# Understanding Self-Supervised Pretraining with Part-Aware Representation Learning

arXiv: https://arxiv.org/abs/2301.11915 · HTML: https://mlsanity.com/paper/2301.11915/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 27 Jan 2023.

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

- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [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)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Context Autoencoder for Self-Supervised Representation Learning](https://mlsanity.com/paper/2202.03026/) (2022)
- [Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts](https://mlsanity.com/paper/1406.2031/) (2014)
- [DetCo: Unsupervised Contrastive Learning for Object Detection](https://mlsanity.com/paper/2102.04803/) (2021)
- [PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers](https://mlsanity.com/paper/2111.12710/) (2021)
- [Self-Supervised Learning with Swin Transformers](https://mlsanity.com/paper/2105.04553/) (2021)
- [Are Large-scale Datasets Necessary for Self-Supervised Pre-training?](https://mlsanity.com/paper/2112.10740/) (2021)
- [Revealing the Dark Secrets of Masked Image Modeling](https://mlsanity.com/paper/2205.13543/) (2022)
- [MST: Masked Self-Supervised Transformer for Visual Representation](https://mlsanity.com/paper/2106.05656/) (2021)
- [Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing](https://mlsanity.com/paper/1703.05446/) (2017)
- [Understanding Contrastive Learning Requires Incorporating Inductive Biases](https://mlsanity.com/paper/2202.14037/) (2022)

## Built on by (most cited first, 7 of 7)

- [PLIP: Language-Image Pre-training for Person Representation Learning](https://mlsanity.com/paper/2305.08386/) (2023)
- [FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning](https://mlsanity.com/paper/2412.12032/) (2024)
- [Towards Free Data Selection with General-Purpose Models](https://mlsanity.com/paper/2309.17342/) (2023)
- [A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability](https://mlsanity.com/paper/2404.02462/) (2024)
- [A Review on Self-Supervised Learning for Time Series Anomaly Detection: Recent Advances and Open Challenges](https://mlsanity.com/paper/2501.15196/) (2025)
- [A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability](https://mlsanity.com/paper/2505.10351/) (2025)
- [Latent evolving World Action Model](https://mlsanity.com/paper/2609.27455/) (2026)

## Abstract (arXiv)

In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised representation pretraining methods learn part-aware representations. The study is mainly motivated by that random views, used in contrastive learning, and random masked (visible) patches, used in masked image modeling, are often about object parts. We explain that contrastive learning is a part-to-whole task: the projection layer hallucinates the whole object representation from the object part representation learned from the encoder, and that masked image modeling is a part-to-part task: the masked patches of the object are hallucinated from the visible patches. The explanation suggests that the self-supervised pretrained encoder is required to understand the object part. We empirically compare the off-the-shelf encoders pretrained with several representative methods on object-level recognition and part-level recognition. The results show that the fully-supervised model outperforms self-supervised models for object-level recognition, and most self-supervised contrastive learning and masked image modeling methods outperform the fully-supervised method for part-level recognition. It is observed that the combination of contrastive learning and masked image modeling further improves the performance.