Papers › Classification-Specific Parts for Improving Fine-Grained Visual Categorization

Classification-Specific Parts for Improving Fine-Grained Visual Categorization

16 Sep 2019arXiv:1909.07075archive 2025-07-28

Dimitri Korsch, Paul Bodesheim, Joachim Denzler

Fine-grained visual categorization is a classification task for distinguishing categories with high intra-class and small inter-class variance. While global approaches aim at using the whole image for performing the classification, part-based solutions gather additional local information in terms of attentions or parts. We propose a novel classification-specific part estimation that uses an initial prediction as well as back-propagation of feature importance via gradient computations in order to estimate relevant image regions. The subsequently detected parts are then not only selected by a-posteriori classification knowledge, but also have an intrinsic spatial extent that is determined automatically. This is in contrast to most part-based approaches and even to available ground-truth part annotations, which only provide point coordinates and no additional scale information. We show in our experiments on various widely-used fine-grained datasets the effectiveness of the mentioned part selection method in conjunction with the extracted part features.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

DiKorsch/l1_parts mentioned on GitHub report
cvjena/cs_parts 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

ClassificationFeature ImportanceFine-Grained Image ClassificationFine-Grained Visual CategorizationGeneral ClassificationImage Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification NABirds CS-Parts Accuracy 88.5% #22 of 30 Archive leaderboard report
Fine-Grained Image Classification NABirds CS-Part Accuracy 88.5% #23 of 30 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars CS-Parts Accuracy 92.5% #73 of 83 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars CS-Part Accuracy 92.5% #74 of 83 Archive leaderboard report
Image Classification Flowers-102 CS-Parts Accuracy 96.9% #39 of 52 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