AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Mitigating Endogenous Confirmation Bias in Noisy Label Learning for Vision-Language Models

Feiyang Ning, Xinyang Chen

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 1 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 Phase 2 noisy label refinement (ablation)DKAF · Avg of CIFAR-100, Cars, CUB (Sym. 0.6)accuracy: 82.57 -> 85.23Improved
add Phase 3 full fine-tuning on clean and corrected samples (ablation)DKAF · Avg of CIFAR-100, Cars, CUB (Sym. 0.6)accuracy: 75.38 -> 82.57Improved
add Phase 1 clean sample selection (ablation)DKAF · Avg of CIFAR-100, Cars, CUB (Sym. 0.6)accuracy: 69.39 -> 75.38Improved
add Phase 3 on Stanford-Cars (ablation)DKAF · Stanford-Cars (Sym. 0.6)accuracy: 77.04 -> 86.94Improved
add Phase 2 on CIFAR-100 (ablation)DKAF · CIFAR-100 (Sym. 0.6)accuracy: 86.41 -> 87.85Improved
use DKAF instead of second-best methodDKAF · CUB-200-2011 (Sym. 0.6)accuracy: 73.08 -> 78.22Improved
use DKAF instead of second-best methodDKAF · OxfordPets (Sym. 0.6)accuracy: 88.67 -> 92.72Improved
use DKAF instead of second-best methodDKAF · Stanford-Cars (Sym. 0.6)accuracy: 86.35 -> 89.61Improved
use DKAF instead of DEFT on real-world noisy dataDKAF · CIFAR-100Naccuracy: 79.04 -> 81.91Improved
use DKAF instead of DEFT on real-world noisy dataDKAF · Clothing-1Maccuracy: 72.44 -> 73.36Improved
use DKAF instead of DEFT on real-world noisy dataDKAF · WebVisionaccuracy: 85.12 -> 85.35No clear effect
use cross-modal collaborative pseudo-labeling instead of DEFT self-training on hard class BombayDKAF · OxfordPets Bombay class (40% noise)F1-score: 15.87 -> 99.15Improved

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