Unified contrastive learning in image-text-label space
Visual recognition is recently learned via either supervised learning on human-annotated
image-label data or language-image contrastive learning with webly-crawled image-text …
image-label data or language-image contrastive learning with webly-crawled image-text …
Data efficient language-supervised zero-shot recognition with optimal transport distillation
Traditional computer vision models are trained to predict a fixed set of predefined
categories. Recently, natural language has been shown to be a broader and richer source of …
categories. Recently, natural language has been shown to be a broader and richer source of …
Ra-clip: Retrieval augmented contrastive language-image pre-training
Abstract Contrastive Language-Image Pre-training (CLIP) is attracting increasing attention
for its impressive zero-shot recognition performance on different down-stream tasks …
for its impressive zero-shot recognition performance on different down-stream tasks …
I2mvformer: Large language model generated multi-view document supervision for zero-shot image classification
Recent works have shown that unstructured text (documents) from online sources can serve
as useful auxiliary information for zero-shot image classification. However, these methods …
as useful auxiliary information for zero-shot image classification. However, these methods …
I2dformer: Learning image to document attention for zero-shot image classification
Despite the tremendous progress in zero-shot learning (ZSL), the majority of existing
methods still rely on human-annotated attributes, which are difficult to annotate and scale …
methods still rely on human-annotated attributes, which are difficult to annotate and scale …
Sus-x: Training-free name-only transfer of vision-language models
V Udandarao, A Gupta… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Abstract Contrastive Language-Image Pre-training (CLIP) has emerged as a simple yet
effective way to train large-scale vision-language models. CLIP demonstrates impressive …
effective way to train large-scale vision-language models. CLIP demonstrates impressive …
Domain-aware visual bias eliminating for generalized zero-shot learning
Generalized zero-shot learning aims to recognize images from seen and unseen domains.
Recent methods focus on learning a unified semantic-aligned visual representation to …
Recent methods focus on learning a unified semantic-aligned visual representation to …
Non-contrastive learning meets language-image pre-training
Contrastive language-image pre-training (CLIP) serves as a de-facto standard to align
images and texts. Nonetheless, the loose correlation between images and texts of web …
images and texts. Nonetheless, the loose correlation between images and texts of web …
Data-efficient language-supervised zero-shot learning with self-distillation
Traditional computer vision models are trained to predict a fixed set of predefined
categories. Recently, natural language has been shown to be a broader and richer source of …
categories. Recently, natural language has been shown to be a broader and richer source of …
Progressive ensemble networks for zero-shot recognition
Despite the advancement of supervised image recognition algorithms, their dependence on
the availability of labeled data and the rapid expansion of image categories raise the …
the availability of labeled data and the rapid expansion of image categories raise the …