# Patch-level Representation Learning for Self-supervised Vision Transformers

arXiv: https://arxiv.org/abs/2206.07990 · HTML: https://mlsanity.com/paper/2206.07990/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 47 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 30 of 42)

- [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)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [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)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)

## Built on by (most cited first, 30 of 60)

- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding](https://mlsanity.com/paper/2503.06287/) (2025)
- [Perceptual Grouping in Contrastive Vision-Language Models](https://mlsanity.com/paper/2210.09996/) (2022)
- [Leveraging Hidden Positives for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2303.15014/) (2023)
- [Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations](https://mlsanity.com/paper/2308.11796/) (2023)
- [LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors](https://mlsanity.com/paper/2403.14625/) (2024)
- [Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image Analysis](https://mlsanity.com/paper/2302.05615/) (2023)
- [CrOC: Cross-View Online Clustering for Dense Visual Representation Learning](https://mlsanity.com/paper/2303.13245/) (2023)
- [Event Camera Data Dense Pre-training](https://mlsanity.com/paper/2311.11533/) (2023)
- [Location-Aware Self-Supervised Transformers for Semantic Segmentation](https://mlsanity.com/paper/2212.02400/) (2022)
- [DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions](https://mlsanity.com/paper/2309.03576/) (2023)
- [CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping](https://mlsanity.com/paper/2310.07855/) (2023)
- [ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising](https://mlsanity.com/paper/2307.12225/) (2023)
- [Near, far: Patch-ordering enhances vision foundation models' scene understanding](https://mlsanity.com/paper/2408.11054/) (2024)
- [Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning](https://mlsanity.com/paper/2306.13337/) (2023)
- [A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationships](https://mlsanity.com/paper/2408.15178/) (2024)
- [FLSL: Feature-level Self-supervised Learning](https://mlsanity.com/paper/2306.06203/) (2023)
- [A Survey of the Self Supervised Learning Mechanisms for Vision Transformers](https://mlsanity.com/paper/2408.17059/) (2024)
- [LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training](https://mlsanity.com/paper/2308.11239/) (2023)
- [Learning Anatomically Consistent Embedding for Chest Radiography](https://mlsanity.com/paper/2312.00335/) (2023)
- [DMT-JEPA: Discriminative Masked Targets for Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2405.17995/) (2024)
- [Masked Autoencoding Does Not Help Natural Language Supervision at Scale](https://mlsanity.com/paper/2301.07836/) (2023)
- [Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation](https://mlsanity.com/paper/2311.14665/) (2023)
- [WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising](https://mlsanity.com/paper/2403.11672/) (2024)
- [Decoupled Contrastive Learning for Long-Tailed Recognition](https://mlsanity.com/paper/2403.06151/) (2024)
- [I3Net: Inter-Intra-slice Interpolation Network for Medical Slice Synthesis](https://mlsanity.com/paper/2405.02857/) (2024)
- [MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning](https://mlsanity.com/paper/2506.08694/) (2025)
- [CLIP-FLow: Contrastive Learning by semi-supervised Iterative Pseudo labeling for Optical Flow Estimation](https://mlsanity.com/paper/2210.14383/) (2022)
- [Unsupervised Camouflaged Object Segmentation as Domain Adaptation](https://mlsanity.com/paper/2308.04528/) (2023)

## Abstract (arXiv)

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the underlying neural network, as the current state-of-the-art visual pretext tasks for SSL do not enjoy the benefit, i.e., they are architecture-agnostic. In particular, we focus on Vision Transformers (ViTs), which have gained much attention recently as a better architectural choice, often outperforming convolutional networks for various visual tasks. The unique characteristic of ViT is that it takes a sequence of disjoint patches from an image and processes patch-level representations internally. Inspired by this, we design a simple yet effective visual pretext task, coined SelfPatch, for learning better patch-level representations. To be specific, we enforce invariance against each patch and its neighbors, i.e., each patch treats similar neighboring patches as positive samples. Consequently, training ViTs with SelfPatch learns more semantically meaningful relations among patches (without using human-annotated labels), which can be beneficial, in particular, to downstream tasks of a dense prediction type. Despite its simplicity, we demonstrate that it can significantly improve the performance of existing SSL methods for various visual tasks, including object detection and semantic segmentation. Specifically, SelfPatch significantly improves the recent self-supervised ViT, DINO, by achieving +1.3 AP on COCO object detection, +1.2 AP on COCO instance segmentation, and +2.9 mIoU on ADE20K semantic segmentation.