Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data
Unsupervised domain adaptation aims to align a labeled source domain and an unlabeled
target domain, but it requires to access the source data which often raises concerns in data …
target domain, but it requires to access the source data which often raises concerns in data …
Chils: Zero-shot image classification with hierarchical label sets
Open vocabulary models (eg CLIP) have shown strong performance on zero-shot
classification through their ability generate embeddings for each class based on their …
classification through their ability generate embeddings for each class based on their …
Msdn: Mutually semantic distillation network for zero-shot learning
The key challenge of zero-shot learning (ZSL) is how to infer the latent semantic knowledge
between visual and attribute features on seen classes, and thus achieving a desirable …
between visual and attribute features on seen classes, and thus achieving a desirable …
Improving zero-shot generalization for clip with synthesized prompts
With the growing interest in pretrained vision-language models like CLIP, recent research
has focused on adapting these models to downstream tasks. Despite achieving promising …
has focused on adapting these models to downstream tasks. Despite achieving promising …
Transzero: Attribute-guided transformer for zero-shot learning
Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic
knowledge from seen classes to unseen ones. Semantic knowledge is learned from attribute …
knowledge from seen classes to unseen ones. Semantic knowledge is learned from attribute …
En-compactness: Self-distillation embedding & contrastive generation for generalized zero-shot learning
Generalized zero-shot learning (GZSL) requires a classifier trained on seen classes that can
recognize objects from both seen and unseen classes. Due to the absence of unseen …
recognize objects from both seen and unseen classes. Due to the absence of unseen …
Progressive semantic-visual mutual adaption for generalized zero-shot learning
Abstract Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge
transferred from the seen domain, relying on the intrinsic interactions between visual and …
transferred from the seen domain, relying on the intrinsic interactions between visual and …
Graph knows unknowns: Reformulate zero-shot learning as sample-level graph recognition
Zero-shot learning (ZSL) is an extreme case of transfer learning that aims to recognize
samples (eg, images) of unseen classes relying on a train-set covering only seen classes …
samples (eg, images) of unseen classes relying on a train-set covering only seen classes …
Duet: Cross-modal semantic grounding for contrastive zero-shot learning
Zero-shot learning (ZSL) aims to predict unseen classes whose samples have never
appeared during training. One of the most effective and widely used semantic information for …
appeared during training. One of the most effective and widely used semantic information for …
Semantic-aware representation blending for multi-label image recognition with partial labels
Training the multi-label image recognition models with partial labels, in which merely some
labels are known while others are unknown for each image, is a considerably challenging …
labels are known while others are unknown for each image, is a considerably challenging …