We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in the encoded representation space. The pretraining tasks include two tasks: masked representation prediction - predict the representations for the masked patches, and masked patch reconstruction - reconstruct the masked patches. The network is an encoder-regressor-decoder architecture: the encoder takes the visible patches as input; the regressor predicts the representations of the masked patches, which are expected to be aligned with the representations computed from the encoder, using the representations of visible patches and the positions of visible and masked patches; the decoder reconstructs the masked patches from the predicted encoded representations. The CAE design encourages the separation of learning the encoder (representation) from completing the pertaining tasks: masked representation prediction and masked patch reconstruction tasks, and making predictions in the encoded representation space empirically shows the benefit to representation learning. We demonstrate the effectiveness of our CAE through superior transfer performance in downstream tasks: semantic segmentation, object detection and instance segmentation, and classification. The code will be available at https://github.com/Atten4Vis/CAE.
Virginia Polytechnic Institute and State University（弗吉尼亚理工学院暨州立大学）
Automated inspection and detection of foreign objects on railways is important for rail transportation safety as it helps prevent potential accidents and trains derailment. Most existing vision-based approaches focus on the detection of frontal intrusion objects with prior labels, such as categories and locations of the objects. In reality, foreign objects with unknown categories can appear anytime on railway tracks. In this paper, we develop a semi-supervised convolutional autoencoder based framework that only requires railway track images without prior knowledge on the foreign objects in the…
Carnegie Mellon University（卡内基梅隆大学）；University of Oxford（牛津大学）；Utrecht University（乌得勒支大学）
Cellular electron cryo-tomography enables the 3D visualization of cellular organization in the near-native state and at submolecular resolution. However, the contents of cellular tomograms are often complex, making it difficult to automatically isolate different in situ cellular components. In this paper, we propose a convolutional autoencoder-based unsupervised approach to provide a coarse grouping of 3D small subvolumes extracted from tomograms. We demonstrate that the autoencoder can be used for efficient and coarse characterization of features of macromolecular complexes and surfaces, such…
Technical University of Denmark（丹麦技术大学）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
In this paper we propose a semi-supervised variational autoencoder for classification of overall survival groups from tumor segmentation masks. The model can use the output of any tumor segmentation algorithm, removing all assumptions on the scanning platform and the specific type of pulse sequences used, thereby increasing its generalization properties. Due to its semi-supervised nature, the method can learn to classify survival time by using a relatively small number of labeled subjects. We validate our model on the publicly available dataset from the Multimodal Brain Tumor Segmentation Chal…
Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based SSL framework consisting of a parallel MAE branch to assist the visual representation learning and make the pseudo labels more accurate. The MAE branch is designed as an asymmetric architecture consisting of a lightweight decoder and a shared-weights encoder. We feed the weakly-augmented unlabeled data with a high masking ratio to the MAE branch and reconstru…
Autoencoders are unsupervised deep learning models used for learning representations. In literature, autoencoders have shown to perform well on a variety of tasks spread across multiple domains, thereby establishing widespread applicability. Typically, an autoencoder is trained to generate a model that minimizes the reconstruction error between the input and the reconstructed output, computed in terms of the Euclidean distance. While this can be useful for applications related to unsupervised reconstruction, it may not be optimal for classification. In this paper, we propose a novel Supervised…
National University of Singapore（新加坡国立大学）；ZheJiang University（浙江大学）；Peking University（北京大学）；Tencent Data Platform（腾讯数据平台）；Pengcheng Laboratory（鹏城实验室）
As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a neat scheme of masked autoencoders for point cloud self-supervised learning, addressing the challenges posed by point cloud's properties, including leakage of location information and uneven information density. Concretely, we divide the input point cloud into irregular point patches and randomly mask them at a high ratio. Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tok…
University of Notre Dame（圣母大学）；IIIT-Delhi（德里 Indraprastha 信息技术学院）
Digital retouching of face images is becoming more widespread due to the introduction of software packages that automate the task. Several researchers have introduced algorithms to detect whether a face image is original or retouched. However, previous work on this topic has not considered whether or how accuracy of retouching detection varies with the demography of face images. In this paper, we introduce a new Multi-Demographic Retouched Faces (MDRF) dataset, which contains images belonging to two genders, male and female, and three ethnicities, Indian, Chinese, and Caucasian. Further, retou…
National Institute of Neurological Disorders and Stroke（美国国家神经疾病与中风研究所）；University of Houston（休斯顿大学）
Reliable large-scale cell detection and segmentation is the fundamental first step to understanding biological processes in the brain. The ability to phenotype cells at scale can accelerate preclinical drug evaluation and system-level brain histology studies. The impressive advances in deep learning offer a practical solution to cell image detection and segmentation. Unfortunately, categorizing cells and delineating their boundaries for training deep networks is an expensive process that requires skilled biologists. This paper presents a novel self-supervised Dual-Loss Adaptive Masked Autoenco…
Computer Vision Center（计算机视觉中心）；Digital Research Center of Sfax（斯法克斯数字研究中心）
In this paper, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE), a self-supervised model designed to tackle two tasks, text recognition (handwritten or scene-text) and document image enhancement. We start by employing a transformer-based architecture that incorporates three pretext tasks as learning objectives to be optimized during pre-training without the usage of labeled data. Each of the pretext objectives is specifically tailored for the final downstream tasks. We conduct several ablation experiments that confirm the design choice of the selected pretext tasks. Importantly…
School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）
Classic variational autoencoders are used to learn complex data distributions, that are built on standard function approximators. Especially, VAE has shown promise on a lot of complex task. In this paper, a new autoencoder model - classification supervised autoencoder (CSAE) based on predefined evenly-distributed class centroids (PEDCC) is proposed. Our method uses PEDCC of latent variables to train the network to ensure the maximization of inter-class distance and the minimization of inner-class distance. Instead of learning mean/variance of latent variables distribution and taking reparamete…
West Virginia University（西弗吉尼亚大学）；IIIT-Delhi（德里印度理工学院）；Texas A&M University-Kingsville（德克萨斯农工大学金斯维尔分校）
Identifying kinship relations has garnered interest due to several applications such as organizing and tagging the enormous amount of videos being uploaded on the Internet. Existing research in kinship verification primarily focuses on kinship prediction with image pairs. In this research, we propose a new deep learning framework for kinship verification in unconstrained videos using a novel Supervised Mixed Norm regularization Autoencoder (SMNAE). This new autoencoder formulation introduces class-specific sparsity in the weight matrix. The proposed three-stage SMNAE based kinship verification…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Sree Chitra Tirunal Institute for Medical Sciences and Technology（Sree Chitra Tirunal医学科学与技术研究所）
The work presented explores the use of denoising autoencoders (DAE) for brain lesion detection, segmentation and false positive reduction. Stacked denoising autoencoders (SDAE) were pre-trained using a large number of unlabeled patient volumes and fine tuned with patches drawn from a limited number of patients (n=20, 40, 65). The results show negligible loss in performance even when SDAE was fine tuned using 20 patients. Low grade glioma (LGG) segmentation was achieved using a transfer learning approach wherein a network pre-trained with High Grade Glioma (HGG) data was fine tuned using LGG im…
University of Surrey（萨里大学）；ByteDance（字节跳动）；The University of Hong Kong（香港大学）；Harbin Institute of Technology（哈尔滨工业大学）
Masked autoencoders (MAEs) have emerged recently as art self-supervised spatiotemporal representation learners. Inheriting from the image counterparts, however, existing video MAEs still focus largely on static appearance learning whilst are limited in learning dynamic temporal information hence less effective for video downstream tasks. To resolve this drawback, in this work we present a motion-aware variant -- MotionMAE. Apart from learning to reconstruct individual masked patches of video frames, our model is designed to additionally predict the corresponding motion structure information ov…
WuHan University（武汉大学）；Zhejiang University（浙江大学）；The University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）；Qing Yuan Research Institute（清源研究院）；Shanghai Jiao Tong University（上海交通大学）
Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested on a different domain. Therefore, the self-supervised learning from multiple domains task is proposed to learn domain-invariant features that are not only suitable for evaluation on the same domain as the training set but also can be generalized to un…
Exploring Self-Supervised Learning with U-Net Masked Autoencoders and EfficientNet-B7 for Improved Gastrointestinal Abnormality Classification in Video Capsule Endoscopy
International Institute of Information Technology, Bangalore（国际信息技术学院，班加罗尔）；Indian Institute of Technology, Hyderabad（印度理工学院，海得拉巴）
Nanjing University（南京大学）；Tencent AI Lab（腾讯人工智能实验室）；Shanghai AI Lab（上海人工智能实验室）
Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners for self-supervised video pre-training (SSVP). We are inspired by the recent ImageMAE and propose customized video tube masking with an extremely high ratio. This simple design makes video reconstruction a more challenging self-supervision task, thus encouraging extracting more effective video representations during this pre-training process. We obtain three i…
University of Science and Technology of China（中国科学技术大学）；JD Explore Academy（京东探索研究院）；Aberystwyth University（阿伯里斯特威斯大学）
Recognizing human actions from point cloud videos has attracted tremendous attention from both academia and industry due to its wide applications like automatic driving, robotics, and so on. However, current methods for point cloud action recognition usually require a huge amount of data with manual annotations and a complex backbone network with high computation costs, which makes it impractical for real-world applications. Therefore, this paper considers the task of semi-supervised point cloud action recognition. We propose a Masked Pseudo-Labeling autoEncoder (\textbf{MAPLE}) framework to l…
The self-supervised Masked Image Modeling (MIM) schema, following "mask-and-reconstruct" pipeline of recovering contents from masked image, has recently captured the increasing interest in the multimedia community, owing to the excellent ability of learning visual representation from unlabeled data. Aiming at learning representations with high semantics abstracted, a group of works attempts to reconstruct non-semantic pixels with large-ratio masking strategy, which may suffer from "over-smoothing" problem, while others directly infuse semantics into targets in off-line way requiring extra data…
Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction (e.g., BERT) have become a de facto standard SSL practice in NLP. By contrast, early attempts at generative methods in vision have been buried by their discriminative counterparts (like contrastive learning); however, the success of mask image modeling has revived the masking autoencoder (often termed denoising autoencoder in the pa…
RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning
South China University of Technology（华南理工大学）；The University of Adelaide（阿德莱德大学）；The University of Western Australia（西澳大学）；The University of Sydney（悉尼大学）
Carnegie Mellon University（卡内基梅隆大学）；NVIDIA（英伟达）；UC Berkeley（加州大学伯克利分校）；UC San Diego（加州大学圣地亚哥分校）
A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in nearby video frames remains static. Given a sequence of video frames as input, the video autoencoder extracts a disentangled representation of the scene includ- ing: (i) a temporally-consistent deep voxel feature to represent the 3D structure and (ii) a 3D trajectory of camera pose for each frame. These two representations will then be re-entangled for render…
Recent works have shown how realistic talking face images can be obtained under the supervision of geometry guidance, e.g., facial landmark or boundary. To alleviate the demand for manual annotations, in this paper, we propose a novel self-supervised hybrid model (DAE-GAN) that learns how to reenact face naturally given large amounts of unlabeled videos. Our approach combines two deforming autoencoders with the latest advances in the conditional generation. On the one hand, we adopt the deforming autoencoder to disentangle identity and pose representations. A strong prior in talking face video…
SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder
Yau Mathematical Sciences Center, Tsinghua University（清华大学丘成桐数学科学中心）；Hisilicon（海思半导体）；Yanqi Lake Beijing Institute of Mathematical Sciences and Applications（雁栖湖北京数学科学与应用研究院）；State Key Laboratory of Membrane Biology, School of Life Sciences, Tsinghua University（清华大学生命科学学院膜生物学国家重点实验室）
The objective of Open set recognition (OSR) is to learn a classifier that can reject the unknown samples while classifying the known classes accurately. In this paper, we propose a self-supervision method, Detransformation Autoencoder (DTAE), for the OSR problem. This proposed method engages in learning representations that are invariant to the transformations of the input data. Experiments on several standard image datasets indicate that the pre-training process significantly improves the model performance in the OSR tasks. Meanwhile, our proposed self-supervision method achieves significant …
We present LBS-AE; a self-supervised autoencoding algorithm for fitting articulated mesh models to point clouds. As input, we take a sequence of point clouds to be registered as well as an artist-rigged mesh, i.e. a template mesh equipped with a linear-blend skinning (LBS) deformation space parameterized by a skeleton hierarchy. As output, we learn an LBS-based autoencoder that produces registered meshes from the input point clouds. To bridge the gap between the artist-defined geometry and the captured point clouds, our autoencoder models pose-dependent deviations from the template geometry. D…
Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt, have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE). However, we found that simply combining these two approaches leads to subpar performance. In this pa…
rPPG-MAE: Self-supervised Pre-training with Masked Autoencoders for Remote Physiological Measurement
Tianjin University（天津大学）；Lappeenranta-Lahti University of Technology LUT（拉彭兰塔-拉赫蒂工业大学（LUT大学））；Great Bay University（大湾区大学）；the Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
本文提出 rPPG-MAE 自监督预训练框架，通过线性重建任务和噪声不敏感策略挖掘生理信号的自相似先验，在多个 rPPG 数据集上超过现有自监督及 SOTA 监督方法。
Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning
Faculty of Automatic Control and Computer Science, Politehnica University of Bucharest（自动化控制与计算机科学系，布加勒斯特理工大学）；Institute of Mathematics of the Romanian Academy（罗马尼亚科学院数学研究所）
We present SeRP, a framework for Self-Supervised Learning of 3D point clouds. SeRP consists of encoder-decoder architecture that takes perturbed or corrupted point clouds as inputs and aims to reconstruct the original point cloud without corruption. The encoder learns the high-level latent representations of the points clouds in a low-dimensional subspace and recovers the original structure. In this work, we have used Transformers and PointNet-based Autoencoders. The proposed framework also addresses some of the limitations of Transformers-based Masked Autoencoders which are prone to leakage o…
Indraprastha Institute of Information Technology（因德拉普拉斯信息技术学院）
Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to variations commonly encountered in image datasets. Using the basic discriminating autoencoder as a unit, we build a stacked architecture aimed at extracting relevant representation from the training data. The efficiency of our feature extraction algorithm ensures a high classification accuracy with even simple classification schemes like KNN (K-nearest neighbor). W…
