AI Paper Atlas

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

Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization

Ran Tao, Hao Chen, Marios Savvides

CVPR 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Alignment-based few-shot metric learning · 0 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 margin-based uncertainty weighting (top-2 probabilities) to transductive fine-tuning (ablation)TF · Meta-Dataset Imagenet-only evaluationaccuracy: around 6% performance gain over equally weighting unlabeled samplesImproved
Use top-2 probabilities rather than all probabilities for uncertainty weighting (ablation)Margin-based uncertainty weighting · Meta-Dataset Imagenet-only evaluationaccuracyImproved
Add margin-based uncertainty weighting to TF (ablation)TF · Meta-Dataset, 10 datasetsaccuracy: from 1.27% on MSCOCO to 13.54% on the Traffic signImproved
Add probability regularization to TF without MW (ablation)TF · Meta-Dataset, 10 datasetsaccuracy: over 7 datasets from 0.29% on DTD to 1.79% on Traffic signImproved
Add probability regularization to TF with MW (ablation)TF with MW · Meta-Dataset, 10 datasetsaccuracy: from 0.45% on Fungi to 4.27% on the Traffic signImproved
Use uniform prior and a per-query estimated marginal distribution for probability regularization (ablation)Probability regularization · ILSVRC-2012 validation, uniform and stochastic query setsaccuracyImproved
Use transductive fine-tuning rather than support-set-only fine-tuning (ablation)TF-MP · Meta-Dataset, 1-shot casesaccuracy: over 10% compared with fine-tuningImproved
Use transductive fine-tuning without uncertainty weighting or probability regularization (ablation)TF · Meta-Dataset, 10 datasetsaccuracyHurt
Add TF-MP to TSATSA · Meta-Dataset All-datasets evaluationaccuracy: 0.82% average marginImproved

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