AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Fine-Grained Generalization via Structuralizing Concept and Feature Space into Commonality, Specificity and Confounding

Zhen Wang, Jiaojiao Zhao, Qilong Wang, Yongfeng Dong, Wenlong Yu

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add concept structuralization (with feature structuralization) (ablation)CFSG · CUB-Paintings (avg of C->P, P->C)accuracy (%): 55.65 -> 66.56Improved
add feature structuralization to backbone + CS (ablation)CFSG · CUB-Paintings (avg of C->P, P->C)accuracy (%): 58.75 -> 66.56Improved
add feature structuralization alone to backbone (ablation)Backbone · CUB-Paintings (avg of C->P, P->C)accuracy (%): 51.65 -> 55.65Improved
add concept structuralization alone to backbone (ablation)Backbone · CUB-Paintings (avg of C->P, P->C)accuracy (%): 51.65 -> 58.75Improved
use fixed manual component weights instead of learnable weights (ablation)CFSG · CUB-Paintings (avg of C->P, P->C)accuracy (%): 55.00 -> 66.56Improved
classify with structured concept weights instead of sub-centroids (ablation)CFSG · CUB-Paintings (avg of C->P, P->C)accuracy (%): 59.53 -> 66.56Improved
sub-centroid classification vs FSDG baselineFSDG · CUB-Paintings (avg of C->P, P->C)accuracy (%): 55.65 -> 59.53Improved
replace FSDG with CFSG on ResNet-50 dual backboneFSDG · CUB-Paintings (avg of C->P, P->C)accuracy (%): 55.65 -> 66.56Improved
replace FSDG with CFSG on ResNet-101FSDG · CUB-Paintings (avg of C->P, P->C)accuracy (%): 57.25 -> 68.44Improved
replace FSDG with CFSG on ViT-SmallFSDG · CUB-Paintings (avg of C->P, P->C)accuracy (%): 68.26 -> 70.31Improved
replace FSDG with CFSG on ASMLP-SmallFSDG · CUB-Paintings (avg of C->P, P->C)accuracy (%): 58.75 -> 67.19Improved
use CFSG on VMamba instead of HSSH on Birds-31HSSH · Birds-31 (avg of 6 transfers)accuracy (%): 90.69 -> 90.52No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy