SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-supervised No-Reference Image Quality Assessment
cs.CV, cs.AI, cs.LG
Submitted: 2026-03-14
Updated: 2026-11-17
Code: https://github.com/Mahdi-Naseri/SHAMISA
Terminology
Sources
- Graph Barlow Twins: A self-supervised representation learning framework for graphs
- ExGRG: Explicitly-Generated Relation Graph for Self-Supervised Representation Learning
- MUSIQ: Multi-scale Image Quality Transformer
- From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
- A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Subjective and Objective Quality Assessment of Image: A Survey
- Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods
- Self-labelling via simultaneous clustering and representation learning
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs