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:2607.09086v2 Announce Type: replace
Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfo...
By Jie Zhu, Ivy Zhang, Minchul Kim, Xiaoming Liu
arXiv:2608.22368v1 Announce Type: new
Abstract: While linear attention is a compelling mechanism for high-resolution object detection due to its reduced cost for global token mixing, converting the S...
By Huaiyuan Qin, Gabriel James Goenawan, Zihang Lin, Muli Yang, Hongyuan Zhu
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:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.
By Weinuo Ou
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
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
FocusOVD is an open‑vocabulary object detector that improves small‑object detection by refining geometric and contextual features without altering the frozen vision‑language model backbone. It introduces a Reweighted Cross‑scale Feature Fusion module to balance shallow and deep features, a Residual Pinwheel‑shaped Gated Convolution module to enhance local geometry in high‑resolution features, and a Residual Convolutional Gated Linear Unit module to suppress background activations and boost region‑of‑interest discriminability. Experiments on COCO‑OVD and LVIS‑OVD show that FocusOVD outperforms state‑of‑the‑art methods, achieving a novel‑category AP of 36.3% on COCO‑OVD and an overall AP of 33.7% on LVIS‑OVD.
By Hanlin Kou, Beiqi Bai, Li Chen, Youjia Jing, Shupan Li, Mingyuan Jiu
arXiv:2609.09863v1 Announce Type: new
Abstract: Choosing a deep learning architecture for label-free single-cell classification remains an open question, with microscopy benchmarks reporting conflict...
By Philip Graemer, Giuseppe Di Caprio
RT-DETRv4 introduces a cost‑effective distillation framework that leverages Vision Foundation Models to improve lightweight real‑time object detectors. The method uses a Deep Semantic Injector to embed high‑level VFM representations into deep detector layers and a Gradient‑guided Adaptive Modulation strategy to adjust semantic transfer intensity based on gradient norms. These techniques yield consistent performance gains across DETR‑based models without adding inference overhead, achieving state‑of‑the‑art COCO AP scores at high FPS.
By Zijun Liao, Yian Zhao, Xin Shan, Yu Yan, Chang Liu, Lei Lu, Xiangyang Ji, Jie Chen
The paper introduces QK Product Steering, a data‑free, training‑free method that edits the query‑key product in vision‑language models to reduce object hallucination. By suppressing a few dominant singular modes in selected middle layers and mapping the edited product back to query weights, the approach lowers hallucination rates without affecting inference cost. Experiments on three GQA‑based VLMs show a 4.0% average reduction in CHAIR$_s$, with the effect localized to symmetric mutual‑attention channels.
By Karn Tiwari, Varnith Chordia, Prathosh A P