MuMIC -- Multimodal Embedding for Multi-label Image Classification with Tempered Sigmoid. (arXiv:2211.05232v1 [cs.CV])

Multi-label image classification is a foundational topic in various domains.
Multimodal learning approaches have recently achieved outstanding results in
image representation and single-label image classification. For instance,
Contrastive Language-Image Pretraining (CLIP) demonstrates impressive
image-text representation learning abilities and is robust to natural
distribution shifts. This success inspires us to leverage multimodal learning
for multi-label classification tasks, and benefit from contrastively learnt
pretrained models. We propose the Multimodal Multi-label Image Classification
(MuMIC) framework, which utilizes a hardness-aware tempered sigmoid based
Binary …

arxiv classification embedding image multimodal sigmoid