AI Paper Atlas

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

Binocular Mutual Learning for Improving Few-Shot Classification

Ziqi Zhou, Xi Qiu, Jiangtao Xie, Jianan Wu, Chi Zhang

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 114 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 mutual KL loss between global and local views (ablation)BML · miniImageNet 5-shotaccuracy: 82.84 -> 83.63Improved
add mutual KL loss to local branch (ablation)BML-Local · miniImageNet 5-shotaccuracy: 79.29 -> 80.95Improved
add elastic loss to local branch (ablation)Baseline-local · miniImageNet 5-shotaccuracy: 77.07 -> 77.77Improved
share first three blocks instead of none (ablation)BML · miniImageNet 5-shotaccuracy: 83.10 -> 83.63Improved
train global and local views jointly with mutual learning instead of simple ensemble (ablation)BML · miniImageNet 5-shotaccuracy: 81.08 -> 83.10Improved
add binocular training to local branch (ablation)Baseline-local · miniImageNetaccuracy: 1.4%-9.7%Improved
add binocular training to global branch (ablation)Baseline-global · miniImageNetaccuracy: 1.8%-13.3%Improved
add binocular learning over single global view (ablation)Baseline-global · FC100 5-shotaccuracy: 61.03 -> 63.03Improved
combine global and local views (ablation)Baseline-global · CUB-200-2011 5-way 1-shotaccuracy: 60.13 -> 76.21Improved
enlarge test image size to 224x224 (robustness) (ablation)BML vs DeepEMD · miniImageNetaccuracy: 83.59 -> 81.57No clear effect
apply Gaussian blur to test images (ablation)BML vs Rethink-Distill · miniImageNetaccuracy: 83.59 -> 61.96Mixed

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