Semantic Equitable Clustering: A Simple, Fast and Effective Strategy for Vision Transformer

• URL: http://arxiv.org/abs/2405.13337v1
• Date: Wed, 22 May 2024 04:49:00 GMT
• Title: Semantic Equitable Clustering: A Simple, Fast and Effective Strategy for Vision Transformer
• Authors: Qihang Fan, Huaibo Huang, Mingrui Chen, Ran He,
• Abstract summary: We introduce a fast and balanced clustering method, named textbfSemantic textbfEquitable textbfClustering (SEC) SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner. We propose a versatile vision backbone, SecViT, which attains an impressive textbf84.2% image classification accuracy with only textbf27M parameters and textbf4.4G FLOPs.
• Score: 57.37893387775829
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial computational burdens. A common remedy spatially groups tokens for self-attention, reducing computational requirements. Nonetheless, this strategy neglects semantic information in tokens, possibly scattering semantically-linked tokens across distinct groups, thus compromising the efficacy of self-attention intended for modeling inter-token dependencies. Motivated by these insights, we introduce a fast and balanced clustering method, named \textbf{S}emantic \textbf{E}quitable \textbf{C}lustering (SEC). SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner. In contrast to traditional clustering methods requiring multiple iterations, our method achieves token clustering in a single pass. Additionally, SEC regulates the number of tokens per cluster, ensuring a balanced distribution for effective parallel processing on current computational platforms without necessitating further optimization. Capitalizing on SEC, we propose a versatile vision backbone, SecViT. Comprehensive experiments in image classification, object detection, instance segmentation, and semantic segmentation validate to the effectiveness of SecViT. Remarkably, SecViT attains an impressive \textbf{84.2\%} image classification accuracy with only \textbf{27M} parameters and \textbf{4.4G} FLOPs, without the need for for additional supervision or data. Code will be available at \url{https://github.com/qhfan/SecViT}.

Related papers

• Self-Supervised Graph Embedding Clustering [70.36328717683297]
  K-means one-step dimensionality reduction clustering method has made some progress in addressing the curse of dimensionality in clustering tasks. We propose a unified framework that integrates manifold learning with K-means, resulting in the self-supervised graph embedding framework.
  arXiv  Detail & Related papers  (2024-09-24T08:59:51Z)
• Agglomerative Token Clustering [61.0477253613511]
  Agglomerative Token Clustering (ATC) is a novel token merging method that consistently outperforms previous methods. We find that ATC achieves state-of-the-art performance across all tasks, and can even perform on par with prior state-of-the-art when applied off-the-shelf.
  arXiv  Detail & Related papers  (2024-09-18T12:37:58Z)
• Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation [59.37587762543934]
  This paper studies the problem of weakly open-vocabulary semantic segmentation (WOVSS) Existing methods suffer from a granularity inconsistency regarding the usage of group tokens. We propose the prototypical guidance network (PGSeg) that incorporates multi-modal regularization.
  arXiv  Detail & Related papers  (2023-10-29T13:18:00Z)
• DenseDINO: Boosting Dense Self-Supervised Learning with Token-Based Point-Level Consistency [12.881617910150688]
  We propose a transformer framework for self-supervised learning called DenseDINO to learn dense visual representations. Specifically, DenseDINO introduces some extra input tokens called reference tokens to match the point-level features with the position prior. Compared with the vanilla DINO, our approach obtains competitive performance when evaluated on classification in ImageNet.
  arXiv  Detail & Related papers  (2023-06-06T15:04:45Z)
• DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering [6.447863458841379]
  This study introduces a lightweight Graph Neural Network (GNN) to replace classical clustering methods. Unlike existing methods, our GNN takes both the pair-wise affinities between local image features and the raw features as input. We demonstrate how classical clustering objectives can be formulated as self-supervised loss functions for training an image segmentation GNN.
  arXiv  Detail & Related papers  (2022-12-12T12:31:46Z)
• ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers [70.76313507550684]
  We propose a content-based sparse attention method, as an alternative to dense self-attention. Specifically, we cluster and then aggregate key and value tokens, as a content-based method of reducing the total token count. The resulting clustered-token sequence retains the semantic diversity of the original signal, but can be processed at a lower computational cost.
  arXiv  Detail & Related papers  (2022-08-28T04:18:27Z)
• You Never Cluster Alone [150.94921340034688]
  We extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation. We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one. By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps.
  arXiv  Detail & Related papers  (2021-06-03T14:59:59Z)
• Unsupervised Visual Representation Learning by Online Constrained K-Means [44.38989920488318]
  Cluster discrimination is an effective pretext task for unsupervised representation learning. We propose a novel clustering-based pretext task with online textbfConstrained textbfK-mtextbfeans (textbfCoKe) Our online assignment method has a theoretical guarantee to approach the global optimum.
  arXiv  Detail & Related papers  (2021-05-24T20:38:32Z)
• Information Maximization Clustering via Multi-View Self-Labelling [9.947717243638289]
  We propose a novel single-phase clustering method that simultaneously learns meaningful representations and assigns the corresponding annotations. This is achieved by integrating a discrete representation into the self-supervised paradigm through a net. Our empirical results show that the proposed framework outperforms state-of-the-art techniques with the average accuracy of 89.1% and 49.0%, respectively.
  arXiv  Detail & Related papers  (2021-03-12T16:04:41Z)
• GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering [9.722607434532883]
  We propose a self-supervised clustering network for image Clustering (GATCluster) Rather than extracting intermediate features first and then performing the traditional clustering, GATCluster semantic cluster labels without further post-processing. We develop a two-step learning algorithm that is memory-efficient for clustering large-size images.
  arXiv  Detail & Related papers  (2020-02-27T00:57:18Z)

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.