Papers › Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition

Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition

29 Nov 2016CVPR 2018 6arXiv:1611.09932archive 2025-07-28

Yaming Wang, Vlad I. Morariu, Larry S. Davis

Compared to earlier multistage frameworks using CNN features, recent end-to-end deep approaches for fine-grained recognition essentially enhance the mid-level learning capability of CNNs. Previous approaches achieve this by introducing an auxiliary network to infuse localization information into the main classification network, or a sophisticated feature encoding method to capture higher order feature statistics. We show that mid-level representation learning can be enhanced within the CNN framework, by learning a bank of convolutional filters that capture class-specific discriminative patches without extra part or bounding box annotations. Such a filter bank is well structured, properly initialized and discriminatively learned through a novel asymmetric multi-stream architecture with convolutional filter supervision and a non-random layer initialization. Experimental results show that our approach achieves state-of-the-art on three publicly available fine-grained recognition datasets (CUB-200-2011, Stanford Cars and FGVC-Aircraft). Ablation studies and visualizations are provided to understand our approach.

PaperPDFConference PDFCode

Code

jobinkv/Ongoing mentioned on GitHub report

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

Representation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification CUB-200-2011 DFL-CNN Accuracy 87.4 #25 of 30 Archive leaderboard report
Fine-Grained Image Classification FGVC Aircraft DFB-CNN Accuracy 92.0% #44 of 57 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars DFL-CNN Accuracy 93.8% #60 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