# Deeply-supervised Knowledge Synergy

## TL;DR

This paper introduces Deeply-supervised Knowledge Synergy (DKS), a training method for CNNs that enhances generalization by utilizing dynamic knowledge matching among auxiliary supervision branches without extra inference costs.

## Contribution

The paper proposes a novel synergy loss that enables dense pairwise knowledge matching in CNN training, improving accuracy without additional inference complexity.

## Key findings

- ResNet-152 with DKS outperforms baseline by 1.47% Top-1 accuracy on ImageNet.
- DKS improves CNN generalization across multiple architectures.
- Dynamic knowledge matching enhances training effectiveness.

## Abstract

Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet. However, current prevailing training scheme follows the previous way of adding supervision to the last layer of the network only and propagating error information up layer-by-layer. In this paper, we propose Deeply-supervised Knowledge Synergy (DKS), a new method aiming to train CNNs with improved generalization ability for image classification tasks without introducing extra computational cost during inference. Inspired by the deeply-supervised learning scheme, we first append auxiliary supervision branches on top of certain intermediate network layers. While properly using auxiliary supervision can improve model accuracy to some degree, we go one step further to explore the possibility of utilizing the probabilistic knowledge dynamically learnt by the classifiers connected to the backbone network as a new regularization to improve the training. A novel synergy loss, which considers pairwise knowledge matching among all supervision branches, is presented. Intriguingly, it enables dense pairwise knowledge matching operations in both top-down and bottom-up directions at each training iteration, resembling a dynamic synergy process for the same task. We evaluate DKS on image classification datasets using state-of-the-art CNN architectures, and show that the models trained with it are consistently better than the corresponding counterparts. For instance, on the ImageNet classification benchmark, our ResNet-152 model outperforms the baseline model with a 1.47% margin in Top-1 accuracy. Code is available at https://github.com/sundw2014/DKS.