Papers › Fine-Grained Visual Classification with Batch Confusion Norm

Fine-Grained Visual Classification with Batch Confusion Norm

28 Oct 2019None 2019 10archive 2025-07-28

Yen-Chi Hsu, Cheng-Yao Hong, Ding-Jie Chen, Ming-Sui Lee, Davi Geiger, Tyng-Luh Liu

We introduce a regularization concept based on the proposed Batch Confusion Norm (BCN) to address Fine-Grained Visual Classification (FGVC). The FGVC problem is notably characterized by its two intriguing properties, significant inter-class similarity and intra-class variations, which cause learning an effective FGVC classifier a challenging task. Inspired by the use of pairwise confusion energy as a regularization mechanism, we develop the BCN technique to improve the FGVC learning by imposing class prediction confusion on each training batch, and consequently alleviate the possible overfitting due to exploring image feature of fine details. In addition, our method is implemented with an attention gated CNN model, boosted by the incorporation of Atrous Spatial Pyramid Pooling (ASPP) to extract discriminative features and proper attentions. To demonstrate the usefulness of our method, we report state-of-the-art results on several benchmark FGVC datasets, along with comprehensive ablation comparisons.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

ClassificationFine-Grained Image ClassificationGeneral Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification FGVC Aircraft BCN Accuracy 93.5% #21 of 57 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars BCN Accuracy 94.8% #30 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.

Methods

Spatial Pyramid Pooling

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