Interpolation between Convolution and Attention via K-Nearest Neighbors

• URL: http://arxiv.org/abs/2606.14725v1
• Date: Sun, 31 May 2026 23:23:42 GMT
• Title: Interpolation between Convolution and Attention via K-Nearest Neighbors
• Abstract summary: We argue that convolution and self-attention can be unified within a single k-nearest neighbor aggregation framework.<n>We introduce Convolutional Nearest Neighbors (ConvNN), a unified framework that formalizes this connection.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The shift from Convolutional Neural Networks to Transformers has reshaped computer vision, yet these two architectural families are typically viewed as fundamentally distinct. Convolutional Neural Networks are defined by spatially local convolution operations, while Transformers rely on global self-attention. We argue that convolution and self-attention, despite their apparent differences, can be unified within a single k-nearest neighbor aggregation framework. The critical insight is that both operations are special cases of neighbor selection and weighted aggregation. Convolution selects neighbors by spatial proximity while self-attention selects by feature similarity, revealing that they lie on a continuous spectrum rather than representing categorically different computations. We introduce Convolutional Nearest Neighbors (ConvNN), a unified framework that formalizes this connection. ConvNN exactly recovers standard and depthwise convolution by restricting neighbor selection to normalized spatial coordinates, and exactly recovers self-attention and its sparse variants, including KVT-attention, by replacing spatial proximity with scaled dot-product similarity. Beyond these special cases, ConvNN serves as a drop-in replacement for both convolution and attention layers, enabling systematic exploration of the intermediate spectrum between local and global aggregation through configurable similarity functions, neighbor selection strategies, positional encodings, and aggregation kernels.

Related papers

• Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization [7.881713230406407]
  We introduce a constrained two-view framework for node prediction that aligns structure-conditioned GNN embeddings with a structure-free feature prior learned by an anchor model.<n>We also propose a Channel-Split Adaptive Gated GNN (CSAG-GNN) that dynamically routes representations between global spectral smoothing and local spatial discrimination through a node-wise gating mechanism.
  arXiv  Detail & Related papers  (2026-07-13T13:58:52Z)
• SONIC: Spectral Oriented Neural Invariant Convolutions [0.0]
  Convolutional Neural Networks (CNNs) rely on fixed-size kernels scanning local patches.<n>ViTs provide global connectivity but lack spatial inductive bias, depend on explicit positional encodings, and remain tied to the initial patch size.<n>We introduce SONIC, a continuous spectral parameterisation that models convolutional operators using a small set of shared, orientation-selective components.
  arXiv  Detail & Related papers  (2026-01-27T18:51:11Z)
• Attention Via Convolutional Nearest Neighbors [0.5729426778193399]
  We argue that convolution and self-attention can be unified within a single k-nearest neighbor aggregation framework.<n>We introduce Convolutional Nearest Neighbors (ConvNN), a unified framework that formalizes this connection.<n>We validate the framework's coherence on CIFAR-10 and CIFAR-100 classification tasks.
  arXiv  Detail & Related papers  (2025-11-18T04:54:39Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Augmenting Convolutional networks with attention-based aggregation [55.97184767391253]
  We show how to augment any convolutional network with an attention-based global map to achieve non-local reasoning. We plug this learned aggregation layer with a simplistic patch-based convolutional network parametrized by 2 parameters (width and depth) It yields surprisingly competitive trade-offs between accuracy and complexity, in particular in terms of memory consumption.
  arXiv  Detail & Related papers  (2021-12-27T14:05:41Z)
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning [74.76431541169342]
  Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. We propose a novel hierarchical semantic-visual adaptation (HSVA) framework to align semantic and visual domains. Experiments on four benchmark datasets demonstrate HSVA achieves superior performance on both conventional and generalized ZSL.
  arXiv  Detail & Related papers  (2021-09-30T14:27:50Z)
• Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds [70.32518963244466]
  A major complication in comparison to flat spaces is that it is unclear in which alignment a convolution kernel should be applied on a manifold. We argue that the particular choice of coordinatization should not affect a network's inference -- it should be coordinate independent. A simultaneous demand for coordinate independence and weight sharing is shown to result in a requirement on the network to be equivariant.
  arXiv  Detail & Related papers  (2021-06-10T19:54:19Z)
• 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)
• Conformer: Local Features Coupling Global Representations for Visual Recognition [72.9550481476101]
  We propose a hybrid network structure, termed Conformer, to take advantage of convolutional operations and self-attention mechanisms for enhanced representation learning. Experiments show that Conformer, under the comparable parameter complexity, outperforms the visual transformer (DeiT-B) by 2.3% on ImageNet.
  arXiv  Detail & Related papers  (2021-05-09T10:00:03Z)
• Field Convolutions for Surface CNNs [19.897276088740995]
  We present a novel surface convolution operator acting on vector fields based on a simple observation. This formulation combines intrinsic spatial convolution with parallel transport in a scattering operation. We achieve state-of-the-art results on standard benchmarks in fundamental geometry processing tasks.
  arXiv  Detail & Related papers  (2021-04-08T17:11:14Z)

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.