improved long short-term memory network, and the method comprises the steps: extracting a pulse arrival time sequence, namely, a TOA sequence, from a pulse description word stream of a radar receiver; discretization processing is conducted on the TOA sequence through a preset fixed time window width wunit, the TOA sequence is mapped into a binary vector, each time window corresponds to one position in the vector, if a pulse arrives in the window, the corresponding position is set to be 1, and otherwise, the corresponding position is set to be 0; an improved ILSTM neural network is constructed, the network adopts an encoder-decoder architecture, and an encoder is used for performing high-level feature extraction on an input binary sequence and outputting a context feature vector; the decoder performs sequence prediction or reconstruction by using the context feature vector so as to output a sorting result; training the improved LSTM neural network by using a binary TOA vector data set of a known radiation source label, and optimizing network parameters; and after processing the to-be-sorted interleaved pulse TOA sequence, inputting the to-be-sorted interleaved pulse TOA sequence into the trained ILSTM network, and outputting a radiation source sorting result corresponding to each pulse by the network. The method is suitable for radar signal sorting in high-density, complex-modulation and strong-interference environments.

This invention discloses a speech model compression method, electronic device, and storage medium. It is specifically designed for large-scale sequence-to-sequence speech recognition models with an encoder-decoder architecture. This method avoids cumbersome backpropagation computation by sequentially pruning the decoder and encoder. It can reduce the parameters of a Whisper-large model by approximately 60% without backpropagation or retraining, with almost no impact on the model's performance on various datasets. Furthermore, this method is applicable to multilingual datasets, and the pruned model maintains good robustness and generalization capabilities across multiple languages. This innovation significantly lowers the barrier to large-scale model deployment, making it easier to apply in resource-constrained environments.

The invention discloses a multi-mode body intelligent agent track prediction method, which comprises the following steps of: receiving and processing input data, and standardizing dynamic and static contexts; an encoder-feature fusion device-decoder architecture model is constructed, the encoder maps high-dimensional features to a low-dimensional space and keeps key information, the feature fusion device fuses the features, the decoder extracts a trajectory mode probability, Gaussian noise is injected to enhance variation capture, and a multi-modal three-dimensional trajectory sequence is generated through GRU; and dynamically selecting an optimal path in combination with real-time environment feedback to complete prediction. Through standardization processing, multi-feature fusion and noise injection, prediction accuracy and environmental adaptability are improved, and efficient trajectory prediction is realized.

A method for quantifying uncertainty in parameterized (e.g., machine learning) model predictions is described herein. The method includes causing a parameterized model to predict multiple posterior distributions for a given input from the parameterized model. The multiple posterior distributions include distributions from a plurality of distributions. The method includes determining variability in the predicted multiple posterior distributions for a given input by sampling from the distributions from the plurality of distributions; and quantifying uncertainty in the parameterized model predictions using the determined variability in the predicted multiple posterior distributions. The parameterized model includes an encoder-decoder architecture. The method includes adjusting the parameterized model using the determined variability in the predicted multiple posterior distributions to reduce uncertainty in the parameterized model for predicting wafer geometry, overlay, and / or other information as part of a semiconductor manufacturing process.

The invention provides a time series data interpolation method based on graph attention coding and a cross attention diffusion model. The core of the method is that an asymmetric encoder-decoder architecture is constructed, covariant feature representation is enhanced through a graph neural network, priori knowledge is injected, and then enhanced condition information is dynamically fused into each step of denoising process of a diffusion model by using a cross attention mechanism. Therefore, high-precision and high-robustness missing data interpolation is realized.

A high-speed parallel GRAND-CRC decoding method for functional safety communication is presented. M A round-robin noise error mode allocation scheme for each memory cell, without affecting error correction performance, provides... N The system adds an all-zero error mode to the set E of noise error modes and allocates noise error modes to each memory unit in turn. A high-speed parallel decoder architecture design scheme for GRAND-CRC is proposed, including a distributed memory design strategy and the advantage of unrestricted parallelism. The parallelism can be easily set according to hardware resources, and the decoder throughput increases linearly with the parallelism. The system uses a corrector as the basis for logical judgment, and the corrector signal processing unit triggers the correct decoding output. Its features include different processing methods in three cases, especially when contention occurs, selecting the guessed sequence corresponding to the corrector with the smallest sequence number as the decoding output.

The invention discloses a cluster aided decision planning method based on a large model, and the method comprises the steps: a commander carries out the unified deployment and control according to the order placing demands of a user, and gives out a natural language instruction; acquiring a natural language instruction sent by a commander, and converting the natural language instruction into a hyper-parameter combination in a standardized format based on a retrieval enhancement generation technology and a large language model; analyzing the hyper-parameter combination, and if a predefined path segment is empty, selecting a vehicle-node pair by adopting a station encoder-vehicle encoder-decoder architecture and an autoregression alternating strategy to generate a dynamic path planning scheme; and if the predefined path segment is not empty, redefining a decoder process based on the predefined path segment, and realizing path completion and optimization through a meta-action sequence, a flag matrix and a mask matrix. According to the method, dynamic path planning of any vehicle and node scale is realized, and meanwhile, quick response to a dynamic environment can be realized through real-time planning.

The application provides an image enhancement model training method and an image enhancement method, and relates to the technical field of image processing. Through an encoder-decoder architecture and supplemented by adaptive fusion skip connection, effective extraction and fusion of multi-scale features are realized. The encoder is responsible for multi-scale feature coding of the input image, gradually extracts the abstract features of the image and reduces the spatial resolution. The decoder is responsible for gradually restoring the image resolution and using the multi-scale features provided by the encoder for fine reconstruction, and finally outputs the enhanced image. While highlighting the local details of the ink droplets, the global contrast of the image and the statistical characteristics consistent with the physical reality are effectively maintained, and the distinguishability of the ink droplets and the background is significantly improved, providing a high-precision and high-quality image basis for subsequent quantitative analysis of the ink droplets.