UtVAA: Ultra-tiny Vision Transformer with Affix Attention for Mobile Image Classification

• URL: http://arxiv.org/abs/2606.14735v1
• Date: Tue, 02 Jun 2026 12:53:35 GMT
• Title: UtVAA: Ultra-tiny Vision Transformer with Affix Attention for Mobile Image Classification
• Abstract summary: UtVAA is an ultra-tiny Vision Transformer architecture designed for efficient visual recognition under strict computational budgets.<n>It incorporates a novel Affix Attention block that combines depthwise-pointwise local feature extraction, linear self-attention, coordinate attention for spatial dependency modelling, and a lightweight ternary fusion strategy.<n>It is implemented in scalable Tiny, Medium, and Large variants, with the smallest model containing 204.67K parameters and 53.95M FLOPs.
• Score: 1.6566053195631467
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformers (ViTs) have demonstrated strong representation capability in image classification. However, their quadratic self-attention complexity and large parameter counts limit deployment on resource-constrained mobile and edge devices. This paper introduces UtVAA, an ultra-tiny Vision Transformer architecture designed for efficient visual recognition under strict computational budgets. It incorporates a novel Affix Attention block that combines depthwise-pointwise local feature extraction, linear self-attention, coordinate attention for spatial dependency modelling, and a lightweight ternary fusion strategy to integrate local and global representations. In addition, Dilated Bottleneck blocks expand the receptive field using dilated depthwise separable convolutions while maintaining low FLOPs and stable optimisation through residual connections. UtVAA is implemented in scalable Tiny, Medium, and Large variants, with the smallest model containing 204.67K parameters and 53.95M FLOPs. Experimental results on CIFAR-10, CIFAR-100, PlantVillage-Tomato and SLIF-Tomato datasets show that UtVAA achieves competitive accuracy within a sub-million-parameter regime. Overall, the results demonstrate that transformer-based vision models can be redesigned into ultra-tiny architectures without significant loss in discriminative performance, making UtVAA suitable for mobile and edge deployment. Code is available at https://github.com/romiyal/UtVAA

Related papers

• CUST: Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution [0.2538209532048866]
  Clustered Unit-level Similarity Transformer (CUST) is a novel architecture that efficiently integrates global and local information.<n>CUST enables each patch to aggregate and attend to similar patches within a broadened regional scope outside its local window.<n>Experiments demonstrate that our proposed model achieves a practical balance between computational efficiency and restoration performance.
  arXiv  Detail & Related papers  (2026-07-13T04:56:57Z)
• GlimmerNet: A Lightweight Grouped Dilated Depthwise Convolutions for UAV-Based Emergency Monitoring [0.0]
  GlimmerNet is an ultra-lightweight convolutional network built on the principle of separating receptive field diversity from feature recombination.<n>With just 31K parameters and 29% fewer FLOPs than the most recent baseline, GlimmerNet achieves a new state-of-the-art weighted F1-score of 0.966 on the UAV-focused Av2 dataset.
  arXiv  Detail & Related papers  (2025-12-08T10:24:19Z)
• CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision [2.558238597112103]
  CoSwin is a novel feature-fusion architecture that augments the hierarchical shifted window attention with localized convolutional feature learning.<n>We evaluate CoSwin on multiple image classification benchmarks including CIFAR-10, CIFAR-100, MNIST, SVHN, and Tiny ImageNet.
  arXiv  Detail & Related papers  (2025-09-10T19:43:16Z)
• VRS-UIE: Value-Driven Reordering Scanning for Underwater Image Enhancement [104.78586859995333]
  State Space Models (SSMs) have emerged as a promising backbone for vision tasks due to their linear complexity and global receptive field.<n>The predominance of large-portion, homogeneous but useless oceanic backgrounds can dilute the feature representation responses of sparse yet valuable targets.<n>We propose a novel Value-Driven Reordering Scanning framework for Underwater Image Enhancement (UIE)<n>Our framework sets a new state-of-the-art, delivering superior enhancement performance (surpassing WMamba by 0.89 dB on average) by effectively suppressing water bias and preserving structural and color fidelity.
  arXiv  Detail & Related papers  (2025-05-02T12:21:44Z)
• CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications [73.80247057590519]
  Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability.<n>We introduce CAS-ViT: Convolutional Additive Self-attention Vision Transformers, to achieve a balance between efficiency and performance in mobile applications.<n>Our model achieves 83.0%/84.1% top-1 with only 12M/21M parameters on ImageNet-1K.
  arXiv  Detail & Related papers  (2024-08-07T11:33:46Z)
• Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures [96.00848293994463]
  This paper introduces Vision-RWKV, a model adapted from the RWKV model used in the NLP field.<n>Our model is designed to efficiently handle sparse inputs and demonstrate robust global processing capabilities.<n>Our evaluations demonstrate that VRWKV surpasses ViT's performance in image classification and has significantly faster speeds and lower memory usage.
  arXiv  Detail & Related papers  (2024-03-04T18:46:20Z)
• VMamba: Visual State Space Model [98.0517369083152]
  We adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity.<n>At the core of VMamba is a stack of Visual State-Space (VSS) blocks with the 2D Selective Scan (SS2D) module.
  arXiv  Detail & Related papers  (2024-01-18T17:55:39Z)
• Compressing Vision Transformers for Low-Resource Visual Learning [7.662469543657508]
  Vision transformer (ViT) and its variants offer state-of-the-art accuracy in tasks such as image classification, object detection, and semantic segmentation. These models are large and computation-heavy, making their deployment on mobile and edge scenarios limited. We aim to take a step toward bringing vision transformers to the edge by utilizing popular model compression techniques such as distillation, pruning, and quantization.
  arXiv  Detail & Related papers  (2023-09-05T23:33:39Z)
• Lightweight Vision Transformer with Bidirectional Interaction [59.39874544410419]
  We propose a Fully Adaptive Self-Attention (FASA) mechanism for vision transformer to model the local and global information.<n>Based on FASA, we develop a family of lightweight vision backbones, Fully Adaptive Transformer (FAT) family.
  arXiv  Detail & Related papers  (2023-06-01T06:56:41Z)
• SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition [29.522565659389183]
  We introduce a new method squeeze-enhanced Axial Transformer (SeaFormer) for mobile visual recognition.<n>We beat both the mobilefriendly rivals and Transformer-based counterparts with better performance and lower latency without bells and whistles.
  arXiv  Detail & Related papers  (2023-01-30T18:34:16Z)
• Adaptive Split-Fusion Transformer [90.04885335911729]
  We propose an Adaptive Split-Fusion Transformer (ASF-former) to treat convolutional and attention branches differently with adaptive weights. Experiments on standard benchmarks, such as ImageNet-1K, show that our ASF-former outperforms its CNN, transformer counterparts, and hybrid pilots in terms of accuracy.
  arXiv  Detail & Related papers  (2022-04-26T10:00:28Z)
• ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond [76.35955924137986]
  We propose a Vision Transformer Advanced by Exploring intrinsic IB from convolutions, i.e., ViTAE. ViTAE has several spatial pyramid reduction modules to downsample and embed the input image into tokens with rich multi-scale context. We obtain the state-of-the-art classification performance, i.e., 88.5% Top-1 classification accuracy on ImageNet validation set and the best 91.2% Top-1 accuracy on ImageNet real validation set.
  arXiv  Detail & Related papers  (2022-02-21T10:40:05Z)
• PnP-DETR: Towards Efficient Visual Analysis with Transformers [146.55679348493587]
  Recently, DETR pioneered the solution vision tasks with transformers, it directly translates the image feature map into the object result. Recent transformer-based image recognition model andTT show consistent efficiency gain.
  arXiv  Detail & Related papers  (2021-09-15T01:10:30Z)

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.