Auto-Transfer: Learning to Route Transferable RepresentationsDownload PDF

Published: 28 Jan 2022, Last Modified: 13 Feb 2023ICLR 2022 PosterReaders: Everyone
Keywords: Feature routing, Transferable Representations
Abstract: Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be difficult to obtain in many applications. Existing approaches typically constrain the target deep neural network (DNN) feature representations to be close to the source DNNs feature representations, which can be limiting. We, in this paper, propose a novel adversarial multi-armed bandit approach that automatically learns to route source representations to appropriate target representations following which they are combined in meaningful ways to produce accurate target models. We see upwards of 5\% accuracy improvements compared with the state-of-the-art knowledge transfer methods on four benchmark (target) image datasets CUB200, Stanford Dogs, MIT67, and Stanford40 where the source dataset is ImageNet. We qualitatively analyze the goodness of our transfer scheme by showing individual examples of the important features focused on by our target network at different layers compared with the (closest) competitors. We also observe that our improvement over other methods is higher for smaller target datasets making it an effective tool for small data applications that may benefit from transfer learning.
One-sentence Summary: This paper offers a novel transfer method that uses a routing function to select source-target pairs as well as aggregation functions that combine source and target features (as opposed to matching source to target features).
Supplementary Material: zip
19 Replies