DenseTwins: Dense Modality Decoupling for Multimodal Self-Supervision
cs.CV, cs.AI, cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/CarloSgaravatti/DenseTwins
Terminology
Sources
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Indoor Semantic Segmentation using depth information
- Momentum Contrast for Unsupervised Visual Representation Learning
- Improved Baselines with Momentum Contrastive Learning
- Improving Dense Contrastive Learning with Dense Negative Pairs
- DINOv2: Learning Robust Visual Features without Supervision
- BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding
- An Information Criterion for Controlled Disentanglement of Multimodal Data
- iBOT: Image BERT Pre-Training with Online Tokenizer
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