ChanSFormer: A Channel Agnostic Vision Transformer for Multi-Channel Cell Painting Images
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/cvlab-stonybrook/ChanSFormer
Terminology
Sources
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words
- DINOv2: Learning Robust Visual Features without Supervision
- iBOT: Image BERT Pre-Training with Online Tokenizer
- Isolated Channel Vision Transformers: From Single-Channel Pretraining to Multi-Channel Finetuning
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- Contextual Vision Transformers for Robust Representation Learning
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