One-bit Supervision for Image Classification
This addresses the challenge of reducing annotation effort for image classification, though it is incremental as it builds on semi-supervised learning methods.
The paper tackles the problem of learning image classification from incomplete annotations by introducing one-bit supervision, where models query with predicted labels and receive yes/no answers, and achieves higher annotation efficiency on three benchmarks.
This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accurate label of each sample, our setting requires the model to query with a predicted label of each sample and learn from the answer whether the guess is correct. This provides one bit (yes or no) of information, and more importantly, annotating each sample becomes much easier than finding the accurate label from many candidate classes. There are two keys to training a model upon one-bit supervision: improving the guess accuracy and making use of incorrect guesses. For these purposes, we propose a multi-stage training paradigm which incorporates negative label suppression into an off-the-shelf semi-supervised learning algorithm. In three popular image classification benchmarks, our approach claims higher efficiency in utilizing the limited amount of annotations.