Elastic Attention Cores for Scalable Vision Transformers

• URL: http://arxiv.org/abs/2605.12491v1
• Date: Tue, 12 May 2026 17:59:26 GMT
• Title: Elastic Attention Cores for Scalable Vision Transformers
• Abstract summary: Vision Transformers (ViTs) achieve strong data-driven scaling by leveraging all-to-all self-attention.<n>This flexibility incurs a computational cost that scales quadratically with image resolution, limiting ViTs in high-resolution domains.<n>We propose VECA (Visual Elastic Core Attention), a vision transformer architecture that uses efficient linear-time core-periphery structured attention.
• Score: 42.3374915084462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformers (ViTs) achieve strong data-driven scaling by leveraging all-to-all self-attention. However, this flexibility incurs a computational cost that scales quadratically with image resolution, limiting ViTs in high-resolution domains. Underlying this approach is the assumption that pairwise token interactions are necessary for learning rich visual-semantic representations. In this work, we challenge this assumption, demonstrating that effective visual representations can be learned without any direct patch-to-patch interaction. We propose VECA (Visual Elastic Core Attention), a vision transformer architecture that uses efficient linear-time core-periphery structured attention enabled by a small set of learned cores. In VECA, these cores act as a communication interface: patch tokens exchange information exclusively through the core tokens, which are initialized from scratch and propagated across layers. Because the $N$ image patches only directly interact with a resolution invariant set of $C$ learned "core" embeddings, this yields linear complexity $O(N)$ for predetermined $C$, which bypasses quadratic scaling. Compared to prior cross-attention architectures, VECA maintains and iteratively updates the full set of $N$ input tokens, avoiding a small $C$-way bottleneck. Combined with nested training along the core axis, our model can elastically trade off compute and accuracy during inference. Across classification and dense tasks, VECA achieves performance competitive with the latest vision foundation models while reducing computational cost. Our results establish elastic core-periphery attention as a scalable alternative building block for Vision Transformers.

Related papers

• Rényi Entropy: A New Token Pruning Metric for Vision Transformers [7.739339395706548]
  We argue that the [] token can be unreliable in early layers where semantic representations are still immature.<n>We propose a training-free token importance metric, namely Col-Ln, which is derived from Rényi entropy.<n>Our approach consistently outperforms state-of-the-art pruning methods across diverse benchmarks.
  arXiv  Detail & Related papers  (2026-03-29T23:01:45Z)
• Elastic ViTs from Pretrained Models without Retraining [74.5386166956142]
  Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes.<n>We introduce SnapViT: Single-shot network approximation for pruned Vision Transformers.<n>Our approach efficiently combines gradient information with cross-network structure correlations, approximated via an evolutionary algorithm.
  arXiv  Detail & Related papers  (2025-10-20T16:15:03Z)
• End-to-End Vision Tokenizer Tuning [73.3065542220568]
  The vision tokenizer optimized for low-level reconstruction is to downstream tasks requiring varied representations and semantics.<n>The loss of the vision tokenization can be the representation bottleneck for target tasks.<n>We propose ETT, an end-to-end vision tokenizer tuning approach that enables joint optimization between vision tokenization and target autoregressive tasks.
  arXiv  Detail & Related papers  (2025-05-15T17:59:39Z)
• Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers [54.20763128054692]
  We study how a two-attention-layer transformer is trained to perform ICL on $n$-gram Markov chain data. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model.
  arXiv  Detail & Related papers  (2024-09-09T18:10:26Z)
• 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)
• Multi-Scale And Token Mergence: Make Your ViT More Efficient [3.087140219508349]
  Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. We propose a novel token pruning method that retains information from non-crucial tokens by merging them with more crucial tokens. Our method achieves a remarkable 33% reduction in computational costs while only incurring a 0.1% decrease in accuracy on DeiT-S.
  arXiv  Detail & Related papers  (2023-06-08T02:58:15Z)
• Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention [36.90363317158731]
  We propose an adaptive sparse token pruning framework with a minimal cost. Our method improves the throughput of DeiT-S by 50% and brings only 0.2% drop in top-1 accuracy.
  arXiv  Detail & Related papers  (2022-09-28T03:07:32Z)
• Rethinking Query-Key Pairwise Interactions in Vision Transformers [5.141895475956681]
  We propose key-only attention, which excludes query-key pairwise interactions and uses a compute-efficient saliency-gate to obtain attention weights. We develop a new self-attention model family, LinGlos, which reach state-of-the-art accuracies on the parameter-limited setting of ImageNet classification benchmark.
  arXiv  Detail & Related papers  (2022-07-01T03:36:49Z)
• Global Context Vision Transformers [78.5346173956383]
  We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. We address the lack of the inductive bias in ViTs, and propose to leverage a modified fused inverted residual blocks in our architecture. Our proposed GC ViT achieves state-of-the-art results across image classification, object detection and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2022-06-20T18:42:44Z)
• 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)
• IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers [81.31885548824926]
  Self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. We present an Interpretability-Aware REDundancy REDuction framework (IA-RED$2$) We include extensive experiments on both image and video tasks, where our method could deliver up to 1.4X speed-up.
  arXiv  Detail & Related papers  (2021-06-23T18:29:23Z)
• KVT: k-NN Attention for Boosting Vision Transformers [44.189475770152185]
  We propose a sparse attention scheme, dubbed k-NN attention, for boosting vision transformers. The proposed k-NN attention naturally inherits the local bias of CNNs without introducing convolutional operations. We verify, both theoretically and empirically, that $k$-NN attention is powerful in distilling noise from input tokens and in speeding up training.
  arXiv  Detail & Related papers  (2021-05-28T06:49:10Z)
• So-ViT: Mind Visual Tokens for Vision Transformer [27.243241133304785]
  We propose a new classification paradigm, where the second-order, cross-covariance pooling of visual tokens is combined with class token for final classification. We develop a light-weight, hierarchical module based on off-the-shelf convolutions for visual token embedding. The results show our models, when trained from scratch, outperform the competing ViT variants, while being on par with or better than state-of-the-art CNN models.
  arXiv  Detail & Related papers  (2021-04-22T09:05:09Z)

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.