AI Paper Atlas

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

How to Trust Unlabeled Data? Instance Credibility Inference for Few-Shot Learning

Yikai Wang, Li Zhang, Yuan Yao, Yanwei Fu

TPAMI 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 55 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 ICI credibility selection instead of random selection (ablation)ICI-R · miniImageNet 1-shot (transductive)accuracy: 67.54 -> 71.19Improved
use ICI selection instead of nearest-neighbor selection (ablation)ICI-R · miniImageNet 1-shot (transductive)accuracy: 69.80 -> 71.19Improved
use ICI selection instead of classifier confidence (ablation)ICI-R · miniImageNet 1-shot (transductive)accuracy: 70.57 -> 71.19Improved
use ICI (x-axis) selection instead of coefficient norm (y-axis) (ablation)ICI-R · miniImageNet 5-shot (semi-supervised)accuracy: 81.49 -> 82.32Improved
select samples iteratively (2 iterations of 3) rather than once (ablation)ICI · miniImageNetaccuracy: ICI(3) with 6 images beats ICI(8) with 8 imagesImproved
use logistic regression instead of kNN as the classifier (ablation)ICI-R · miniImageNet 5-shot (transductive)accuracy: 79.88 -> 83.27Improved
use logistic regression instead of SVM as the classifier (ablation)ICI-R · miniImageNet 5-shot (transductive)accuracy: 82.76 -> 83.27Improved
reduce features to d=5 with LLE instead of no reduction (d=512) (ablation)ICI-R · miniImageNet 1-shotaccuracy: 67.08 -> 72.39Improved
use LLE instead of MDS for dimension reduction (ablation)ICI-R · miniImageNet 1-shotaccuracy: 68.05 -> 72.39Improved
use LLE instead of spectral embedding (ablation)ICI-R · miniImageNet 1-shotaccuracy: 72.43 -> 72.39No clear effect
add more unlabeled data (30/50 instead of 15/15)ICI-R · miniImageNet 1-shot (semi-supervised)accuracy: 72.32 -> 73.12Improved
apply ICI on CAN featuresICI-R · miniImageNet 1-shotaccuracy: 67.19 -> 70.53Improved

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