Skip to content
conftrace_

dynamic margin loss

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

pre-trained contextual embedding (1) taxonomy-path ranking (1) hard negative (1) hypernym detection (1) taxonomy expansion (1) compositional reasoning (1) pre-trained language model (1) vision-language model (1) multimodal learning (1) self-supervised learning (1)

Papers

Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models IJCAI 2025 TEMP: Taxonomy Expansion with Dynamic Margin Loss through Taxonomy-Paths EMNLP 2021