Explicit Connection Distillation

Lujun Li, Yikai Wang, Anbang Yao, Yi Qian, Xiao Zhou, Ke He

Abstract: One effective way to ease the deployment of deep neural networks on resource constrained devices is Knowledge Distillation (KD), which boosts the accuracy of a low-capacity student model by mimicking the learnt information of a high-capacity teacher (either a single model or a multi-model ensemble). Although great progress has been attained on KD research, existing efforts are primarily invested to design better distillation losses by using soft logits or intermediate feature representations of the teacher as the extra supervision. In this paper, we present Explicit Connection Distillation (ECD), a new KD framework, which addresses the knowledge distillation problem in a novel perspective of bridging dense intermediate feature connections between a student network and its corresponding teacher generated automatically in the training, achieving knowledge transfer goal via direct cross-network layer-to-layer gradients propagation. ECD has two interdependent modules. In the first module, given a student network, an auxiliary teacher architecture is temporarily generated conditioned on strengthening feature representations of basic convolutions of the student network via replacing them with dynamic additive convolutions and keeping the other layers unchanged in structure. The teacher generated in this way guarantees its superior capacity and makes a perfect feature alignment (both in input and output dimensions) to the student at every convolutional layer. In the second module, dense feature connections between the aligned convolutional layers from the student to its auxiliary teacher are introduced, which allows explicit layer-to-layer gradients propagation from the teacher to the student via the merged model training from scratch. Intriguingly, as feature connection direction is one-way, all feature connections together with the auxiliary teacher merely exist during training phase. Experiments on popular image classification tasks validate the effectiveness of our method. Code will be made publicly available.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=pKZZ54fk1o