Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition

14 Jul 2021  ·  Xinda Liu, Lili Wang, Xiaoguang Han ·

Fine-grained image recognition is challenging because discriminative clues are usually fragmented, whether from a single image or multiple images. Despite their significant improvements, most existing methods still focus on the most discriminative parts from a single image, ignoring informative details in other regions and lacking consideration of clues from other associated images. In this paper, we analyze the difficulties of fine-grained image recognition from a new perspective and propose a transformer architecture with the peak suppression module and knowledge guidance module, which respects the diversification of discriminative features in a single image and the aggregation of discriminative clues among multiple images. Specifically, the peak suppression module first utilizes a linear projection to convert the input image into sequential tokens. It then blocks the token based on the attention response generated by the transformer encoder. This module penalizes the attention to the most discriminative parts in the feature learning process, therefore, enhancing the information exploitation of the neglected regions. The knowledge guidance module compares the image-based representation generated from the peak suppression module with the learnable knowledge embedding set to obtain the knowledge response coefficients. Afterwards, it formalizes the knowledge learning as a classification problem using response coefficients as the classification scores. Knowledge embeddings and image-based representations are updated during training so that the knowledge embedding includes discriminative clues for different images. Finally, we incorporate the acquired knowledge embeddings into the image-based representations as comprehensive representations, leading to significantly higher performance. Extensive evaluations on the six popular datasets demonstrate the advantage of the proposed method.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Fine-Grained Image Classification CUB-200-2011 TPSKG Accuracy 91.3% # 16
Fine-Grained Image Classification NABirds TPSKG Accuracy 90.1% # 11
Fine-Grained Image Classification Stanford Dogs TPSKG Accuracy 92.5% # 6

Methods


No methods listed for this paper. Add relevant methods here