Balancing Representations by Identifying and Generating Under-represented Data
cs.CV, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- PASS: An ImageNet replacement for self-supervised pretraining without humans
- Synthetic Data from Diffusion Models Improves ImageNet Classification
- On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning
- Learning to See by Looking at Noise
- A Simple Framework for Contrastive Learning of Visual Representations
- Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets
- Is synthetic data from generative models ready for image recognition?
- Denoising Diffusion Probabilistic Models
- Generative Models as a Data Source for Multiview Representation Learning
- Self-Damaging Contrastive Learning
- Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data
- Fine-Grained Visual Classification of Aircraft
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
- Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion Models
- DINOv2: Learning Robust Visual Features without Supervision
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- DINOv3
- Out-of-Distribution Detection with Deep Nearest Neighbors
- Effective Data Augmentation With Diffusion Models
- DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation
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