Research map / Label-efficient and robust learning / Recognition and long-tail
SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision
Read the paperCheck your idea against 108,967 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 SEGA, a method for learning hash codes from noisy supervision that shapes the geometric structure of the hash space rather than only denoising labels.
Problem
Learning hash codes for image and cross-modal retrieval when training labels are noisy; existing methods focus on label denoising and ignore the geometric structure of the hash space.
Approach
Shifts the focus from label denoising to shaping the geometry of the hash space to obtain stable hash codes under noisy supervision.
Closest papers by meaning
- UDCH: Unsupervised Dynamic Weighted Cluster-cooperative Hashing for Cross-modal Retreival (AAAI 2026 · similarity 0.88)
- SADIH: Semantic-Aware DIscrete Hashing (AAAI 2019 · similarity 0.88)
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization (ICML 2025 · similarity 0.86)
- Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.86)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.86)
- Generalized Debiased Semi-Supervised Hashing for Large-Scale Image Retrieval (AAAI 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.