AI Paper Atlas

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

Partner-Assisted Learning for Few-Shot Image Classification

Jiawei Ma, Hanchen Xie, Guangxing Han, Shih-Fu Chang, Aram Galstyan, Wael Abd-Almageed

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 75 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 partner-assisted alignment (SupCT partner -> CE main) over CE-only training (ablation)ResNet-12 main encoder · miniImageNet 5-way 1-shotaccuracy (%): 63.76 -> 69.37Improved
add partner-assisted alignment over CE-only training (ablation)ResNet-12 main encoder · miniImageNet 5-way 5-shotaccuracy (%): 81.17 -> 84.40Improved
use SupCT partner one-way instead of multi-task L_CE + L_SupCT (ablation)PAL · miniImageNet 5-way 1-shotaccuracy (%): 67.53 -> 69.37Improved
use one-way SupCT partner instead of mutual learning (ablation)PAL · miniImageNet 5-way 1-shotaccuracy (%): 65.21 -> 69.37Improved
use SupCT -> CE direction instead of CE -> SupCT (ablation)PAL · miniImageNet 5-way 1-shotaccuracy (%): 66.54 -> 69.37Improved
train partner with SupCT instead of CE (ablation)PAL · miniImageNet 5-way 1-shotaccuracy (%): 66.95 -> 69.37Improved
train partner with SupCT instead of unsupervised contrastive (ablation)PAL · miniImageNet 5-way 1-shotaccuracy (%): 65.89 -> 69.37Improved
add feature-level alignment to logit-level alignment (ablation)PAL · miniImageNet 5-way 1-shotaccuracy (%): 66.35 -> 69.37Improved
add logit-level alignment to feature-level alignment (ablation)PAL · miniImageNet 5-way 1-shotaccuracy (%): 68.03 -> 69.37Improved
feature-level alignment alone over no alignment (ablation)PAL · miniImageNet 5-way 1-shotaccuracy (%): 63.76 -> 68.03Improved
use L_KL instead of L_logit with feature alignment (ablation)PAL · miniImageNet 5-way 1-shotaccuracy (%): 69.37 -> 68.75Hurt
use L_KL alone instead of L_logit alone (ablation)PAL · miniImageNet 5-way 5-shotaccuracy (%): 81.32 -> 80.58Hurt

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