2022

Exploring Long-Sequence Masked Autoencoders

Hu, Ronghang, Debnath, Shoubhik, Xie, Saining et al.

Understand

Masked Autoencoding (MAE) has emerged as an effective approach for pre-training representations across multiple domains.

In contrast to discrete tokens in natural languages, the input for image MAE is continuous and subject to additional specifications.
We systematically study each input specification during the pre-training stage, and find sequence length is a key axis that further scales MAE.
Our study leads to a long-sequence version of MAE with minimal changes to the original recipe, by just decoupling the mask size from the patch size.

Built on

Backpropagation applied to handwritten zip code recognition
Yann LeCun, Bernhard Boser, John S Denker, Donnie Henderson, Richard E Howard, Wayne Hubbard, and Lawrence D Jackel · 1989
Earlier work this paper cites.
Extracting and composing robust features with denoising autoencoders
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, and Pierre-Antoine Manzagol · 2008
Earlier work this paper cites.
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei · 2009
Earlier work this paper cites.
The elements of statistical learning: data mining, inference, and prediction
Trevor Hastie, Robert Tibshirani, Jerome H Friedman, and Jerome H Friedman · 2009
Earlier work this paper cites.
Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, Pierre-Antoine Manzagol, and Léon Bottou · 2010
Earlier work this paper cites.
Imagenet classification with deep convolutional neural networks
Alex Krizhevsky, Ilya Sutskever, and Geoff Hinton · 2012
Earlier work this paper cites.
Microsoft COCO: Common objects in context
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick · 2014
Earlier work this paper cites.
Distilling the knowledge in a neural network
Original
Geoffrey Hinton, Oriol Vinyals, Jeff Dean, et al · 2015
Earlier work this paper cites.
Faster R-CNN: Towards real-time object detection with region proposal networks
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun · 2015
Earlier work this paper cites.
U-net: Convolutional networks for biomedical image segmentation
Olaf Ronneberger, Philipp Fischer, and Thomas Brox · 2015
Earlier work this paper cites.
Deep residual learning for image recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016
Earlier work this paper cites.
Context encoders: Feature learning by inpainting
Deepak Pathak, Philipp Krahenbuhl, Jeff Donahue, Trevor Darrell, and Alexei A Efros · 2016
Earlier work this paper cites.
Multi-scale context aggregation by dilated convolutions
Fisher Yu and Vladlen Koltun · 2016
Earlier work this paper cites.
DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille · 2017
Earlier work this paper cites.
Mask R-CNN
Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick · 2017
Earlier work this paper cites.
Feature pyramid networks for object detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie · 2017
Earlier work this paper cites.
Attention is all you need
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin · 2017
Earlier work this paper cites.
Places: A 10 million image database for scene recognition
Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba · 2017
Earlier work this paper cites.

Similar

Cascade R-CNN: Delving into high quality object detection
Zhaowei Cai and Nuno Vasconcelos · 2018
Cited alongside, same era.
Unified perceptual parsing for scene understanding
Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, and Jian Sun · 2018
Cited alongside, same era.
BERT: Pre-training of deep bidirectional transformers for language understanding
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova · 2019
Cited alongside, same era.
LVIS: A dataset for large vocabulary instance segmentation
Agrim Gupta, Piotr Dollar, and Ross Girshick · 2019
Cited alongside, same era.
Roberta: A robustly optimized bert pretraining approach
Original
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov · 2019
Cited alongside, same era.
Efficientnet: Rethinking model scaling for convolutional neural networks
Mingxing Tan and Quoc Le · 2019
Cited alongside, same era.
Semantic understanding of scenes through the ADE20K dataset
Bolei Zhou, Hang Zhao, Xavier Puig, Tete Xiao, Sanja Fidler, Adela Barriuso, and Antonio Torralba · 2019
Cited alongside, same era.
Deformable convnets v2: More deformable, better results
Xizhou Zhu, Han Hu, Stephen Lin, and Jifeng Dai · 2019
Cited alongside, same era.
Generative pretraining from pixels
Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever · 2020
Cited alongside, same era.
A simple framework for contrastive learning of visual representations
Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton · 2020
Cited alongside, same era.
In defense of grid features for visual question answering
Huaizu Jiang, Ishan Misra, Marcus Rohrbach, Erik Learned-Miller, and Xinlei Chen · 2020
Cited alongside, same era.
The open images dataset v4
Alina Kuznetsova, Hassan Rom, Neil Alldrin, Jasper Uijlings, Ivan Krasin, Jordi Pont-Tuset, Shahab Kamali, Stefan Popov, Matteo Malloci, Alexander Kolesnikov, et al · 2020
Cited alongside, same era.

Then

An empirical study of training self-supervised Vision Transformers
Xinlei Chen, Saining Xie, and Kaiming He · 2021
Later among the works it cites.
Peco: Perceptual codebook for bert pre-training of vision transformers
Original
Xiaoyi Dong, Jianmin Bao, Ting Zhang, Dongdong Chen, Weiming Zhang, Lu Yuan, Dong Chen, Fang Wen, and Nenghai Yu · 2021
Later among the works it cites.
An image is worth 16x16 words: Transformers for image recognition at scale
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby · 2021
Later among the works it cites.
Are large-scale datasets necessary for self-supervised pre-training?
Original
Alaaeldin El-Nouby, Gautier Izacard, Hugo Touvron, Ivan Laptev, Hervé Jegou, and Edouard Grave · 2021
Later among the works it cites.
Simple copy-paste is a strong data augmentation method for instance segmentation
Golnaz Ghiasi, Yin Cui, Aravind Srinivas, Rui Qian, Tsung-Yi Lin, Ekin D Cubuk, Quoc V Le, and Barret Zoph · 2021
Later among the works it cites.
Benchmarking detection transfer learning with vision transformers
Original
Yanghao Li, Saining Xie, Xinlei Chen, Piotr Dollar, Kaiming He, and Ross Girshick · 2021
Later among the works it cites.
Training data-efficient image transformers & distillation through attention
Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Hervé Jégou · 2021
Later among the works it cites.
SimMIM: A simple framework for masked image modeling
Original
Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, and Han Hu · 2021
Later among the works it cites.
BEiT: BERT pre-training of image transformers
Hangbo Bao, Li Dong, and Furu Wei · 2022
Closest in time.
Better plain ViT baselines for ImageNet-1k
Original
Lucas Beyer, Xiaohua Zhai, and Alexander Kolesnikov · 2022
Closest in time.
Context autoencoder for self-supervised representation learning
Original
Xiaokang Chen, Mingyu Ding, Xiaodi Wang, Ying Xin, Shentong Mo, Yunhao Wang, Shumin Han, Ping Luo, Gang Zeng, and Jingdong Wang · 2022
Closest in time.
Masked autoencoders are scalable vision learners
Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, and Ross Girshick · 2022
Closest in time.
Efficient self-supervised vision transformers for representation learning
Chunyuan Li, Jianwei Yang, Pengchuan Zhang, Mei Gao, Bin Xiao, Xiyang Dai, Lu Yuan, and Jianfeng Gao · 2022
Closest in time.
Exploring plain vision transformer backbones for object detection
Original
Yanghao Li, Hanzi Mao, Ross Girshick, and Kaiming He · 2022
Closest in time.
The devil is in the frequency: Geminated gestalt autoencoder for self-supervised visual pre-training
Original
Hao Liu, Xinghua Jiang, Xin Li, Antai Guo, Deqiang Jiang, and Bo Ren · 2022
Closest in time.
Masked feature prediction for self-supervised visual pre-training
Chen Wei, Haoqi Fan, Saining Xie, Chao-Yuan Wu, Alan Yuille, and Christoph Feichtenhofer · 2022
Closest in time.
iBOT: Image bert pre-training with online tokenizer
Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, and Tao Kong · 2022
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…