Muli Yang
YOU?
Author Swipe
View article: Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning
Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning Open
Self-supervised learning (SSL) conventionally relies on the instance consistency paradigm, assuming that different views of the same image can be treated as positive pairs. However, this assumption breaks down for non-iconic data, where di…
View article: Hierarchical Prompt Learning for Compositional Zero-Shot Recognition
Hierarchical Prompt Learning for Compositional Zero-Shot Recognition Open
Compositional Zero-Shot Learning (CZSL) aims to imitate the powerful generalization ability of human beings to recognize novel compositions of known primitive concepts that correspond to a state and an object, e.g., purple apple. To fully …
View article: Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning
Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning Open
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions formed from seen state and object during training. Since the same state may be various in the visual appearance while entangled with different objects, CZSL is s…
View article: Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies
Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies Open
Deep metric learning plays a key role in various machine learning tasks. Most of the previous works have been confined to sampling from a mini-batch, which cannot precisely characterize the global geometry of the embedding space. Although …
View article: Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval
Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval Open
Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a specific cross-modal retrieval task for searching natural images given free-hand sketches under the zero-shot scenario. Most existing methods solve this problem by simultaneously projec…
View article: Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval
Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval Open
Zero-shot sketch-based image retrieval (ZS-SBIR) is a specific cross-modal retrieval task for searching natural images given free-hand sketches under the zero-shot scenario. Most existing methods solve this problem by simultaneously projec…
View article: Fully-Featured Attribute Transfer
Fully-Featured Attribute Transfer Open
Image attribute transfer aims to change an input image to a target one with expected attributes, which has received significant attention in recent years. However, most of the existing methods lack the ability to de-correlate the target at…