A fine-grained image classification method based on discriminative learning

Abstract

The invention belongs to the technical field of computer vision, and provides a fine-grained image classification method based on discriminant learning. We propose a new end-to-end autoregressive localization with discriminative prior network model that learns to explore more accurate discriminative patch sizes and is able to classify images in real-time. Specifically, a multi-task discriminative learning network is designed, including an autoregressive localization sub-network and a discriminative prior sub-network with a bootstrap loss function and a consistency loss function to simultaneously learn the self- Regression coefficients and discriminative prior map. The autoregressive coefficients can reduce the noise information in the discriminative patch, and the discriminative prior map filters thousands of candidate patches into single-digit patches by learning the discriminative probability value. Extensive experiments show that the proposed SDN model achieves the state-of-the-art in both accuracy and efficiency.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and takes improving the accuracy and efficiency of fine-grained image classification as a starting point, and proposes a fine-grained image classification method based on discriminant learning. Background technique [0002] Unlike general image classification, Weakly Supervised Fine-Grained Image Classification (WFGIC) uses only image-level labels to identify objects at more detailed categories and granularities. WFGIC has received extensive attention from academia and industry due to its numerous potential applications in image understanding and computer vision systems. WFGIC is an open problem in the field of computer vision, not only because images belonging to the same subcategory vary widely in size, pose, color, and background, whereas images belonging to different subcategories can be very similar in these aspects, and only using Image-level label extraction is very difficult to d...

AI Technical Summary

Problems solved by technology

A large number of about 2000 candidate patches generated by SS need to be predicted whether to contain discriminative features through a deep CNN classification network, which requires high computational cost

Images