DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
arXiv:2003.07496
Abstract
Exploring the intrinsic interconnections between the knowledge encoded in PRe-trained Deep Neural Networks (PR-DNNs) of heterogeneous tasks sheds light on their mutual transferability, and consequently enables knowledge transfer from one task to another so as to reduce the training effort of the latter. In this paper, we propose the DEeP Attribution gRAph (DEPARA) to investigate the transferability of knowledge learned from PR-DNNs. In DEPARA, nodes correspond to the inputs and are represented by their vectorized attribution maps with regards to the outputs of the PR-DNN. Edges denote the relatedness between inputs and are measured by the similarity of their features extracted from the PR-DNN. The knowledge transferability of two PR-DNNs is measured by the similarity of their corresponding DEPARAs. We apply DEPARA to two important yet under-studied problems in transfer learning: pre-trained model selection and layer selection. Extensive experiments are conducted to demonstrate the effectiveness and superiority of the proposed method in solving both these problems. Code, data and models reproducing the results in this paper are available at \url{https://github.com/zju-vipa/DEPARA}.
arXiv commentAccepted by CVPR2020 (oral)
References in corpus (11)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Distilling the Knowledge in a Neural Network
- Deep Residual Learning for Image Recognition
- How transferable are features in deep neural networks?
- Axiomatic Attribution for Deep Networks
- Learning Important Features Through Propagating Activation Differences
- Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
- Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
- What makes ImageNet good for transfer learning?
- Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
- Factors of Transferability for a Generic ConvNet Representation