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.
By Umar Marikkar, Sameed Husain, Muhammad Awais, Sara Atito
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...
By Yu-Sheng Liu, Yu-Chen Tung
arXiv:2607. 12526v1 Announce Type: new Abstract: Interpreting a neural network requires understanding what its internal features extract from a particular input.
By Kaixiang Shu
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.
By Aon Safdar, Mohamed Saadeldin
arXiv:2611.06015v1 Announce Type: new
Abstract: High-content multi-channel imaging, from Cell Painting assays to remote sensing, is central to modern scientific pipelines. Because these channels are...
By Jingwei Zhang, Srinivasan Sivanandan, Dimitris Samaras
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...
By Xuezhi Xiang, Jiayao Liu, Heqi Xiang, Yuqi Hu, Yiming Chen, Shanjun Zhang
The paper investigates whether keeping non‑spatial register tokens in vision transformer decoders improves image reconstruction and generation. Using representation autoencoders with frozen register‑equipped encoders, the authors show that joint self‑attention over both patch and register tokens yields better reconstruction quality on ImageNet‑1K, with lower FID scores and higher PSNRs compared to patch‑only baselines. For generation, a multi‑head attention pooling predictor recovers register features from sampled patches, further reducing FID by nearly 10% over the patch‑only approach.
By David Jacob Drexlin, Julius Hense, Jonas Dippel
arXiv:2606. 17037v1 Announce Type: cross Abstract: Oppenheim and Lim (1981) showed that natural images stay recognizable when reconstructed from their Fourier phase alone, while the magnitude carries little of their identity.
By Alper Y{\i}ld{\i}r{\i}m
arXiv:2606. 04772v1 Announce Type: cross Abstract: Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience.
By Hoang-Son Vo, Van-Hung Bui, Minh-Huy Mai-Duc, Tien-Dung Mai, Soo-Hyung Kim
arXiv:2607. 18625v1 Announce Type: cross Abstract: Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones.
By Jin Yu, Juyoun Park
arXiv:2606. 09928v1 Announce Type: cross Abstract: The Forward-Forward (FF) algorithm offers a biologically inspired alternative to backpropagation by replacing gradient-based credit assignment with local, forward-only objectives.
By Mohammadnavid Ghader, Saeed Reza Kheradpisheh, Bahar Farahani, Mahmood Fazlali
Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning the necessity of SSMs for vision.