AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

DETA: Denoised Task Adaptation for Few-Shot Learning

Ji Zhang, Lianli Gao, Xu Luo, Hengtao Shen, Jingkuan Song

ICCV 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 42 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 DETA image-denoising to adapter/finetuning task adaptationTSA on URL (RN-18) · Meta-Dataset image-denoising (avg of 10)accuracy (%): 75.5 -> 77.3Improved
add DETA to F-NCC on Swin-TF-NCC on Swin-T · Meta-Dataset image-denoising (avg of 10)accuracy (%): 81.3 -> 85.4Improved
add DETA label-denoising under 30% label noiseF-NCC on Swin-T · Meta-Dataset label noise 30% (avg of 10)accuracy (%): 71.6 -> 77.3Improved
add DETA on top of state-of-the-art TSA (standard protocol, single-domain)TSA on URL (RN-18) · Meta-Dataset standard protocol, single-domain (avg of 10)accuracy (%): 70.7 -> 72.8Improved
add DETA to eTT on AircrafteTT on DINO (ViT-S) · Aircraft (Meta-Dataset)accuracy (%): 68.1 -> 67.7Hurt
use cropped regions as plain augmentation without DETA components (ablation)MoCo F-NCC · Meta-Dataset image-denoising (avg of 10)accuracy (%): 73.0 -> 73.8No clear effect
add out-of-class relevance aggregation to CoRA (ablation)DETA · Meta-Dataset image-denoising (avg of 10)accuracy (%): 74.1 -> 74.4Improved
add global dispersion loss to CoRA + local compactness loss (ablation)DETA · Meta-Dataset label noise 30% (avg of 10)accuracy (%): 65.4 -> 67.1Improved
add local compactness loss to CoRA + global dispersion loss (ablation)DETA · Meta-Dataset image-denoising (avg of 10)accuracy (%): 75.2 -> 75.8Improved
add momentum accumulator for image weights at inference (ablation)DETA · Meta-Dataset label noise 30% (avg of 10)accuracy (%): 67.1 -> 68.0Improved
increase ratio of label-noisy support samples from 10% to 70%TSA on URL (RN-18) · Meta-Dataset label noise (avg of 10)accuracy (%): 72.8 -> 38.3Hurt

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