# CanKD: Cross-Attention-based Non-local operation for Feature-based Knowledge Distillation

Source: [CanKD: Cross-Attention-based Non-local operation for Feature-based Knowledge Distillation](<https://www.sota2.com/research/paper/6927db4cd6b0dd3342930ee6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-28T05:02:18.972Z

Authors: Shizhe Sun, Wataru Ohyama

Published: 2025-11-26T15:38:10.000Z

## Abstract

We propose Cross-Attention-based Non-local Knowledge Distillation (CanKD), a novel feature-based knowledge distillation framework that leverages cross-attention mechanisms to enhance the knowledge transfer process. Unlike traditional self-attention-based distillation methods that align teacher and student feature maps independently, CanKD enables each pixel in the student feature map to dynamically consider all pixels in the teacher feature map. This non-local knowledge transfer more thoroughly captures pixel-wise relationships, improving feature representation learning. Our method introduces only an additional loss function to achieve superior performance compared with existing attention-guided distillation methods. Extensive experiments on object detection and image segmentation tasks demonstrate that CanKD outperforms state-of-the-art feature and hybrid distillation methods. These experimental results highlight CanKD's potential as a new paradigm for attention-guided distillation in computer vision tasks. Code is available at https://github.com/tori-hotaru/CanKD

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.21503>)

[PDF](<https://arxiv.org/pdf/2511.21503.pdf>)
