Skip to main content

Image Classification

MLLM-as-a-Judge for Image Safety without Human Labeling
·6596 words·31 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Image Classification 🏢 Meta AI
Zero-shot image safety judgment is achieved using MLLMs and a novel method called CLUE, objectifying safety rules, and significantly reducing the need for human labeling.
Learned Compression for Compressed Learning
·2966 words·14 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Image Classification 🏢 University of Texas at Austin
WaLLOC: a novel neural codec boosts compressed-domain learning by combining wavelet transforms with asymmetric autoencoders, achieving high compression ratios with minimal computation and uniform dime…
EMOv2: Pushing 5M Vision Model Frontier
·6258 words·30 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Image Classification 🏢 Tencent AI Lab
EMOv2 achieves state-of-the-art performance in various vision tasks using a novel Meta Mobile Block, pushing the 5M parameter lightweight model frontier.