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
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
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.
By Zimian Wei, Tianqi Zhang, Hengyue Pan
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
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...
By Ali Mehizel, Oussama Khaldi
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:2608. 08575v1 Announce Type: cross Abstract: Accurate 3D medical image segmentation requires the integration of long-range anatomical context with fine boundary detail.
By Zheyang Jing, Qin Lu, Jianwang Li, Yujie Yang, Chen Yi, Shaofeng Jiang
arXiv:2610.31848v1 Announce Type: new
Abstract: Imaging Flow Cytometry (IFC) generates large multispectral datasets, yet the need for expert annotations bottlenecks the development of supervised deep...
By Angelo Jovin Yamachui Sitcheu, Roxana-Teodora Fetescu, Thomas Lautenschlager, Nils Friederich, Linus Schilpp, Stephan Allgeier, Luca Deininger, Daniel H\"ubschmann, Ralf Mikut
The paper introduces SparK-SAR, a sparse convolutional masked pretraining framework that leverages ConvNeXt for high‑resolution Sentinel‑1 GRD SAR data. It presents three key contributions: a domain‑adapted ConvNeXt‑RS encoder with a reduced stem stride, a lightweight ConvNeXt‑512 decoder that cuts VRAM usage while matching UNet accuracy, and an analysis of FP16 instability and layer‑wise learning‑rate decay benefits. Experiments on four Copernicus‑Bench S1GRD tasks show that the 27.8 M‑parameter ConvNeXt‑RS encoder outperforms a larger ViT baseline on most tasks and demonstrates strong data efficiency, with classification saturating at 10–25 % of the SSL4EO‑S12 corpus.
By Yuki Natsume, Sang-Ho Yun, Chai Kiat Yeo
arXiv:2603. 18846v3 Announce Type: replace-cross Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL).
By Samuel Ofosu Mensah, Camila Roa, Kerol Djoumessi, Philipp Berens
Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers. They convert tabular data into image representations, mapping each feature at a fixed pixel location derived from a dimensionality-reduction method (e.
Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.