Research map / Label-efficient and robust learning / Self-supervised and contrastive
Adaptive and Multi-scale Affinity Alignment for Hierarchical Contrastive Learning
Jiawei Huang, Minming Li, Hu Ding
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an adaptive, multi-scale affinity alignment objective for contrastive self-supervised learning that aims to preserve fine-grained and hierarchical semantic relationships.
Problem
Standard contrastive self-supervised learning captures broad categorical distinctions but struggles to preserve fine-grained and hierarchical relationships in data.
Approach
Replaces strict instance-level alignment with adaptive, multi-scale affinity alignment so representations are aligned to semantic structure at several granularities rather than only to a single positive pair. Full method details are unavailable, so this is based on the abstract only.
Closest papers by meaning
- Variational Supervised Contrastive Learning (NeurIPS 2025 · similarity 0.87)
- On the Similarities of Embeddings in Contrastive Learning (ICML 2025 · similarity 0.87)
- Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining (NeurIPS 2025 · similarity 0.86)
- Aligning Visual Contrastive learning models via Preference Optimization (ICLR 2025 · similarity 0.86)
- Aligning Text to Image in Diffusion Models is Easier Than You Think (NeurIPS 2025 · similarity 0.86)
- Diversity Is All You Need for Contrastive Learning: Spectral Bounds on Gradient Magnitudes (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
