Subtoken Vision Transformer for Fine-grained Recognition

• URL: http://arxiv.org/abs/2607.09086v1
• Date: Fri, 10 Jul 2026 04:07:23 GMT
• Title: Subtoken Vision Transformer for Fine-grained Recognition
• Abstract summary: SubViT is a selective image tokenization method for fine-grained visual recognition.<n>It represents discriminative patches with multiple subtokens while retaining the original token sequence for global context.<n>It improves the average novel-category accuracy of DINOv2 from $81.3%$ to $84.7%$, with only $0.50$ ms additional latency and $3.4%$ more FLOPs.
• Score: 21.033814568458897
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transformers compress each fixed-size patch into a single token, although fine-grained distinctions often depend on localized variations within only a few patches. SubViT addresses this mismatch by representing discriminative patches with multiple subtokens while retaining the original token sequence for global context, thereby allocating additional capacity where it is most needed. Since attention heads encode complementary semantics and extracting attention maps at inference requires an extra backbone forward, we adopt a two-stage training strategy. Stage 1 fine-tunes the ViT using subdivision regions sampled from random attention heads, exposing the model to diverse subdivision patterns. Stage 2 identifies informative attention maps through feature-degradation distances and distills them into a lightweight single-map router, which directly predicts deterministic token-importance scores without a separate attention forward. We evaluate SubViT on Generalized Category Discovery (GCD), a challenging task requiring both fine-grained discrimination and generalization to unlabeled novel categories. Across CUB, FGVC-Aircraft, and Stanford Cars, SubViT improves the average novel-category accuracy of DINOv2 from $81.3\%$ to $84.7\%$, with only $0.50$ ms additional latency and $3.4\%$ more FLOPs, while reducing latency by $73.8\%$ relative to Retina Patch. Results on CIFAR-10 and ImageNet-100 demonstrate its broader applicability.

Related papers

• Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding [49.540751364954666]
  Visual Token Codec separates global and patch tokens into dedicated coding paths.<n>We show that VTC consistently outperforms representative ViT feature coding baselines on classification, segmentation, and detection tasks.
  arXiv  Detail & Related papers  (2026-08-09T17:32:04Z)
• [CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation [20.637119409165418]
  PIAA formulates prediction as Patch-level Inference followed by Adaptive Aggregation.<n>We introduce an adaptive aggregation module that consolidates patch-level scores into the final multi-label prediction.<n>Experiments show that our method achieves strong improvements with minimal extra computation.
  arXiv  Detail & Related papers  (2026-05-25T13:19:12Z)
• Saccadic Vision for Fine-Grained Visual Classification [10.681604440788854]
  Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features.<n>Existing part-based methods rely on complex localization networks that learn mappings from pixel to sample space.<n>We propose a two-stage process that first extracts peripheral features and generates a sample map.<n>We employ contextualized selective attention to weigh the impact of each fixation patch before fusing peripheral and focus representations.
  arXiv  Detail & Related papers  (2025-09-19T07:03:37Z)
• LookupViT: Compressing visual information to a limited number of tokens [36.83826969693139]
  Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from complexity in the number of tokens. In this work, we introduce LookupViT, that exploits this information sparsity to reduce ViT inference cost.
  arXiv  Detail & Related papers  (2024-07-17T17:22:43Z)
• AiluRus: A Scalable ViT Framework for Dense Prediction [95.1313839257891]
  Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. We propose to apply adaptive resolution for different regions in the image according to their importance. We evaluate our proposed method on three different datasets and observe promising performance.
  arXiv  Detail & Related papers  (2023-11-02T12:48:43Z)
• Making Vision Transformers Efficient from A Token Sparsification View [26.42498120556985]
  We propose a novel Semantic Token ViT (STViT) for efficient global and local vision transformers. Our method can achieve competitive results compared to the original networks in object detection and instance segmentation, with over 30% FLOPs reduction for backbone. In addition, we design a STViT-R(ecover) network to restore the detailed spatial information based on the STViT, making it work for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-15T15:12:36Z)
• Patch-level Representation Learning for Self-supervised Vision Transformers [68.8862419248863]
  Vision Transformers (ViTs) have gained much attention recently as a better architectural choice, often outperforming convolutional networks for various visual tasks. Inspired by this, we design a simple yet effective visual pretext task, coined SelfPatch, for learning better patch-level representations. We demonstrate that SelfPatch can significantly improve the performance of existing SSL methods for various visual tasks.
  arXiv  Detail & Related papers  (2022-06-16T08:01:19Z)
• ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator [21.351034332423374]
  We propose a novel ViT based fine-grained object discriminator for Fine-Grained Visual Classification (FGVC) tasks. Besides a ViT backbone, it introduces three novel components, i.e. Attention Patch Combination (APC), Critical Regions Filter (CRF) and Complementary Tokens Integration (CTI) We conduct comprehensive experiments on widely used datasets and the results demonstrate that ViT-FOD is able to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-03-24T02:34:57Z)
• Self-Promoted Supervision for Few-Shot Transformer [178.52948452353834]
  Self-promoted sUpervisioN (SUN) is a few-shot learning framework for vision transformers (ViTs) SUN pretrains the ViT on the few-shot learning dataset and then uses it to generate individual location-specific supervision for guiding each patch token. Experiments show that SUN using ViTs significantly surpasses other few-shot learning frameworks with ViTs and is the first one that achieves higher performance than those CNN state-of-the-arts.
  arXiv  Detail & Related papers  (2022-03-14T12:53:27Z)
• Shunted Self-Attention via Multi-Scale Token Aggregation [124.16925784748601]
  Recent Vision Transformer(ViT) models have demonstrated encouraging results across various computer vision tasks. We propose shunted self-attention(SSA) that allows ViTs to model the attentions at hybrid scales per attention layer. The SSA-based transformer achieves 84.0% Top-1 accuracy and outperforms the state-of-the-art Focal Transformer on ImageNet.
  arXiv  Detail & Related papers  (2021-11-30T08:08:47Z)
• Vision Transformer with Progressive Sampling [73.60630716500154]
  We propose an iterative and progressive sampling strategy to locate discriminative regions. When trained from scratch on ImageNet, PS-ViT performs 3.8% higher than the vanilla ViT in terms of top-1 accuracy.
  arXiv  Detail & Related papers  (2021-08-03T18:04:31Z)

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.