Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?

• URL: http://arxiv.org/abs/2503.10632v1
• Date: Thu, 13 Mar 2025 17:59:52 GMT
• Title: Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?
• Authors: Subhajit Maity, Killian Hitsman, Xin Li, Aritra Dutta,
• Abstract summary: Learnable activation functions (KANs) are a remarkable innovation consisting of learnable activation functions with the potential to capture more complex relationships from data.<n>In this paper, we are the first to design a general learnable Kolmogorov-Arnold Attention (KArAt) for vanilla vision Transformers (ViTs)
• Score: 5.2768199606089095
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Kolmogorov-Arnold networks (KANs) are a remarkable innovation consisting of learnable activation functions with the potential to capture more complex relationships from data. Although KANs are useful in finding symbolic representations and continual learning of one-dimensional functions, their effectiveness in diverse machine learning (ML) tasks, such as vision, remains questionable. Presently, KANs are deployed by replacing multilayer perceptrons (MLPs) in deep network architectures, including advanced architectures such as vision Transformers (ViTs). In this paper, we are the first to design a general learnable Kolmogorov-Arnold Attention (KArAt) for vanilla ViTs that can operate on any choice of basis. However, the computing and memory costs of training them motivated us to propose a more modular version, and we designed particular learnable attention, called Fourier-KArAt. Fourier-KArAt and its variants either outperform their ViT counterparts or show comparable performance on CIFAR-10, CIFAR-100, and ImageNet-1K datasets. We dissect these architectures' performance and generalization capacity by analyzing their loss landscapes, weight distributions, optimizer path, attention visualization, and spectral behavior, and contrast them with vanilla ViTs. The goal of this paper is not to produce parameter- and compute-efficient attention, but to encourage the community to explore KANs in conjunction with more advanced architectures that require a careful understanding of learnable activations. Our open-source code and implementation details are available on: https://subhajitmaity.me/KArAt

Related papers

• 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)
• DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention [1.5624421399300303]
  We propose a novel hierarchical transformer model that adeptly integrates the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the advanced representational potential of Vision Transformers (ViTs) Addressing the lack of inductive biases and dependence on extensive training datasets in ViTs, our model employs a CNN backbone to generate hierarchical visual representations. These representations are then adapted for transformer input through an innovative patch tokenization.
  arXiv  Detail & Related papers  (2024-07-18T22:15:35Z)
• Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads [10.169639612525643]
  We propose a new multi-head self-attention (MHSA) variant named Fibottention, which can replace MHSA in Transformer architectures.<n>Fibottention is data-efficient and computationally more suitable for processing large numbers of tokens than the standard MHSA.<n>It employs structured sparse attention based on dilated Fibonacci sequences, which, uniquely, differ across attention heads, resulting in-like diverse features across heads.
  arXiv  Detail & Related papers  (2024-06-27T17:59:40Z)
• DAT++: Spatially Dynamic Vision Transformer with Deformable Attention [87.41016963608067]
  We present Deformable Attention Transformer ( DAT++), a vision backbone efficient and effective for visual recognition. DAT++ achieves state-of-the-art results on various visual recognition benchmarks, with 85.9% ImageNet accuracy, 54.5 and 47.0 MS-COCO instance segmentation mAP, and 51.5 ADE20K semantic segmentation mIoU.
  arXiv  Detail & Related papers  (2023-09-04T08:26:47Z)
• Enhancing Performance of Vision Transformers on Small Datasets through Local Inductive Bias Incorporation [13.056764072568749]
  Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) on smaller datasets. We propose a module called Local InFormation Enhancer (LIFE) that extracts patch-level local information and incorporates it into the embeddings used in the self-attention block of ViTs. Our proposed module is memory and efficient, as well as flexible enough to process auxiliary tokens such as the classification and distillation tokens.
  arXiv  Detail & Related papers  (2023-05-15T11:23:18Z)
• RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer [95.71132572688143]
  This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs), are intended to perform information communication between different spatial tokens but suffer from considerable computational cost and latency.
  arXiv  Detail & Related papers  (2023-04-12T07:34:13Z)
• Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning [0.0]
  We study pretraining a Vision Transformer using several state-of-the-art self-supervised methods and assess the quality of the learned representations. Our results show that all methods are effective in learning useful representations and avoiding representational collapse. The encoder pretrained with the temporal order verification task shows the best results across all experiments.
  arXiv  Detail & Related papers  (2022-09-22T10:18:59Z)
• 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)
• Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers [52.30336730712544]
  We introduce a deep reinforcement learning architecture whose purpose is to increase sample efficiency without sacrificing performance. We propose a visually attentive model that uses transformers to learn a self-attention mechanism on the feature maps of the state representation. We demonstrate empirically that this architecture improves sample complexity for several Atari environments, while also achieving better performance in some of the games.
  arXiv  Detail & Related papers  (2022-02-01T19:03:03Z)
• Self-slimmed Vision Transformer [52.67243496139175]
  Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. We propose a generic self-slimmed learning approach for vanilla ViTs, namely SiT. Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs.
  arXiv  Detail & Related papers  (2021-11-24T16:48:57Z)
• Hybrid BYOL-ViT: Efficient approach to deal with small Datasets [0.0]
  In this paper, we investigate how self-supervision with strong and sufficient augmentation of unlabeled data can train effectively the first layers of a neural network. We show that the low-level features derived from a self-supervised architecture can improve the robustness and the overall performance of this emergent architecture.
  arXiv  Detail & Related papers  (2021-11-08T21:44:31Z)

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.