Image-Sequence Object Discovery With Noise-Filtered Pseudo-Labels

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing unsupervised object discovery methods struggle with noise in pseudo-labels and limited localization of static objects due to reliance on motion information, leading to robustness issues and incomplete object detection.

Innovation Solution

Introduces automatic noise filtering of pseudo-labels using confidence scores and distillation learning to integrate static object supervision, enhancing the model's ability to distinguish between noise and objects, particularly static ones.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If unsupervised object discovery is performed using motion information from optical flow maps, then human annotation is eliminated and training data can be obtained automatically, but the generated pseudo-labels contain noise and are incomplete, leading to reduced detection accuracy

Engineering Contradiction:
Improveautomatic training data generationVSAvoiddetection accuracy
Core Design Contradiction:
Ease of manufactureVSReliability

Solution Approach 1:

The patent introduces an intermediary verification step between automatic pseudo-label generation and model training. A segmentation model first generates candidate object masks from optical flow maps, then these candidates are verified against the actual images to filter out noise and false positives. This intermediary verification process maintains the automatic generation advantage while significantly improving the reliability of training data.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Extent of automation

If motion information is used to generate pseudo-labels for object discovery, then training can be performed without human annotation, but static objects are missed and the pseudo-labels are incomplete

Engineering Contradiction:
Improveunsupervised training capabilityVSAvoidstatic object detection
Core Design Contradiction:
Extent of automationVSLoss of information

Solution Approach 1:

The patent segments the object detection task into two distinct parts: moving objects detected through optical flow-based pseudo-labels, and static objects detected through a separate mechanism. The system generates pseudo-labels for moving objects while simultaneously identifying static objects that are absent from motion-based labels, ensuring both types of objects are included in the training data without requiring human annotation for either category.

Inventive Principle:
Principle #1Segmentation

3Productivity

If all generated pseudo-labels are used for training, then the training process is simple and fast, but noise segments are treated as valid objects, reducing model robustness

Engineering Contradiction:
Improvetraining speedVSAvoidmodel robustness
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent implements a feedback mechanism where the segmentation model's predictions are evaluated against ground truth images to compute accuracy metrics. Pseudo-labels that fail to meet quality thresholds or are identified as noise segments are filtered out before being used for training. This feedback loop ensures that only high-quality pseudo-labels are incorporated, maintaining model robustness while preserving reasonable training efficiency.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4632689A1Method for training a machine learning model for discovering objects in an image sequence
Publication Date: 2025.10.15 COMMISSARIAT A LENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
  • EP4632689A1 patent drawingFigure 1a~1b
  • EP4632689A1 patent drawingFigure 2
  • EP4632689A1 patent drawingFigure 3~4

AI summary

Method for training a model (MDO, MDOEL) for discovering objects in an input image sequence (SI), the model comprising: an encoder (ENC, ENCEL) an attention module (ATT, ATTEL) configured to transform the first feature vector into a plurality of feature vectors called slots (S1, ..SK-1), a decoder (DEC) learning the attention maps (W1, ..WK-1) being supervised (404) by a set of binary masks for discovering moving objects produced by an external source, called pseudo-labels (PL), the pseudo-labels (PL) being filtered (FIL) by means of the steps of: determining (401) an attention map of the foreground of the image (Wfg), calculating (402) a confidence score from the average of the values ​​of the attention map (Wfg) of the foreground of the image at the positions of each moving object present in a pseudo-label, filtering (403) the moving objects of the pseudo-labels for which the confidence score is lower than a predefined threshold,.