AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Concept Drift and Long-Tailed Distribution in Fine-Grained Visual Categorization: Benchmark and Method

Shuo Ye, Shiming Chen, Ruxin Wang, Tianxu Wu, Salman Khan, Fahad Shahbaz Khan, Ling Shao

TPAMI 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 10 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
train on all data instead of ignoring concept-drift dataNTS-Net (ResNet-50) · CDLT-cdtop-1 accuracy: 69.00 -> 74.32Improved
train on all data instead of ignoring concept-drift dataViT-B-16 IMS · CDLT-cdtop-1 accuracy: 70.82 -> 77.92Improved
use range loss instead of softmax lossResNet-50 · CDLT long-tailed overalltop-1 accuracy: 62.27 -> 72.30Improved
use under-sampling instead of softmax lossResNet-50 · CDLT long-tailed overalltop-1 accuracy: 62.27 -> 46.21Hurt
use over-sampling instead of softmax lossResNet-50 · CDLT long-tailed overalltop-1 accuracy: 62.27 -> 62.20No clear effect
use focal loss instead of softmax lossResNet-50 · CDLT long-tailed overalltop-1 accuracy: 62.27 -> 66.31Improved
use class-balanced loss instead of softmax lossResNet-50 · CDLT long-tailed overalltop-1 accuracy: 62.27 -> 67.45Improved
apply frequency-based feature recombination (diffusion low-frequency generation and high-frequency shuffling)ResNet-50 · CDLT long-tailed overalltop-1 accuracy: 72.30 -> 75.18Improved
apply feature recombination instead of NTS-NetResNet-50 · CDLTtop-1 accuracy: 78.20 -> 78.82Improved
fine-tune CLIP with a text-encoder adapterCLIP ViT-B · CDLTaccuracy: 3.03 -> 2.02No clear effect
fine-tune CLIP with a text-encoder adapterCLIP ViT-B · CUB-200-2011accuracy: 50.89 -> 58.91Improved
fine-tune CLIP with a text-encoder adapterCLIP ViT-B · Stanford Carsaccuracy: 57.73 -> 53.22Hurt

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