SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
Shanghai Jiao Tong University（上海交通大学）；University of Washington（华盛顿大学）；The Johns Hopkins University（约翰斯·霍普金斯大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；University of California, Santa Cruz（加利福尼亚大学圣克鲁兹分校）；Tsinghua University（清华大学）；Stanford University（斯坦福大学）
Yiqing Wang, Zihan Li, Jieru Mei, Zihao Wei, Li Liu, Chen Wang, Shengtian Sang, Alan Yuille, Cihang Xie, Yuyin Zhou
Recent advancements in large-scale Vision Transformers have made significant strides in improving pre-trained models for medical image segmentation. However, these methods face a notable challenge in acquiring a substantial amount of pre-training data, particularly within the medical field. To address this limitation, we present Masked Multi-view with Swin Transformers (SwinMM), a novel multi-view pipeline for enabling accurate and data-efficient self-supervised medical image analysis. Our strategy harnesses the potential of multi-view information by incorporating two principal components. In the pre-training phase, we deploy a masked multi-view encoder devised to concurrently train masked multi-view observations through a range of diverse proxy tasks. These tasks span image reconstruction, rotation, contrastive learning, and a novel task that employs a mutual learning paradigm. This new task capitalizes on the consistency between predictions from various perspectives, enabling the extraction of hidden multi-view information from 3D medical data. In the fine-tuning stage, a cross-view decoder is developed to aggregate the multi-view information through a cross-attention block. Compared with the previous state-of-the-art self-supervised learning method Swin UNETR, SwinMM demonstrates a notable advantage on several medical image segmentation tasks. It allows for a smooth integration of multi-view information, significantly boosting both the accuracy and data-efficiency of the model. Code and models are available at https://github.com/UCSC-VLAA/SwinMM/.
The computer-assisted radiologic informative report is currently emerging in dental practice to facilitate dental care and reduce time consumption in manual panoramic radiographic interpretation. However, the amount of dental radiographs for training is very limited, particularly from the point of view of deep learning. This study aims to utilize recent self-supervised learning methods like SimMIM and UM-MAE to increase the model efficiency and understanding of the limited number of dental radiographs. We use the Swin Transformer for teeth numbering, detection of dental restorations, and insta…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text alignment. In this paper, we show that the inferior fine-tuning performance of these pre-training approaches can be significantly improved by a simple post-processing in the form of feature distillation (FD). The feature distillation converts the old representations to new representations that have a few desirable properties just like those representations produced b…
Huazhong University of Science & Technology（华中科技大学）；Tencent PCG（腾讯平台与内容事业群）
We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our two novel observations: (i) A MIM pre-trained vanilla ViT encoder can work surprisingly well in the challenging object-level recognition scenario even with randomly sampled partial observations, e.g., only 25% $\sim$ 50% of the input embeddings. (ii) In order to construct multi-scale representations for object detection from single-scale ViT, a randomly initialized compact convolutional stem supplants the pre-trained …
The development of deep learning models in medical image analysis is majorly limited by the lack of large-sized and well-annotated datasets. Unsupervised learning does not require labels and is more suitable for solving medical image analysis problems. However, most of the current unsupervised learning methods need to be applied to large datasets. To make unsupervised learning applicable to small datasets, we proposed Swin MAE, which is a masked autoencoder with Swin Transformer as its backbone. Even on a dataset of only a few thousand medical images and without using any pre-trained models, S…
The University of Tokyo（东京大学）；SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）
We present an efficient approach for Masked Image Modeling (MIM) with hierarchical Vision Transformers (ViTs), allowing the hierarchical ViTs to discard masked patches and operate only on the visible ones. Our approach consists of three key designs. First, for window attention, we propose a Group Window Attention scheme following the Divide-and-Conquer strategy. To mitigate the quadratic complexity of the self-attention w.r.t. the number of patches, group attention encourages a uniform partition that visible patches within each local window of arbitrary size can be grouped with equal size, whe…
University of Chinese Academy of Sciences（中国科学院大学）；Fudan University（复旦大学）
Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e.g., ViT), albeit hierarchical vision transformers (e.g., Swin Transformer) have potentially better properties in formulating vision inputs. In this paper, we offer a new design of hierarchical vision transformers named HiViT (short for Hierarchical ViT) that enjoys both high effici…
Picsart AI Research (PAIR)（Picsart人工智能研究院（PAIR））；University of Oregon（俄勒冈大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；IIT Roorkee（印度理工学院鲁尔基分校）
Finetuning a pretrained backbone in the encoder part of an image transformer network has been the traditional approach for the semantic segmentation task. However, such an approach leaves out the semantic context that an image provides during the encoding stage. This paper argues that incorporating semantic information of the image into pretrained hierarchical transformer-based backbones while finetuning improves the performance considerably. To achieve this, we propose SeMask, a simple and effective framework that incorporates semantic information into the encoder with the help of a semantic …
The University of Sydney（悉尼大学）；Monash University（莫纳什大学）
The DETR-like segmentors have underpinned the most recent breakthroughs in semantic segmentation, which end-to-end train a set of queries representing the class prototypes or target segments. Recently, masked attention is proposed to restrict each query to only attend to the foreground regions predicted by the preceding decoder block for easier optimization. Although promising, it relies on the learnable parameterized positional queries which tend to encode the dataset statistics, leading to inaccurate localization for distinct individual queries. In this paper, we propose a simple yet effecti…
The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder layers, which leads to inconsistent optimization goals and low utilization of decoder queries. To address this problem, we propose a mask-piloted training approach, which additionally feeds noised ground-truth masks in masked-attention and trains the model to reconstruct the original ones. Compared with the predicted masks used in mask-attention, the ground…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；Xi’an Jiaotong University（西安交通大学）
This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let the masked image modeling task learn good representations, we systematically study the major components in our framework, and find that simple designs of each component have revealed very strong representation learning performance: 1) random masking of the input image with a moderately large masked patch size (e.g., 32) makes a strong pre-text task; 2) pred…
DeepMind；VGG, Dept. of Engineering Science, University of Oxford（牛津大学工程科学系VGG）
Attention-based models are appealing for multimodal processing because inputs from multiple modalities can be concatenated and fed to a single backbone network - thus requiring very little fusion engineering. The resulting representations are however fully entangled throughout the network, which may not always be desirable: in learning, contrastive audio-visual self-supervised learning requires independent audio and visual features to operate, otherwise learning collapses; in inference, evaluation of audio-visual models should be possible on benchmarks having just audio or just video. In this …
Though image transformers have shown competitive results with convolutional neural networks in computer vision tasks, lacking inductive biases such as locality still poses problems in terms of model efficiency especially for embedded applications. In this work, we address this issue by introducing attention masks to incorporate spatial locality into self-attention heads. Local dependencies are captured efficiently with masked attention heads along with global dependencies captured by unmasked attention heads. With Masked attention image Transformer - MaiT, top-1 accuracy increases by up to 1.7…
University of Sydney（悉尼大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
The combination of transformers and masked image modeling (MIM) pre-training framework has shown great potential in various vision tasks. However, the pre-training computational budget is too heavy and withholds the MIM from becoming a practical training paradigm. This paper presents FastMIM, a simple and generic framework for expediting masked image modeling with the following two steps: (i) pre-training vision backbones with low-resolution input images; and (ii) reconstructing Histograms of Oriented Gradients (HOG) feature instead of original RGB values of the input images. In addition, we p…
HMSViT: A Hierarchical Masked Self-Supervised Vision Transformer for Corneal Nerve Segmentation and Diabetic Neuropathy Diagnosis
Department of Computing and Mathematics, Manchester Metropolitan University（计算与数学系，曼彻斯特 Metropolitan 大学）；Department of Eye and Vision Sciences, University of Liverpool（眼科学与视觉科学系，利物浦大学）；Faculty of Biology, Medicine and Health, University of Manchester（生物、医学与健康学院，曼彻斯特大学）；Department of Medicine, Weill Cornell Medicine-Qatar（医学系，Weill Cornell Medicine-Qatar）
Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）
Magnetic Resonance Imaging (MRI) scans are time consuming and precarious, since the patients remain still in a confined space for extended periods of time. To reduce scanning time, some experts have experimented with undersampled k spaces, trying to use deep learning to predict the fully sampled result. These studies report that as many as 20 to 30 minutes could be saved off a scan that takes an hour or more. However, none of these studies have explored the possibility of using masked image modeling (MIM) to predict the missing parts of MRI k spaces. This study makes use of 11161 reconstructed…
Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from two perspectives, the visualizations and the experiments, to uncover their key representational differences. From the visualizations, we find that MIM brings locality inductive bias to all layers of the trained models, but supervised models tend to focus locally at lower layers but more globally at higher layers. That may be the reason why MIM helps Vision Tr…
Nanjing University of Science and Technology（南京理工大学）；Shanghai AI Laboratory（上海人工智能实验室）
Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy. Notably, the success of the asymmetric structure relies on the "global" property of Vanilla Vision Transformer (ViT), whose self-attention mechanism reasons over arbitrary subset of discrete image patches. However, it is still unclear how the advanced Pyramid-based ViTs (e.g., PVT, Swin) can be adopted in MAE pre-training as they commonly introduce operators within "local" w…
University of California, Los Angeles（加州大学洛杉矶分校）；Microsoft Corporation（微软公司）
Vision-and-language (VL) pre-training has proven to be highly effective on various VL downstream tasks. While recent work has shown that fully transformer-based VL models can be more efficient than previous region-feature-based methods, their performance on downstream tasks often degrades significantly. In this paper, we present METER, a Multimodal End-to-end TransformER framework, through which we investigate how to design and pre-train a fully transformer-based VL model in an end-to-end manner. Specifically, we dissect the model designs along multiple dimensions: vision encoders (e.g., CLIP-…
Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art performance in various computer vision and medical image analysis tasks. In this work, we introduce a unified framework consisting of two architectures, dubbed UNetFormer, with a 3D Swin Transformer-based encoder and Convolutional Neural Network (CNN) and transformer-based decoders. In the proposed model, the encoder is linked to the decoder via skip connections at…
Improving Representation of High-frequency Components for Medical Visual Foundation Models
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；Ningbo Institute of Information Technology Application, Chinese Academy of Sciences (CAS)（中国科学院宁波信息技术应用研究所）
