Improving Diffusion-Based Augmentation for Data-Scarce Image Classification via Mask-Guided Reference Attention and Repulsive Noise Optimization
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/hvcl/MGRAttn-RNO
Terminology
Sources
- SAM 3: Segment Anything with Concepts
- Is synthetic data from generative models ready for image recognition?
- Visual Style Prompting with Swapping Self-Attention
- Diverse Text-to-Image Generation via Contrastive Noise Optimization
- Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection
- HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models
- Fine-Grained Visual Classification of Aircraft
- Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- DINOv2: Learning Robust Visual Features without Supervision
- Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
- Denoising Diffusion Implicit Models
- SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems
- mixup: Beyond Empirical Risk Minimization
- Salient Concept-Aware Generative Data Augmentation
- ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection
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