arXiv Computer Vision
ChanSFormer: A Channel Agnostic Vision Transformer for Multi-Channel Cell Painting Images
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 21
Extending Decoupled Attention to Dense Prediction and Masked Training for Multi-Channel Images
The paper introduces an extension of the Decoupled Vision Transformer (DC‑ViT) to handle multi‑channel imaging (MCI) data, where each channel carries a distinct semantic signal. By tokenizing each channel separately and then decoupling intra‑channel from inter‑channel updates, the model preserves channel‑specific features. The authors further enable independent per‑channel masking by solving a linear assignment between retained patches, allowing masked training without restricting visible tokens. Experiments on fluorescence microscopy, imaging mass cytometry, and satellite imaging datasets demonstrate that this approach outperforms the strongest Multi‑Channel Vision Transformer baselines on both classification and dense‑prediction tasks.
arXiv Computer Vision
Oct 12
Learning Features, Not Layouts: Feature-Axis Attention as a Transfer Prior for Medical Imaging
The paper introduces FAD‑ViT, a vision transformer that decouples spatial and feature axes of global attention, making feature‑axis attention the primary operator. Experiments on 23 medical imaging tasks show that shifting global attention from spatial to feature leaves from‑scratch performance unchanged but significantly boosts transfer learning, achieving up to three times the gain with fewer parameters and lower compute. The study demonstrates that prioritizing feature‑axis attention is a simple, cost‑effective design choice for improving medical image transfer.
arXiv AI
Oct 27
ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer
The paper introduces ACSAN, an All‑Convolutional Self‑Attention Network that replaces the fully‑connected matrix multiplications of Vision Transformers with convolution operations. Its core module, Dynamic Convolutional Self‑Attention (DCSA), uses multi‑scale dilated convolutions to produce Query, Key, and Value tensors, and combines spatial and channel self‑attention into a single output. Experiments on CIFAR‑10, CIFAR‑100, and ImageNet‑1k demonstrate that ACSAN attains competitive or superior classification accuracy to ViT while using comparable or fewer parameters, and ablation studies confirm the positive contribution of each component.
arXiv Computer Vision
Sep 22
CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention
arXiv:2609.24494v1 Announce Type: new Abstract: Accurate monocular depth estimation serves as a core enabler for single camera scene understanding. However, existing self-supervised monocular depth e...
arXiv Computer Vision
Sep 22
Rethinking Vision Architectures with Gated Linear Attention and KAN
arXiv:2609.22506v1 Announce Type: new Abstract: Vision Transformers allocate most parameters to multi-layer perceptrons (MLPs) for channel mixing, while token interactions usually rely on quadratic m...
arXiv Computer Vision
Sep 1
ConCA: Concentration-Aware Channel Attention for Fine-Grained Visual Recognition
arXiv:2608.30183v1 Announce Type: cross Abstract: Lightweight channel attention mechanisms are widely used in image classification, yet their effectiveness in fine-grained visual recognition (FGVR) r...