arXiv Computer Vision
LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba
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 30
Generalizing Geometry-Guided Mamba as a Plug-and-Play Context Module for CNN-based Semantic Segmentation
arXiv:2606.08866v2 Announce Type: replace Abstract: CNN-based semantic segmentation networks usually rely on context heads such as ASPP, PPM, or attention modules to enlarge the receptive field. Thes...
arXiv Computer Vision
Aug 27
CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression
CrossMambaTuning is a new framework that adapts pretrained learned image compression models to machine vision tasks with minimal retraining. It combines State Space Models with cross‑layer interaction, featuring a Mamba adapter that uses task‑specific prompts and multi‑scale branching, and a Scale‑Invariant Cross‑Layer Adapter (SICA) that shares parameters across scales to reduce redundancy. Experiments show that this approach achieves state‑of‑the‑art performance while cutting parameter overhead by 72% compared to existing methods.
arXiv AI
Jun 3
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
arXiv:2606. 03748v1 Announce Type: cross Abstract: Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware.
arXiv Computer Vision
Sep 21
Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models
The paper introduces Recursive Block-Diagonal Coupling (RBDC), a training protocol that builds wide vision models by recursively coupling narrower, independently trained models in a parameter‑free block‑diagonal manner. RBDC allows flexible allocation of training budgets across all models and, when applied to vision transformers (DeiT) and convolutional networks (ResNet) on ImageNet, achieves a 30% reduction in FLOPs while maintaining similar test accuracies. Additionally, models trained with RBDC outperform those from existing growth methods at the same training FLOPs and serve as stronger backbones for downstream tasks such as object detection and instance segmentation.
arXiv Computer Vision
2d ago
XYScanNet: A State Space Model for Single Image Deblurring
XYScanNet introduces a slice‑and‑scan strategy that alternates scanning along intra‑ and inter‑slices to preserve local pixel dependencies, addressing shortcomings of flatten‑and‑scan approaches in Mamba‑based restoration. The paper presents a new Vision State Space Module (VSSM) tailored for image deblurring and integrates it into the XYScanNet architecture with a lightweight feature fusion module. Experimental results demonstrate that XYScanNet achieves competitive distortion metrics while improving perceptual performance, notably boosting KID by 17% over the nearest competitor.
arXiv Computer Vision
Oct 27
VGGT-$\Omega$
arXiv:2605.15195v2 Announce Type: replace Abstract: Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also prov...