Lightweight Structure-Aware Attention for Visual Understanding

• URL: http://arxiv.org/abs/2211.16289v2
• Date: Thu, 03 Jul 2025 12:08:30 GMT
• Title: Lightweight Structure-Aware Attention for Visual Understanding
• Authors: Heeseung Kwon, Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Karteek Alahari,
• Abstract summary: We propose a novel attention operator, called Lightweight Structure-aware Attention (LiSA), which has a better representation power with log-linear complexity.<n>Our operator transforms the attention kernels to be more discriminative by learning structural patterns.<n>Our experiments and analyses demonstrate that the proposed operator outperforms self-attention and other existing operators.
• Score: 13.72466817835681
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Attention operator has been widely used as a basic brick in visual understanding since it provides some flexibility through its adjustable kernels. However, this operator suffers from inherent limitations: (1) the attention kernel is not discriminative enough, resulting in high redundancy, and (2) the complexity in computation and memory is quadratic in the sequence length. In this paper, we propose a novel attention operator, called Lightweight Structure-aware Attention (LiSA), which has a better representation power with log-linear complexity. Our operator transforms the attention kernels to be more discriminative by learning structural patterns. These structural patterns are encoded by exploiting a set of relative position embeddings (RPEs) as multiplicative weights, thereby improving the representation power of the attention kernels. Additionally, the RPEs are approximated to obtain log-linear complexity. Our experiments and analyses demonstrate that the proposed operator outperforms self-attention and other existing operators, achieving state-of-the-art results on ImageNet-1K and other downstream tasks such as video action recognition on Kinetics-400, object detection \& instance segmentation on COCO, and semantic segmentation on ADE-20K.

Related papers

• ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models [39.520825264698374]
  Vision Transformers (ViTs) have delivered remarkable progress through global self-attention, yet their quadratic complexity can become prohibitive for high-resolution inputs. We present ViT-Linearizer, a cross-architecture distillation framework that transfers rich ViT representations into a linear-time, recurrent-style model. Our results underscore the good potential of RNN-based solutions for large-scale visual tasks, bridging the gap between theoretical efficiency and real-world practice.
  arXiv  Detail & Related papers  (2025-03-30T15:35:24Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space. Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction [29.12836710966048]
  We propose a novel transformer attention operator whose computational complexity scales linearly with the number of tokens. Our results call into question the conventional wisdom that pairwise similarity style attention mechanisms are critical to the success of transformer architectures.
  arXiv  Detail & Related papers  (2024-12-23T18:59:21Z)
• Graph Structure Refinement with Energy-based Contrastive Learning [56.957793274727514]
  We introduce an unsupervised method based on a joint of generative training and discriminative training to learn graph structure and representation. We propose an Energy-based Contrastive Learning (ECL) guided Graph Structure Refinement (GSR) framework, denoted as ECL-GSR. ECL-GSR achieves faster training with fewer samples and memories against the leading baseline, highlighting its simplicity and efficiency in downstream tasks.
  arXiv  Detail & Related papers  (2024-12-20T04:05:09Z)
• Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads [10.169639612525643]
  Visual perception tasks are predominantly solved by ViT, despite their effectiveness. Despite their effectiveness, ViT encounters a computational bottleneck due to the complexity of computing self-attention. We propose Fibottention architecture, which approximating self-attention that is built upon.
  arXiv  Detail & Related papers  (2024-06-27T17:59:40Z)
• Operator Learning of Lipschitz Operators: An Information-Theoretic Perspective [2.375038919274297]
  This work addresses the complexity of neural operator approximations for the general class of Lipschitz continuous operators. Our main contribution establishes lower bounds on the metric entropy of Lipschitz operators in two approximation settings. It is shown that, regardless of the activation function used, neural operator architectures attaining an approximation accuracy $epsilon$ must have a size that is exponentially large in $epsilon-1$.
  arXiv  Detail & Related papers  (2024-06-26T23:36:46Z)
• You Only Need Less Attention at Each Stage in Vision Transformers [19.660385306028047]
  Vision Transformers (ViTs) capture the global information of images through self-attention modules. We propose the Less-Attention Vision Transformer (LaViT), which computes only a few attention operations at each stage. Our architecture demonstrates exceptional performance across various vision tasks including classification, detection and segmentation.
  arXiv  Detail & Related papers  (2024-06-01T12:49:16Z)
• Self-Attention Based Semantic Decomposition in Vector Symbolic Architectures [6.473177443214531]
  We introduce a new variant of the resonator network, based on self-attention based update rules in iterative search problem. Our algorithm enables a larger capacity for associative memory, enabling applications in many tasks like perception based pattern recognition, scene decomposition, and object reasoning.
  arXiv  Detail & Related papers  (2024-03-20T00:37:19Z)
• Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation [76.68301884987348]
  We propose a simple yet effective approach for self-supervised video object segmentation (VOS) Our key insight is that the inherent structural dependencies present in DINO-pretrained Transformers can be leveraged to establish robust-temporal segmentation correspondences in videos. Our method demonstrates state-of-the-art performance across multiple unsupervised VOS benchmarks and excels in complex real-world multi-object video segmentation tasks.
  arXiv  Detail & Related papers  (2023-11-29T18:47:17Z)
• ViR: Towards Efficient Vision Retention Backbones [97.93707844681893]
  We propose a new class of computer vision models, dubbed Vision Retention Networks (ViR) ViR has dual parallel and recurrent formulations, which strike an optimal balance between fast inference and parallel training with competitive performance. We have validated the effectiveness of ViR through extensive experiments with different dataset sizes and various image resolutions.
  arXiv  Detail & Related papers  (2023-10-30T16:55:50Z)
• FLatten Transformer: Vision Transformer using Focused Linear Attention [80.61335173752146]
  Linear attention offers a much more efficient alternative with its linear complexity. Current linear attention approaches either suffer from significant performance degradation or introduce additional computation overhead. We propose a novel Focused Linear Attention module to achieve both high efficiency and expressiveness.
  arXiv  Detail & Related papers  (2023-08-01T10:37:12Z)
• Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations [70.41385310930846]
  We present an end-to-end framework Structure-CLIP to enhance multi-modal structured representations. We use scene graphs to guide the construction of semantic negative examples, which results in an increased emphasis on learning structured representations. A Knowledge-Enhance (KEE) is proposed to leverage SGK as input to further enhance structured representations.
  arXiv  Detail & Related papers  (2023-05-06T03:57:05Z)
• Multiscale Attention via Wavelet Neural Operators for Vision Transformers [0.0]
  Transformers have achieved widespread success in computer vision. At their heart, there is a Self-Attention (SA) mechanism. Standard SA mechanism has quadratic complexity with the sequence length, which impedes its utility to long sequences appearing in high resolution vision. We introduce a Multiscale Wavelet Attention (MWA) by leveraging wavelet neural operators which incurs linear complexity in the sequence size.
  arXiv  Detail & Related papers  (2023-03-22T09:06:07Z)
• Towards Lightweight Cross-domain Sequential Recommendation via External Attention-enhanced Graph Convolution Network [7.1102362215550725]
  Cross-domain Sequential Recommendation (CSR) depicts the evolution of behavior patterns for overlapped users by modeling their interactions from multiple domains. We introduce a lightweight external attention-enhanced GCN-based framework to solve the above challenges, namely LEA-GCN. To further alleviate the framework structure and aggregate the user-specific sequential pattern, we devise a novel dual-channel External Attention (EA) component.
  arXiv  Detail & Related papers  (2023-02-07T03:06:29Z)
• Inducing Gaussian Process Networks [80.40892394020797]
  We propose inducing Gaussian process networks (IGN), a simple framework for simultaneously learning the feature space as well as the inducing points. The inducing points, in particular, are learned directly in the feature space, enabling a seamless representation of complex structured domains. We report on experimental results for real-world data sets showing that IGNs provide significant advances over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-21T05:27:09Z)
• Synthesizer Based Efficient Self-Attention for Vision Tasks [10.822515889248676]
  Self-attention module shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning. This paper proposes a self-attention plug-in module with its variants, namely, Synthesizing Transformations (STT) for directly processing image tensor features.
  arXiv  Detail & Related papers  (2022-01-05T02:07:32Z)
• Graph Kernel Neural Networks [53.91024360329517]
  We propose to use graph kernels, i.e. kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type of graph kernels and has the added benefit of providing some interpretability.
  arXiv  Detail & Related papers  (2021-12-14T14:48:08Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• X-volution: On the unification of convolution and self-attention [52.80459687846842]
  We propose a multi-branch elementary module composed of both convolution and self-attention operation. The proposed X-volution achieves highly competitive visual understanding improvements.
  arXiv  Detail & Related papers  (2021-06-04T04:32:02Z)
• Scalable Visual Transformers with Hierarchical Pooling [61.05787583247392]
  We propose a Hierarchical Visual Transformer (HVT) which progressively pools visual tokens to shrink the sequence length. It brings a great benefit by scaling dimensions of depth/width/resolution/patch size without introducing extra computational complexity. Our HVT outperforms the competitive baselines on ImageNet and CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2021-03-19T03:55:58Z)
• A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention [96.77554122595578]
  We introduce a parametrized representation of fixed size, which embeds and then aggregates elements from a given input set according to the optimal transport plan between the set and a trainable reference. Our approach scales to large datasets and allows end-to-end training of the reference, while also providing a simple unsupervised learning mechanism with small computational cost.
  arXiv  Detail & Related papers  (2020-06-22T08:35:58Z)
• Attention improves concentration when learning node embeddings [1.2233362977312945]
  Given nodes labelled with search query text, we want to predict links to related queries that share products. Experiments with a range of deep neural architectures show that simple feedforward networks with an attention mechanism perform best for learning embeddings. We propose an analytically tractable model of query generation, AttEST, that views both products and the query text as vectors embedded in a latent space.
  arXiv  Detail & Related papers  (2020-06-11T21:21:12Z)

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.