# Revisiting the Transferability of Supervised Pretraining: an MLP Perspective

arXiv: https://arxiv.org/abs/2112.00496 · HTML: https://mlsanity.com/paper/2112.00496/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 70 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 30 of 47)

- [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)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [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)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [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)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Transfusion: Understanding Transfer Learning for Medical Imaging](https://mlsanity.com/paper/1902.07208/) (2019)

## Built on by (most cited first, 30 of 36)

- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking](https://mlsanity.com/paper/2203.05328/) (2022)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [Siamese Image Modeling for Self-Supervised Vision Representation Learning](https://mlsanity.com/paper/2206.01204/) (2022)
- [HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining](https://mlsanity.com/paper/2303.05675/) (2023)
- [The Tunnel Effect: Building Data Representations in Deep Neural Networks](https://mlsanity.com/paper/2305.19753/) (2023)
- [Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs](https://mlsanity.com/paper/2302.02865/) (2023)
- [UNIC: Universal Classification Models via Multi-teacher Distillation](https://mlsanity.com/paper/2408.05088/) (2024)
- [Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning](https://mlsanity.com/paper/2206.13378/) (2022)
- [No Reason for No Supervision: Improved Generalization in Supervised Models](https://mlsanity.com/paper/2206.15369/) (2022)
- [Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation](https://mlsanity.com/paper/2303.17051/) (2023)
- [Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches](https://mlsanity.com/paper/2207.08220/) (2022)
- [Generic Knowledge Boosted Pre-training For Remote Sensing Images](https://mlsanity.com/paper/2401.04614/) (2024)
- [A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation](https://mlsanity.com/paper/2303.09165/) (2023)
- [Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning](https://mlsanity.com/paper/2502.10691/) (2025)
- [Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains](https://mlsanity.com/paper/2205.04771/) (2022)
- [Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2307.04231/) (2023)
- [EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds](https://mlsanity.com/paper/2502.05857/) (2025)
- [Revisiting the Encoding of Satellite Image Time Series](https://mlsanity.com/paper/2305.02086/) (2023)
- [DPStyler: Dynamic PromptStyler for Source-Free Domain Generalization](https://mlsanity.com/paper/2403.16697/) (2024)
- [Positive-Negative Equal Contrastive Loss for Semantic Segmentation](https://mlsanity.com/paper/2207.01417/) (2022)
- [Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks](https://mlsanity.com/paper/2211.06023/) (2022)
- [Deciphering the Projection Head: Representation Evaluation Self-supervised Learning](https://mlsanity.com/paper/2301.12189/) (2023)
- [Revisiting Supervision for Continual Representation Learning](https://mlsanity.com/paper/2311.13321/) (2023)
- [A Probabilistic Model Behind Self-Supervised Learning](https://mlsanity.com/paper/2402.01399/) (2024)
- [MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection](https://mlsanity.com/paper/2407.09920/) (2024)
- [OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions](https://mlsanity.com/paper/2210.05557/) (2022)
- [Zero-Shot and Few-Shot Learning for Lung Cancer Multi-Label Classification using Vision Transformer](https://mlsanity.com/paper/2205.15290/) (2022)
- [Improving Cross-domain Few-shot Classification with Multilayer Perceptron](https://mlsanity.com/paper/2312.09589/) (2023)
- [Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning](https://mlsanity.com/paper/2401.17802/) (2024)

## Abstract (arXiv)

The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on unsupervised pretraining methods shows superior transfer performance to their supervised counterparts. This paper revisits this phenomenon and sheds new light on understanding the transferability gap between unsupervised and supervised pretraining from a multilayer perceptron (MLP) perspective. While previous works focus on the effectiveness of MLP on unsupervised image classification where pretraining and evaluation are conducted on the same dataset, we reveal that the MLP projector is also the key factor to better transferability of unsupervised pretraining methods than supervised pretraining methods. Based on this observation, we attempt to close the transferability gap between supervised and unsupervised pretraining by adding an MLP projector before the classifier in supervised pretraining. Our analysis indicates that the MLP projector can help retain intra-class variation of visual features, decrease the feature distribution distance between pretraining and evaluation datasets, and reduce feature redundancy. Extensive experiments on public benchmarks demonstrate that the added MLP projector significantly boosts the transferability of supervised pretraining, e.g. +7.2% top-1 accuracy on the concept generalization task, +5.8% top-1 accuracy for linear evaluation on 12-domain classification tasks, and +0.8% AP on COCO object detection task, making supervised pretraining comparable or even better than unsupervised pretraining.