Multi Task Learning of Different Class Label Representations for Stronger Models

Judah A Goldfeder, Boyuan Chen, Hod Lipson

Keywords: Label Representation, Image Classification, Representation Learning, Multi-Task Learning

TL;DR: We present a new way of representing class labels, and train a network to recognize them as an auxiliary task, leading to stronger models.

Abstract: We find that the way in which class labels are represented can have a powerful effect on how well models trained on them learn. In classification, the standard way of representing class labels is as one-hot vectors. We present a new way of representing class labels called Binary Labels, where each class label is a large binary vector. We further introduce a new paradigm, multi task learning on different label representations. We train a network on two tasks. The main task is to classify images based on their one-hot label, and the auxiliary task is to classify images based on their Binary Label. We show that networks trained on both tasks have many advantages, including higher accuracy across a wide variety of datasets and architectures, both when trained from scratch and when using transfer learning. Networks trained on both tasks are also much more effective when training data is limited, and seem to do especially well on more challenging problems.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

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

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning