CoCAViT: Compact Vision Transformer with Robust Global Coordination

• URL: http://arxiv.org/abs/2508.05307v1
• Date: Thu, 07 Aug 2025 12:07:12 GMT
• Title: CoCAViT: Compact Vision Transformer with Robust Global Coordination
• Authors: Xuyang Wang, Lingjuan Miao, Zhiqiang Zhou,
• Abstract summary: We present CoCAViT, a novel visual backbone designed for robust real-time visual representation.<n>At a resolution of 224*224, CoCAViT-28M achieves 84.0% top-1 accuracy on ImageNet-1K, with significant gains on multiple OOD benchmarks.<n>It also attains 52.2 mAP on object detection and 51.3 mIOU on ADE20K semantic segmentation, while maintaining low latency.
• Score: 8.041959685852085
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, large-scale visual backbones have demonstrated remarkable capabilities in learning general-purpose features from images via extensive pre-training. Concurrently, many efficient architectures have emerged that have performance comparable to that of larger models on in-domain benchmarks. However, we observe that for smaller models, the performance drop on out-of-distribution (OOD) data is disproportionately larger, indicating a deficiency in the generalization performance of existing efficient models. To address this, we identify key architectural bottlenecks and inappropriate design choices that contribute to this issue, retaining robustness for smaller models. To restore the global field of pure window attention, we further introduce a Coordinator-patch Cross Attention (CoCA) mechanism, featuring dynamic, domain-aware global tokens that enhance local-global feature modeling and adaptively capture robust patterns across domains with minimal computational overhead. Integrating these advancements, we present CoCAViT, a novel visual backbone designed for robust real-time visual representation. Extensive experiments empirically validate our design. At a resolution of 224*224, CoCAViT-28M achieves 84.0% top-1 accuracy on ImageNet-1K, with significant gains on multiple OOD benchmarks, compared to competing models. It also attains 52.2 mAP on COCO object detection and 51.3 mIOU on ADE20K semantic segmentation, while maintaining low latency.

Related papers

• Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts [4.454997649515497]
  We introduce ViCA2 (Visuospatial Cognitive Assistant 2), a novel MLLM designed to enhance spatial reasoning.<n>ViCA2 features a dual vision architecture integrating SigLIP for semantics and Hiera for spatial structure, coupled with a token ratio control mechanism for efficiency.<n>We also developed ViCA322K, a new large-scale cognition dataset with over 322,000 spatially grounded question-answer pairs.
  arXiv  Detail & Related papers  (2025-05-18T10:57:33Z)
• Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient [52.96232442322824]
  Collaborative Decoding (CoDe) is a novel efficient decoding strategy tailored for the Visual Auto-Regressive ( VAR) framework.<n>CoDe capitalizes on two critical observations: the substantially reduced parameter demands at larger scales and the exclusive generation patterns across different scales.<n>CoDe achieves a 1.7x speedup, slashes memory usage by around 50%, and preserves image quality with only a negligible FID increase from 1.95 to 1.98.
  arXiv  Detail & Related papers  (2024-11-26T15:13:15Z)
• LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba [54.85262314960038]
  Local Attentional Mamba blocks capture both global contexts and local details with linear complexity. Our model exhibits exceptional scalability and surpasses the performance of DiT across various model scales on ImageNet at 256x256 resolution. Compared to state-of-the-art diffusion models on ImageNet 256x256 and 512x512, our largest model presents notable advantages, such as a reduction of up to 62% GFLOPs.
  arXiv  Detail & Related papers  (2024-08-05T16:39:39Z)
• Interpreting and Improving Attention From the Perspective of Large Kernel Convolution [51.06461246235176]
  We introduce Large Kernel Convolutional Attention (LKCA), a novel formulation that reinterprets attention operations as a single large- Kernel convolution.<n>LKCA achieves competitive performance across various visual tasks, particularly in data-constrained settings.
  arXiv  Detail & Related papers  (2024-01-11T08:40:35Z)
• ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders [104.05133094625137]
  We propose a fully convolutional masked autoencoder framework and a new Global Response Normalization layer. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets.
  arXiv  Detail & Related papers  (2023-01-02T18:59:31Z)
• A Close Look at Spatial Modeling: From Attention to Convolution [70.5571582194057]
  Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism. We generalize self-attention formulation to abstract a queryirrelevant global context directly and integrate the global context into convolutions. With less than 14M parameters, our FCViT-S12 outperforms related work ResT-Lite by 3.7% top1 accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-12-23T19:13:43Z)
• VOLO: Vision Outlooker for Visual Recognition [148.12522298731807]
  Vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification. We introduce a novel outlook attention and present a simple and general architecture, termed Vision Outlooker (VOLO) Unlike self-attention that focuses on global dependency modeling at a coarse level, the outlook attention efficiently encodes finer-level features and contexts into tokens. Experiments show that our VOLO achieves 87.1% top-1 accuracy on ImageNet-1K classification, which is the first model exceeding 87% accuracy on this competitive benchmark.
  arXiv  Detail & Related papers  (2021-06-24T15:46:54Z)
• Bottleneck Transformers for Visual Recognition [97.16013761605254]
  We present BoTNet, a powerful backbone architecture that incorporates self-attention for vision tasks. We present models that achieve a strong performance of 84.7% top-1 accuracy on the ImageNet benchmark. We hope our simple and effective approach will serve as a strong baseline for future research in self-attention models for vision.
  arXiv  Detail & Related papers  (2021-01-27T18:55:27Z)
• Objectness-Aware Few-Shot Semantic Segmentation [31.13009111054977]
  We show how to increase overall model capacity to achieve improved performance. We introduce objectness, which is class-agnostic and so not prone to overfitting. Given only one annotated example of an unseen category, experiments show that our method outperforms state-of-art methods with respect to mIoU.
  arXiv  Detail & Related papers  (2020-04-06T19:12:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.