Masked image modeling (MIM) has demonstrated impressive results in self-supervised representation learning by recovering corrupted image patches. However, most existing studies operate on low-level image pixels, which hinders the exploitation of high-level semantics for representation models. In this work, we propose to use a semantic-rich visual tokenizer as the reconstruction target for masked prediction, providing a systematic way to promote MIM from pixel-level to semantic-level. Specifically, we propose vector-quantized knowledge distillation to train the tokenizer, which discretizes a continuous semantic space to compact codes. We then pretrain vision Transformers by predicting the original visual tokens for the masked image patches. Furthermore, we introduce a patch aggregation strategy which associates discrete image patches to enhance global semantic representation. Experiments on image classification and semantic segmentation show that BEiT v2 outperforms all compared MIM methods. On ImageNet-1K (224 size), the base-size BEiT v2 achieves 85.5% top-1 accuracy for fine-tuning and 80.1% top-1 accuracy for linear probing. The large-size BEiT v2 obtains 87.3% top-1 accuracy for ImageNet-1K (224 size) fine-tuning, and 56.7% mIoU on ADE20K for semantic segmentation. The code and pretrained models are available at https://aka.ms/beitv2.
Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning. A seminal work, BEiT, casts MIM as a classification task with a visual vocabulary, tokenizing the continuous visual signals into discrete vision tokens using a pre-learned dVAE. Despite a feasible solution, the improper discretization hinders further improvements of image pre-training. Since image discretization has no ground-truth answers, we believe that the masked patch should not be assigned with a unique token id even if a better tokenizer can be obtain…
ByteDance（字节跳动）；Johns Hopkins University（约翰斯·霍普金斯大学）；Shanghai Jiao Tong University（上海交通大学）；UC Santa Cruz（加州大学圣克鲁兹分校）
The success of language Transformers is primarily attributed to the pretext task of masked language modeling (MLM), where texts are first tokenized into semantically meaningful pieces. In this work, we study masked image modeling (MIM) and indicate the advantages and challenges of using a semantically meaningful visual tokenizer. We present a self-supervised framework iBOT that can perform masked prediction with an online tokenizer. Specifically, we perform self-distillation on masked patch tokens and take the teacher network as the online tokenizer, along with self-distillation on the class t…
A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked "language" model…
Harbin Institute of Technology（哈尔滨工业大学）；Microsoft Research（微软研究院）
We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to pretrain vision Transformers. Specifically, each image has two views in our pre-training, i.e, image patches (such as 16x16 pixels), and visual tokens (i.e., discrete tokens). We first "tokenize" the original image into visual tokens. Then we randomly mask some image patches and fed them into the backbone Transformer. The pre-training objective …
We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with a shared Transformer. Specifically, we perform masked vision-language modeling on image-text pairs, masked language modeling on texts, and masked image modeling on images. VL-BEiT is learned from scratch with one unified pretraining task, one shared backbone, and one-stage training. Our method is conceptually simple and empirically effective. Experimental r…
Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Monash University（莫纳什大学）；Nile University（尼罗河大学）；Nanyang Technological University（南洋理工大学）
Learning Nuclei Representations with Masked Image Modelling
University of Cologne（科隆大学）；University Hospital Cologne（科隆大学医院）；Institute for Biomedical Informatics（生物医学信息学研究所）；Center for Molecular Medicine Cologne (CMMC)（科隆分子医学中心（CMMC））；Institute of Pathology（病理学研究所）；Cologne Excellence Cluster on Cellular Stress Responses in Aging-Associated Diseases (CECAD)（科隆衰老相关疾病细胞应激反应卓越集群（CECAD））
ARC Lab（ARC实验室）；Peking University（北京大学）；Huazhong University of Science and Technology（华中科技大学）；Foundation Technology Center（基础技术中心）；Tsinghua University（清华大学）；Tencent PCG（腾讯平台与内容事业群）
Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision dictionary look-up. MIM recently dominates this line of research with state-of-the-art performance on vision Transformers (ViTs), where the core is to enhance the patch-level visual context capturing of the network via denoising auto-encoding mechanism. Rather than tailoring image tokenizers with extra training stages as in previous works, we unleash the great poten…
Microsoft Research Asia（微软亚洲研究院）；University of Cambridge（剑桥大学）
Deep supervision, which involves extra supervisions to the intermediate features of a neural network, was widely used in image classification in the early deep learning era since it significantly reduces the training difficulty and eases the optimization like avoiding gradient vanish over the vanilla training. Nevertheless, with the emergence of normalization techniques and residual connection, deep supervision in image classification was gradually phased out. In this paper, we revisit deep supervision for masked image modeling (MIM) that pre-trains a Vision Transformer (ViT) via a mask-and-pr…
Huawei Inc.（华为技术有限公司）；University of Science and Technology of China（中国科学技术大学）
Recently, masked image modeling (MIM) has become a promising direction for visual pre-training. In the context of vision transformers, MIM learns effective visual representation by aligning the token-level features with a pre-defined space (e.g., BEIT used a d-VAE trained on a large image corpus as the tokenizer). In this paper, we go one step further by introducing guidance from other modalities and validating that such additional knowledge leads to impressive gains for visual pre-training. The proposed approach is named Multimodality-guided Visual Pre-training (MVP), in which we replace the …
With the development of generative-based self-supervised learning (SSL) approaches like BeiT and MAE, how to learn good representations by masking random patches of the input image and reconstructing the missing information has grown in concern. However, BeiT and PeCo need a "pre-pretraining" stage to produce discrete codebooks for masked patches representing. MAE does not require a pre-training codebook process, but setting pixels as reconstruction targets may introduce an optimization gap between pre-training and downstream tasks that good reconstruction quality may not always lead to the hi…
Shanghai AI Laboratory（上海人工智能实验室）；Simon Fraser University（西蒙弗雷泽大学）；The Chinese University of Hong Kong（香港中文大学）
Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. However, subsequent works have complicated the framework with new auxiliary tasks or extra pre-trained models, inevitably increasing computational overhead. This paper undertakes a fundamental analysis of MIM from the perspective of pixel reconstruction, which examines the input image patches and reconstruction target, and highlights two critical but previously overlooked bottlenecks. Based on this analysis, we propose a remarkably simple and effective method, {\ourmethod}, that e…
Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level semantics for the encoder, thus suffering from sub-optimal learned representations and long pre-training epochs. To alleviate this, previous methods simply replace the pixel reconstruction targets of 75% masked tokens by encoded features from pre-trained image-image (DINO) or image-language (CLIP) contrastive learning. Different from those efforts, we propose to Mimic before R…
We present Point-BERT, a new paradigm for learning Transformers to generalize the concept of BERT to 3D point cloud. Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers. Specifically, we first divide a point cloud into several local point patches, and a point cloud Tokenizer with a discrete Variational AutoEncoder (dVAE) is designed to generate discrete point tokens containing meaningful local information. Then, we randomly mask out some patches of input point clouds and feed them into the backbone Transformers. The pre-training objective is to …
The University of Hong Kong（香港大学）；ARC Lab（ARC实验室）；UC Berkeley（加州大学伯克利分校）；National University of Singapore（新加坡国立大学）；Tsinghua University（清华大学）；Tencent PCG（腾讯平台与内容事业群）
Dominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations, but ignore detailed local semantics. The recent success of image BERT pre-training with masked visual modeling that promotes the learning of local visual context, motivates a possible solution to address the above limitation. In this work, we for the first time investigate masked visual modeling in video-text pre-training with the "dual-encoder" architecture. We perform Masked vis…
University of Oxford（牛津大学）；The University of Edinburgh（爱丁堡大学）；The Alan Turing Institute（艾伦·图灵研究所）；DeepMind（深度思维）
We propose ADIOS, a masked image model (MIM) framework for self-supervised learning, which simultaneously learns a masking function and an image encoder using an adversarial objective. The image encoder is trained to minimise the distance between representations of the original and that of a masked image. The masking function, conversely, aims at maximising this distance. ADIOS consistently improves on state-of-the-art self-supervised learning (SSL) methods on a variety of tasks and datasets -- including classification on ImageNet100 and STL10, transfer learning on CIFAR10/100, Flowers102 and …
Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding
Hokkaido University（北海道大学）；RIKEN Center for Computational Science (R-CCS)（理化学研究所计算科学研究中心（R-CCS））；Oak Ridge National Laboratory（橡树岭国家实验室）；A*STAR（新加坡科技研究局）；Institute of Science Tokyo（东京科学大学）；Japan Synchrotron Radiation Research Institute (JASRI)（日本同步辐射研究所（JASRI））；RIKEN SPring-8 Center（理化学研究所SPring-8中心）
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, China（中国科学院智能信息处理重点实验室（中国科学院计算技术研究所，中国））；University of Chinese Academy of Sciences, China（中国科学院大学）
Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Science
ETH AI Center（苏黎世联邦理工学院人工智能中心）；IBM Research Europe（IBM欧洲研究院）；Seminar for Applied Mathematics, ETH Zurich（苏黎世联邦理工学院应用数学系）；Swiss Data Science Center, ETH Zurich（瑞士数据科学中心，苏黎世联邦理工学院）
Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China（多媒体信息处理国家重点实验室，计算机科学学院，北京大学，北京，中国）；State Key Discipline Laboratory of Wide Band-Gap Semiconductor Technology, School of Microelectronics, Xidian University, Xi'an, China（宽带隙半导体技术重点学科实验室，微电子学院，西安电子科技大学，西安，中国）
On the Role of Discrete Tokenization in Visual Representation Learning
School of Mathematical Sciences, Peking University（北京大学数学科学学院）；School of Intelligence Science and Technology, Peking University（北京大学智能科学技术学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；MIT（麻省理工学院）
VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning
National Engineering Research Center of Speech and Language Information Processing（国家语音及语言信息处理工程技术研究中心）；University of Science and Technology of China（中国科学技术大学）；Microsoft Corporation（微软公司）
Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation
Nanjing University（南京大学）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）；University of Minnesota Twin Cities（明尼苏达大学 Twin Cities 分校）
BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities
The University of Hong Kong（香港大学）；Hong Kong University of Science and Technology（香港科技大学）；Intellifusion（云天励飞）；The Chinese University of Hong Kong（香港中文大学）
