# OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning

arXiv: https://arxiv.org/abs/2012.11552 · HTML: https://mlsanity.com/paper/2012.11552/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

## Built on by (most cited first, 30 of 65)

- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [What to Hide from Your Students: Attention-Guided Masked Image Modeling](https://mlsanity.com/paper/2203.12719/) (2022)
- [Contrastive Learning with Stronger Augmentations](https://mlsanity.com/paper/2104.07713/) (2021)
- [Self-Supervised Learning of Object Parts for Semantic Segmentation](https://mlsanity.com/paper/2204.13101/) (2022)
- [ALSO: Automotive Lidar Self-supervision by Occupancy estimation](https://mlsanity.com/paper/2212.05867/) (2022)
- [Unsupervised Object Localization: Observing the Background to Discover Objects](https://mlsanity.com/paper/2212.07834/) (2022)
- [A Closer Look at Few-shot Classification Again](https://mlsanity.com/paper/2301.12246/) (2023)
- [Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data](https://mlsanity.com/paper/2303.13664/) (2023)
- [Three Pillars improving Vision Foundation Model Distillation for Lidar](https://mlsanity.com/paper/2310.17504/) (2023)
- [Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss](https://mlsanity.com/paper/2301.05709/) (2023)
- [Reverse Engineering Self-Supervised Learning](https://mlsanity.com/paper/2305.15614/) (2023)
- [Self-Supervised Classification Network](https://mlsanity.com/paper/2103.10994/) (2021)
- [VkD: Improving Knowledge Distillation using Orthogonal Projections](https://mlsanity.com/paper/2403.06213/) (2024)
- [BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds](https://mlsanity.com/paper/2310.17281/) (2023)
- [Bag of Instances Aggregation Boosts Self-supervised Distillation](https://mlsanity.com/paper/2107.01691/) (2021)
- [Continual Barlow Twins: continual self-supervised learning for remote sensing semantic segmentation](https://mlsanity.com/paper/2205.11319/) (2022)
- [Prompt Tuning for Parameter-efficient Medical Image Segmentation](https://mlsanity.com/paper/2211.09233/) (2022)
- [Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning](https://mlsanity.com/paper/2507.14137/) (2025)
- [Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2304.06461/) (2023)
- [Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation](https://mlsanity.com/paper/2203.11160/) (2022)
- [Self-Knowledge Distillation via Dropout](https://mlsanity.com/paper/2208.05642/) (2022)
- [Subsidiary Prototype Alignment for Universal Domain Adaptation](https://mlsanity.com/paper/2210.15909/) (2022)
- [OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks](https://mlsanity.com/paper/2404.14027/) (2024)
- [Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches](https://mlsanity.com/paper/2207.08220/) (2022)
- [UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning](https://mlsanity.com/paper/2506.07087/) (2025)
- [MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments](https://mlsanity.com/paper/2307.09361/) (2023)
- [Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing](https://mlsanity.com/paper/2209.03268/) (2022)
- [Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2212.06486/) (2022)
- [MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors](https://mlsanity.com/paper/2303.03679/) (2023)

## Abstract (arXiv)

Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the idea of making such a representation invariant under different types of perturbations, especially via contrastive-based instance discrimination training. Although effective visual representations should indeed exhibit such invariances, there are other important characteristics, such as encoding contextual reasoning skills, for which alternative reconstruction-based approaches might be better suited. With this in mind, we propose a teacher-student scheme to learn representations by training a convolutional net to reconstruct a bag-of-visual-words (BoW) representation of an image, given as input a perturbed version of that same image. Our strategy performs an online training of both the teacher network (whose role is to generate the BoW targets) and the student network (whose role is to learn representations), along with an online update of the visual-words vocabulary (used for the BoW targets). This idea effectively enables fully online BoW-guided unsupervised learning. Extensive experiments demonstrate the interest of our BoW-based strategy which surpasses previous state-of-the-art methods (including contrastive-based ones) in several applications. For instance, in downstream tasks such Pascal object detection, Pascal classification and Places205 classification, our method improves over all prior unsupervised approaches, thus establishing new state-of-the-art results that are also significantly better even than those of supervised pre-training. We provide the implementation code at https://github.com/valeoai/obow.