AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning

Yulei Qin, Xingyu Chen, Chao Chen, Yunhang Shen, Bo Ren, Yun Gu, Jie Yang, Chunhua Shen

AAAI 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Alignment-based few-shot metric learning · 3 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
Use the learned relation module instead of cosine similarity (ablation)FoPro · WebFG496 averageaccuracy (%): 81.59 -> 82.03Improved
Use the learned relation module instead of cosine similarity (ablation)FoPro · ImageNet1k valTop-1 accuracy (%): 65.22 -> 67.55Improved
Use the learned relation module instead of cosine similarity (ablation)FoPro · ImageNet500Top-1 accuracy (%): 64.69 -> 69.11Improved
Increase real-world examples per class from K=0 to K=16 (ablation)FoPro · WebFG496 averageaccuracy (%): +6.43Improved
Increase real-world examples per class from K=0 to K=16 (ablation)FoPro · ImageNet1k valTop-1 accuracy (%): +1.80Improved
Increase real-world examples per class from K=0 to K=16 (ablation)FoPro · ImageNet500Top-1 accuracy (%): +3.43Improved
Use no real-world shots to initialize and guide prototypes (ablation)FoPro · ImageNet1k valTop-1 accuracy (%): 68.83 -> 67.03Hurt
Use no real-world shots to initialize and guide prototypes (ablation)FoPro · ImageNet500Top-1 accuracy (%): 72.02 -> 68.59Hurt
Set gamma to 0.2 rather than 0.6 (ablation)FoPro · WebFG496accuracy (%)Hurt
Use an unbalanced self-prediction/similarity weighting rather than beta=0.5 (ablation)FoPro · WebFG496accuracy (%)Hurt

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