Colorization as a Proxy Task for Visual Understanding

TL;DR

This paper explores using automatic colorization as a self-supervised proxy task to improve visual understanding, achieving state-of-the-art results without ImageNet labels and analyzing factors influencing its effectiveness.

Contribution

It demonstrates that colorization as a self-supervised task can match ImageNet pretraining in various tasks and provides an in-depth analysis of factors affecting its success.

Findings

State-of-the-art results on VOC segmentation and classification without ImageNet labels

Analysis of loss formulation, training details, and architecture impacts

Colorization offers a supervisory signal comparable to ImageNet pretraining

Abstract

We investigate and improve self-supervision as a drop-in replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has been shown to be more promising for utilizing unlabeled data than other, traditional unsupervised learning methods. We build on this success and evaluate the ability of our self-supervised network in several contexts. On VOC segmentation and classification tasks, we present results that are state-of-the-art among methods not using ImageNet labels for pretraining representations. Moreover, we present the first in-depth analysis of self-supervision via colorization, concluding that formulation of the loss, training details and network architecture play important roles in its effectiveness. This investigation is further expanded by revisiting the ImageNet pretraining paradigm, asking questions such as: How much training data is needed? How many labels are needed? How much do features change when fine-tuned? We relate these questions back to self-supervision by showing that colorization provides a similarly powerful supervisory signal as various flavors of ImageNet pretraining.