# One-bit Supervision for Image Classification

arXiv: https://arxiv.org/abs/2009.06168 · HTML: https://mlsanity.com/paper/2009.06168/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2020.

## Built on by (most cited first, 10 of 10)

- [Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations](https://mlsanity.com/paper/2203.06127/) (2022)
- [Active Label Correction for Semantic Segmentation with Foundation Models](https://mlsanity.com/paper/2403.10820/) (2024)
- [Semantic Contrastive Bootstrapping for Single-positive Multi-label Recognition](https://mlsanity.com/paper/2307.07680/) (2023)
- [Enhancing Cost Efficiency in Active Learning with Candidate Set Query](https://mlsanity.com/paper/2502.06209/) (2025)
- [DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query](https://mlsanity.com/paper/2312.16931/) (2023)
- [A Human-ML Collaboration Framework for Improving Video Content Reviews](https://mlsanity.com/paper/2210.09500/) (2022)
- [Annotation Cost Efficient Active Learning for Content Based Image Retrieval](https://mlsanity.com/paper/2306.11605/) (2023)
- [Optimal and Efficient Binary Questioning for Human-in-the-Loop Annotation](https://mlsanity.com/paper/2307.01578/) (2023)
- [One-bit Supervision for Image Classification: Problem, Solution, and Beyond](https://mlsanity.com/paper/2311.15225/) (2023)
- [Annotation Cost-Efficient Active Learning for Deep Metric Learning Driven Remote Sensing Image Retrieval](https://mlsanity.com/paper/2406.10107/) (2024)

## Abstract (arXiv)

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.