# Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation

arXiv: https://arxiv.org/abs/2206.06363 · HTML: https://mlsanity.com/paper/2206.06363/

## Key facts

- Cited by 54 papers in the map (data through 7 Oct 2026).
- Builds on 72 of its 92 references that are in the map.
- First posted on arXiv 13 Jun 2022.

## Builds on (most cited first, 30 of 72)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)

## Built on by (most cited first, 30 of 54)

- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://mlsanity.com/paper/2210.00939/) (2022)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Unsupervised Object Localization: Observing the Background to Discover Objects](https://mlsanity.com/paper/2212.07834/) (2022)
- [LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding](https://mlsanity.com/paper/2303.09665/) (2023)
- [Hard Patches Mining for Masked Image Modeling](https://mlsanity.com/paper/2304.05919/) (2023)
- [ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2210.05944/) (2022)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [Unsupervised Universal Image Segmentation](https://mlsanity.com/paper/2312.17243/) (2023)
- [Segment Anything without Supervision](https://mlsanity.com/paper/2406.20081/) (2024)
- [NamedMask: Distilling Segmenters from Complementary Foundation Models](https://mlsanity.com/paper/2209.11228/) (2022)
- [TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training](https://mlsanity.com/paper/2312.12828/) (2023)
- [Few-Shot Panoptic Segmentation With Foundation Models](https://mlsanity.com/paper/2309.10726/) (2023)
- [Causal Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2310.07379/) (2023)
- [A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting](https://mlsanity.com/paper/2401.10227/) (2024)
- [Object-centric Learning with Cyclic Walks between Parts and Whole](https://mlsanity.com/paper/2302.08023/) (2023)
- [Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey](https://mlsanity.com/paper/2310.12904/) (2023)
- [CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers](https://mlsanity.com/paper/2403.07700/) (2024)
- [RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters](https://mlsanity.com/paper/2303.08682/) (2023)
- [MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2304.09913/) (2023)
- [The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models](https://mlsanity.com/paper/2404.11957/) (2024)
- [ProMerge: Prompt and Merge for Unsupervised Instance Segmentation](https://mlsanity.com/paper/2409.18961/) (2024)
- [Scene-Centric Unsupervised Panoptic Segmentation](https://mlsanity.com/paper/2504.01955/) (2025)
- [Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals](https://mlsanity.com/paper/2404.16818/) (2024)
- [LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training](https://mlsanity.com/paper/2308.11239/) (2023)
- [Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2304.07314/) (2023)
- [Optical Flow boosts Unsupervised Localization and Segmentation](https://mlsanity.com/paper/2307.13640/) (2023)
- [Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation](https://mlsanity.com/paper/2311.14665/) (2023)
- [A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation](https://mlsanity.com/paper/2405.19035/) (2024)

## Abstract (arXiv)

The task of unsupervised semantic segmentation aims to cluster pixels into semantically meaningful groups. Specifically, pixels assigned to the same cluster should share high-level semantic properties like their object or part category. This paper presents MaskDistill: a novel framework for unsupervised semantic segmentation based on three key ideas. First, we advocate a data-driven strategy to generate object masks that serve as a pixel grouping prior for semantic segmentation. This approach omits handcrafted priors, which are often designed for specific scene compositions and limit the applicability of competing frameworks. Second, MaskDistill clusters the object masks to obtain pseudo-ground-truth for training an initial object segmentation model. Third, we leverage this model to filter out low-quality object masks. This strategy mitigates the noise in our pixel grouping prior and results in a clean collection of masks which we use to train a final segmentation model. By combining these components, we can considerably outperform previous works for unsupervised semantic segmentation on PASCAL (+11% mIoU) and COCO (+4% mask AP50). Interestingly, as opposed to existing approaches, our framework does not latch onto low-level image cues and is not limited to object-centric datasets. The code and models will be made available.