Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Feature Fusion Vision Transformer for Fine-Grained Visual Categorization

About

The core for tackling the fine-grained visual categorization (FGVC) is to learn subtle yet discriminative features. Most previous works achieve this by explicitly selecting the discriminative parts or integrating the attention mechanism via CNN-based approaches.However, these methods enhance the computational complexity and make the modeldominated by the regions containing the most of the objects. Recently, vision trans-former (ViT) has achieved SOTA performance on general image recognition tasks. Theself-attention mechanism aggregates and weights the information from all patches to the classification token, making it perfectly suitable for FGVC. Nonetheless, the classifi-cation token in the deep layer pays more attention to the global information, lacking the local and low-level features that are essential for FGVC. In this work, we proposea novel pure transformer-based framework Feature Fusion Vision Transformer (FFVT)where we aggregate the important tokens from each transformer layer to compensate thelocal, low-level and middle-level information. We design a novel token selection mod-ule called mutual attention weight selection (MAWS) to guide the network effectively and efficiently towards selecting discriminative tokens without introducing extra param-eters. We verify the effectiveness of FFVT on three benchmarks where FFVT achieves the state-of-the-art performance.

Jun Wang, Xiaohan Yu, Yongsheng Gao• 2021

Related benchmarks

TaskDatasetResultRank
Fine-grained Image ClassificationCUB200 2011 (test)
Accuracy91.65
536
Fine-grained visual classificationFGVC-Aircraft (test)
Top-1 Acc91.6
287
Image ClassificationCUB-200-2011 (test)
Top-1 Acc91.6
276
Fine-grained visual classificationNABirds (test)
Top-1 Accuracy89.42
157
Fine-grained Visual CategorizationStanford Cars (test)
Accuracy91.25
110
Image ClassificationStanford Dogs (test)
Top-1 Acc91.5
85
Fine-grained Visual CategorizationFGVCAircraft
Accuracy79.8
60
Fine-grained Image ClassificationNABirds
Accuracy89.42
22
Fine-grained Visual CategorizationCUB
Accuracy91.65
20
Fine-grained Image ClassificationiNaturalist 2017 (test)
Accuracy70.3
19
Showing 10 of 18 rows

Other info

Code

Follow for update