Image Classification

Smaller image patches improve vision transformer performance, defying conventional wisdom and revealing a new scaling law for enhanced visual understanding.

iFormer: A new family of mobile hybrid vision networks that expertly blends ConvNeXt’s fast local feature extraction with the efficient global modeling of self-attention, achieving top-tier accuracy a…

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.

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 achieves state-of-the-art performance in various vision tasks using a novel Meta Mobile Block, pushing the 5M parameter lightweight model frontier.