# DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks

arXiv: https://arxiv.org/abs/2304.00571 · HTML: https://mlsanity.com/paper/2304.00571/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 129 of its 186 references that are in the map.
- First posted on arXiv 2 Apr 2023.

## Builds on (most cited first, 30 of 129)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (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)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (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)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)

## Built on by (most cited first, 22 of 22)

- [HIPTrack: Visual Tracking with Historical Prompts](https://mlsanity.com/paper/2311.02072/) (2023)
- [Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance](https://mlsanity.com/paper/2403.05231/) (2024)
- [Scalable Video Object Segmentation with Simplified Framework](https://mlsanity.com/paper/2308.09903/) (2023)
- [VideoMAC: Video Masked Autoencoders Meet ConvNets](https://mlsanity.com/paper/2402.19082/) (2024)
- [RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba](https://mlsanity.com/paper/2408.08827/) (2024)
- [Masked Modeling for Self-supervised Representation Learning on Vision and Beyond](https://mlsanity.com/paper/2401.00897/) (2023)
- [RTracker: Recoverable Tracking via PN Tree Structured Memory](https://mlsanity.com/paper/2403.19242/) (2024)
- [Divert More Attention to Vision-Language Object Tracking](https://mlsanity.com/paper/2307.10046/) (2023)
- [Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation](https://mlsanity.com/paper/2410.11586/) (2024)
- [OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework](https://mlsanity.com/paper/2403.08682/) (2024)
- [Tracking Transforming Objects: A Benchmark](https://mlsanity.com/paper/2404.18143/) (2024)
- [In Defense and Revival of Bayesian Filtering for Thermal Infrared Object Tracking](https://mlsanity.com/paper/2402.17098/) (2024)
- [LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking](https://mlsanity.com/paper/2405.17660/) (2024)
- [Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking](https://mlsanity.com/paper/2503.11247/) (2025)
- [Synchronizing Vision and Language: Bidirectional Token-Masking AutoEncoder for Referring Image Segmentation](https://mlsanity.com/paper/2311.17952/) (2023)
- [Monocular Per-Object Distance Estimation with Masked Object Modeling](https://mlsanity.com/paper/2401.03191/) (2024)
- [Adaptively Bypassing Vision Transformer Blocks for Efficient Visual Tracking](https://mlsanity.com/paper/2406.08037/) (2024)
- [Robust Visual Tracking by Motion Analyzing](https://mlsanity.com/paper/2309.03247/) (2023)
- [Optimized Information Flow for Transformer Tracking](https://mlsanity.com/paper/2402.08195/) (2024)
- [Learning Tracking Representations from Single Point Annotations](https://mlsanity.com/paper/2404.09504/) (2024)
- [Beyond Traditional Single Object Tracking: A Survey](https://mlsanity.com/paper/2405.10439/) (2024)
- [M2P: Improving Visual Foundation Models with Mask-to-Point Weakly-Supervised Learning for Dense Point Tracking](https://mlsanity.com/paper/2603.17813/) (2026)

## Abstract (arXiv)

This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS), self-supervised visual correspondence learning, dense tracking tasks including optical flow estimation and long-term point tracking, and 3D point cloud tracking. Specifically, our work explores to provide a general representation to boost the temporal matching ability in various downstream tracking tasks. To achieve this, we firstly find that a simple extension of MAE, which randomly masks out frame patches in videos and reconstruct the frame pixels, heavily relies on spatial cues while ignoring temporal relations for frame reconstruction, thus leading to sub-optimal temporal matching representations. To alleviate this, we propose DropMAE, which adaptively performs spatial-attention dropout in the frame reconstruction to facilitate temporal correspondence learning in videos. We obtain several important findings with DropMAE: 1) DropMAE is a strong and efficient temporal matching learner, which achieves better fine-tuning results on matching-based tasks than the ImageNet-based MAE with 2x faster pre-training speed. 2) DropMAE is effective for different tracking tasks, i.e., object-level matching tasks including VOT and VOS, dense tracking tasks including optical flow estimation and tracking any point (TAP), and even 3D tracking in the different modality of point cloud data. Since none exists, we build ViT-based trackers for different downstream tracking tasks, and our pre-trained DropMAE model can be directly loaded in these ViT-based trackers for fine-tuning without further modifications. Experiments on 6 downstream tracking tasks demonstrate the effectiveness of DropMAE as a general pre-trained representation for diverse tracking tasks.