AI Paper Atlas

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

An Erudite Fine-Grained Visual Classification Model

Dongliang Chang, Yujun Tong, Ruoyi Du, Timothy Hospedales, Yi-Zhe Song, Zhanyu Ma

CVPR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 38 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 dataset-specific feature disentanglement and gated feature re-fusion (ablation)Joint multi-dataset FGVC model · D134accuracy: 84.80 -> 86.00Improved
Add the vanilla spatial attention layer, without meta-learning (ablation)Feature disentanglement and re-fusion model · D134accuracy: 86.00 -> 85.52Hurt
Add meta-learning to train the spatial attention layer (ablation)Feature disentanglement and re-fusion model with spatial attention · D134accuracy: 85.52 -> 86.88Improved
Use PCGrad instead of the proposed meta-learning strategy for the spatial attention layer (ablation)Proposed multi-dataset FGVC model · D134accuracy: 86.88 -> 86.45Hurt
Combine the proposed method with PMGPMG · D12accuracy: 83.94 -> 84.93Improved
Jointly train across mixed datasets rather than train each dataset separatelyD24 · D24accuracy: 91.89 -> 90.61Hurt

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