paper-with-me

Papers

Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization

2023-08-14 · ICCV 2023 1 · Jungsoo Lee, Debasmit Das, Jaegul Choo, Sungha Choi

Test-time adaptation (TTA) methods, which generally rely on the model's predictions (e.g., entropy minimization) to adapt the source pretrained model to the unlabeled target domain, suffer from noisy signals originating from 1) incorrect or 2) open-set predictions. Long-term stable adaptation is hampered by such noisy signals, so training models without such error accumulation is crucial for practical TTA. To address these issues, including open-set TTA, we propose a simple yet effective sample selection method inspired by the following crucial empirical finding. While entropy minimization compels the model to increase the probability of its predicted label (i.e., confidence values), we found that noisy samples rather show decreased confidence values. To be more specific, entropy minimization attempts to raise the confidence values of an individual sample's prediction, but individual confidence values may rise or fall due to the influence of signals from numerous other predictions (i.e., wisdom of crowds). Due to this fact, noisy signals misaligned with such 'wisdom of crowds', generally found in the correct signals, fail to raise the individual confidence values of wrong samples, despite attempts to increase them. Based on such findings, we filter out the samples whose confidence values are lower in the adapted model than in the original model, as they are likely to be noisy. Our method is widely applicable to existing TTA methods and improves their long-term adaptation performance in both image classification (e.g., 49.4% reduced error rates with TENT) and semantic segmentation (e.g., 11.7% gain in mIoU with TENT).

📄 PDF Abstract BibTeX arXiv:2308.06879

Code (1)

gaozhengqing/unient pytorch

Tasks

image-classificationImage ClassificationSemantic SegmentationTest-time Adaptation

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Effectiveness of Vision Language Models for Open-world Single Image Test Time Adaptation

2024-06-01 · Manogna Sreenivas, Soma Biswas

We propose a novel framework to address the real-world challenging task of Single Image Test Time Adaptation in an open and dynamic environment. We leverage large scale Vision Language Models like CLIP to enable real tim…

Contrastive LearningDomain AdaptationOut of Distribution (OOD) DetectionTest-time Adaptation

WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge

2024-01-12 · Wenbin Wang, Liang Ding, Li Shen, Yong Luo 외

Sentiment analysis is rapidly advancing by utilizing various data modalities (e.g., text, image). However, most previous works relied on superficial information, neglecting the incorporation of contextual world knowledge…

Multimodal Sentiment AnalysisSentiment AnalysisWorld Knowledge

ProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Models

2026-02-27 · Wei Luo, Yangfan Ou, Jin Deng, Zeshuai Deng 외 arxiv

Large-scale Vision-Language Models (VLMs) exhibit strong zero-shot recognition, yet their real-world deployment is challenged by distribution shifts. While Test-Time Adaptation (TTA) can mitigate this, existing VLM-based…

Test-time Adaptation

MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning

2026-02-03 · Xiaoyu Tao, Mingyue Cheng, Ze Guo, Shuo Yu 외 arxiv

Time series forecasting (TSF) plays a critical role in decision-making for many real-world applications. Recently, large language model (LLM)- based forecasters have made promising advancements. Despite their effectivene…

Time Series Forecasting

Effective Sample Size, Dimensionality, and Generalization in Covariate Shift Adaptation

2020-10-02 · Felipe Maia Polo, Renato Vicente

In supervised learning, training and test datasets are often sampled from distinct distributions. Domain adaptation techniques are thus required. Covariate shift adaptation yields good generalization performance when dom…

Dimensionality ReductionDomain Adaptationfeature selectionGeneralization Bounds