Papers › Learn from Each Other to Classify Better: Cross-layer Mutual Attention Learning for...

Learn from Each Other to Classify Better: Cross-layer Mutual Attention Learning for Fine-grained Visual Classification

22 Mar 2023Pattern Recognition 2023 3archive 2025-07-28

Dichao Liu, Longjiao Zhao, Yu Wang, Jien Kato

Fine-grained visual classification (FGVC) is valuable yet challenging. The difficulty of FGVC mainly lies in its intrinsic inter-class similarity, intra-class variation, and limited training data. Moreover, with the popularity of deep convolutional neural networks, researchers have mainly used deep, abstract, semantic information for FGVC, while shallow, detailed information has been neglected. This work proposes a cross-layer mutual attention learning network (CMAL-Net) to solve the above problems. Specifically, this work views the shallow to deep layers of CNNs as “experts” knowledgeable about different perspectives. We let each expert give a category prediction and an attention region indicating the found clues. Attention regions are treated as information carriers among experts, bringing three benefits: (ⅰ) helping the model focus on discriminative regions; (ⅱ) providing more training data; (ⅲ) allowing experts to learn from each other to improve the overall performance. CMAL-Net achieves state-of-the-art performance on three competitive datasets: FGVC-Aircraft, Stanford Cars, and Food-11.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Fine-Grained Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification FGVC Aircraft CMAL-Net Accuracy 94.7% #6 of 57 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars CMAL-Net Accuracy 97.1% #2 of 83 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections