PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
September 20, 2025

Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning

View Full Paper
Ask AI
Bookmark
Share

Authors

XYXudong YanSFSonghe FengYZYang Zhang

Discussion

Loading...

Member takes

Overview

This framework enhances attribute disentanglement and reduces overconfidence in models for zero-shot learning, emphasizing multimodal embedding benefits.

Key Points

  • State-of-the-art performance was achieved on three challenging datasets through a new framework.
  • The method utilizes MLLM embeddings, which provide superior representation for unseen attributes and objects.
  • Disentanglement challenges are addressed using feature adaptive aggregation and learnable condition masks, enhancing model robustness.
  • Attribute smoothing is employed to mitigate overconfidence in seen compositions, improving generalization capabilities.

Cite This Study

Yan et al. (2025) studied this question.

synapsesocial.com/papers/68d469d631b076d99fa67085https://doi.org/10.24963/ijcai.2025/243
View Full Paper
Ask AI
Bookmark
Share