arXiv AI
Balanced Prompt Adaptation against Entropy-Induced Collapse for Test-Time Binary Segmentation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 2
Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
arXiv:2606. 02339v1 Announce Type: new Abstract: Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood.
arXiv Computer Vision
Aug 25
ENCORE: Entropy-Guided Cropping and Attention Regularization for Robust Vision--Language Understanding
arXiv:2608.22996v1 Announce Type: new Abstract: Vision-Language Models (VLMs) perform well on diverse vision-language tasks, but transformer-based visual encoders split images into fixed-resolution s...
Hugging Face Trending Papers
Aug 24
ENCORE: Entropy-Guided Cropping and Attention Regularization for Robust Vision--Language Understanding
Vision-Language Models (VLMs) perform well on diverse vision-language tasks, but transformer-based visual encoders split images into fixed-resolution sub-images, compromising object integrity in light...
arXiv Machine Learning
Aug 27
Fairness-Aware Test-Time Prompt Tuning
The paper introduces FairTPT, a fairness-aware test‑time prompt tuning method for vision‑language models like CLIP. It jointly minimizes target marginal entropy while maximizing spurious marginal entropy to reduce bias under subpopulation shifts. Experiments show that standard episodic test‑time adaptation can worsen disparities, but FairTPT outperforms existing debiasing methods while preserving overall performance.
arXiv AI
Jul 2
ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions
arXiv:2503. 09399v4 Announce Type: replace-cross Abstract: Large-scale image classification datasets exhibit strong compositional biases: objects tend to be centered, appear at characteristic scales, and co-occur with class-specific context.
arXiv Machine Learning
Sep 1
Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation
arXiv:2608.29923v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) relies on vision-language alignment to recognize arbitrary text-defined categories, yet this alignment i...