Compact Vision Transformer by Reduction of Kernel Complexity

• URL: http://arxiv.org/abs/2507.12780v1
• Date: Thu, 17 Jul 2025 04:41:18 GMT
• Title: Compact Vision Transformer by Reduction of Kernel Complexity
• Authors: Yancheng Wang, Yingzhen Yang,
• Abstract summary: KCR-Transformer is a compact transformer block equipped with differentiable channel selection.<n>It reduces the FLOPs of the vision transformers while maintaining or even improving the prediction accuracy.<n>The resulting TCR-Transformers achieve superior performance on various computer vision tasks.
• Score: 8.905020033545643
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-attention and transformer architectures have become foundational components in modern deep learning. Recent efforts have integrated transformer blocks into compact neural architectures for computer vision, giving rise to various efficient vision transformers. In this work, we introduce Transformer with Kernel Complexity Reduction, or KCR-Transformer, a compact transformer block equipped with differentiable channel selection, guided by a novel and sharp theoretical generalization bound. KCR-Transformer performs input/output channel selection in the MLP layers of transformer blocks to reduce the computational cost. Furthermore, we provide a rigorous theoretical analysis establishing a tight generalization bound for networks equipped with KCR-Transformer blocks. Leveraging such strong theoretical results, the channel pruning by KCR-Transformer is conducted in a generalization-aware manner, ensuring that the resulting network retains a provably small generalization error. Our KCR-Transformer is compatible with many popular and compact transformer networks, such as ViT and Swin, and it reduces the FLOPs of the vision transformers while maintaining or even improving the prediction accuracy. In the experiments, we replace all the transformer blocks in the vision transformers with KCR-Transformer blocks, leading to KCR-Transformer networks with different backbones. The resulting TCR-Transformers achieve superior performance on various computer vision tasks, achieving even better performance than the original models with even less FLOPs and parameters.

Related papers

• Universal Approximation of Visual Autoregressive Transformers [28.909655919558706]
  We extend our analysis to include Visual Autoregressive transformers.<n>Var represents a big step toward generating images using a novel, scalable, coarse-to-fine next-scale prediction'' framework.<n>Our results provide important design principles for effective and computationally efficient VAR Transformer strategies.
  arXiv  Detail & Related papers  (2025-02-10T05:36:30Z)
• Efficient Visual Transformer by Learnable Token Merging [8.905020033545643]
  We propose a novel transformer block, Transformer with Learnable Token Merging (LTM), or LTM-Transformer. LTM-Transformer is compatible with many popular and compact transformer networks. It renders compact and efficient visual transformers with comparable or much better prediction accuracy than the original visual transformers.
  arXiv  Detail & Related papers  (2024-07-21T17:09:19Z)
• On the Convergence of Encoder-only Shallow Transformers [62.639819460956176]
  We build the global convergence theory of encoder-only shallow Transformers under a realistic setting. Our results can pave the way for a better understanding of modern Transformers, particularly on training dynamics.
  arXiv  Detail & Related papers  (2023-11-02T20:03:05Z)
• Deep Laparoscopic Stereo Matching with Transformers [46.18206008056612]
  Self-attention mechanism, successfully employed with the transformer structure, is shown promise in many computer vision tasks. We propose a new hybrid deep stereo matching framework (HybridStereoNet) that combines the best of the CNN and the transformer in a unified design.
  arXiv  Detail & Related papers  (2022-07-25T12:54:32Z)
• HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling [126.89573619301953]
  We propose a new design of hierarchical vision transformers named HiViT (short for Hierarchical ViT) HiViT enjoys both high efficiency and good performance in MIM. In running MAE on ImageNet-1K, HiViT-B reports a +0.6% accuracy gain over ViT-B and a 1.9$times$ speed-up over Swin-B.
  arXiv  Detail & Related papers  (2022-05-30T09:34:44Z)
• Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks [126.33843752332139]
  We introduce Group-wise Transformation towards a universal yet lightweight Transformer for vision-and-language tasks, termed as LW-Transformer. We apply LW-Transformer to a set of Transformer-based networks, and quantitatively measure them on three vision-and-language tasks and six benchmark datasets. Experimental results show that while saving a large number of parameters and computations, LW-Transformer achieves very competitive performance against the original Transformer networks for vision-and-language tasks.
  arXiv  Detail & Related papers  (2022-04-16T11:30:26Z)
• The Nuts and Bolts of Adopting Transformer in GANs [124.30856952272913]
  We investigate the properties of Transformer in the generative adversarial network (GAN) framework for high-fidelity image synthesis. Our study leads to a new alternative design of Transformers in GAN, a convolutional neural network (CNN)-free generator termed as STrans-G.
  arXiv  Detail & Related papers  (2021-10-25T17:01:29Z)
• On the Power of Saturated Transformers: A View from Circuit Complexity [87.20342701232869]
  We show that saturated transformers transcend the limitations of hard-attention transformers. The jump from hard to saturated attention can be understood as increasing the transformer's effective circuit depth by a factor of $O(log n)$.
  arXiv  Detail & Related papers  (2021-06-30T17:09:47Z)
• Glance-and-Gaze Vision Transformer [13.77016463781053]
  We propose a new vision Transformer, named Glance-and-Gaze Transformer (GG-Transformer) It is motivated by the Glance and Gaze behavior of human beings when recognizing objects in natural scenes. We empirically demonstrate our method achieves consistently superior performance over previous state-of-the-art Transformers.
  arXiv  Detail & Related papers  (2021-06-04T06:13:47Z)
• Scalable Transformers for Neural Machine Translation [86.4530299266897]
  Transformer has been widely adopted in Neural Machine Translation (NMT) because of its large capacity and parallel training of sequence generation. We propose a novel scalable Transformers, which naturally contains sub-Transformers of different scales and have shared parameters. A three-stage training scheme is proposed to tackle the difficulty of training the scalable Transformers.
  arXiv  Detail & Related papers  (2021-06-04T04:04:10Z)
• Incorporating Convolution Designs into Visual Transformers [24.562955955312187]
  We propose a new textbfConvolution-enhanced image Transformer (CeiT) which combines the advantages of CNNs in extracting low-level features, strengthening locality, and the advantages of Transformers in establishing long-range dependencies. Experimental results on ImageNet and seven downstream tasks show the effectiveness and generalization ability of CeiT compared with previous Transformers and state-of-the-art CNNs, without requiring a large amount of training data and extra CNN teachers.
  arXiv  Detail & Related papers  (2021-03-22T13:16:12Z)

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.