We introduce a novel principle for self-supervised feature learning based on the discrimination of specific transformations of an image. We argue that the generalization capability of learned features depends on what image neighborhood size is sufficient to discriminate different image transformations: The larger the required neighborhood size and the more global the image statistics that the feature can describe. An accurate description of global image statistics allows to better represent the shape and configuration of objects and their context, which ultimately generalizes better to new tasks such as object classification and detection. This suggests a criterion to choose and design image transformations. Based on this criterion, we introduce a novel image transformation that we call limited context inpainting (LCI). This transformation inpaints an image patch conditioned only on a small rectangular pixel boundary (the limited context). Because of the limited boundary information, the inpainter can learn to match local pixel statistics, but is unlikely to match the global statistics of the image. We claim that the same principle can be used to justify the performance of transformations such as image rotations and warping. Indeed, we demonstrate experimentally that learning to discriminate transformations such as LCI, image warping and rotations, yields features with state of the art generalization capabilities on several datasets such as Pascal VOC, STL-10, CelebA, and ImageNet. Remarkably, our trained features achieve a performance on Places on par with features trained through supervised learning with ImageNet labels.
Technical University of Munich（慕尼黑工业大学）；Artisense（阿蒂森斯公司）
Vision-based learning methods for self-driving cars have primarily used supervised approaches that require a large number of labels for training. However, those labels are usually difficult and expensive to obtain. In this paper, we demonstrate how a model can be trained to control a vehicle's trajectory using camera poses estimated through visual odometry methods in an entirely self-supervised fashion. We propose a scalable framework that leverages trajectory information from several different runs using a camera setup placed at the front of a car. Experimental results on the CARLA simulator …
PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth
The Hong Kong University of Science and Technology（香港科技大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；Li Auto；BAAI（北京人工智能研究院）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；X The Moonshot Factory（X 登月工厂）
We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrat…
University of Tübingen（图宾根大学）；Amazon（亚马逊）；University of Freiburg（弗莱堡大学）
While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision. To address this, we propose Pixel-level Correspondence (PiCo), a method for dense contrastive learning from video. By tracking points with optical flow, we obtain a correspondence map which can be used to match local features at different points in time. We validate PiCo on standard benchmarks, outperforming self-supervised baselines on multiple dense prediction tasks, without compromising performance on image classificati…
Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles. This task is challenging, as coarse annotations (tags, boxes) lack precise pixel localization whereas sparse annotations (points, scribbles) lack broad region coverage. Existing methods tackle these two types of weak supervision differently: Class activation maps are used to localize coarse labels and iteratively refine the segmentation model, whereas conditional random fields are used to pro…
In this paper, we introduce a self-supervised approach for video object segmentation without human labeled data.Specifically, we present Robust Pixel-level Matching Net-works (RPM-Net), a novel deep architecture that matches pixels between adjacent frames, using only color information from unlabeled videos for training. Technically, RPM-Net can be separated in two main modules. The embed-ding module first projects input images into high dimensional embedding space. Then the matching module with deformable convolution layers matches pixels between reference and target frames based on the embedd…
National Taiwan University（台湾大学）；ASUS Intelligent Cloud Services（华硕智能云服务）
Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest. One is typically required to collect a large mount of data (i.e., base classes) with such ground truth information, followed by meta-learning strategies to address the above learning task. When only image-level semantic labels can be observed during both training and testing, it is considered as an even more challenging task of weakly supervised few-shot semantic segmentation. To address this problem, we propose a novel meta-l…
Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University（北京交通大学交通数据分析与挖掘北京市重点实验室）
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing approaches aim to generate accurate pixel-level labels from weak supervisions. However, we observe that those generated labels still inevitably contain noisy labels. Motivated by this observation, we present a novel perspective and formulate this task as a problem of learning with pixel-level label noise. Existing noisy label methods, nevertheless, mainly a…
Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects. To overcome these challenges, we propose a novel framework, namely Explicit Pseudo-pixel Supervision (EPS), which learns from pixel-level feedback by combining two weak supervisions; the image-level label provides the object identity via the localization map and the saliency map from the off-the-shelf saliency detection model offers rich boundaries. We devise a joint…
Universidad de Zaragoza（萨拉戈萨大学）；Magic Leap（Magic Leap公司）；Bitbrain（Bitbrain公司）
This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach outperforms the curr…
Semi-supervised semantic segmentation needs rich and robust supervision on unlabeled data. Consistency learning enforces the same pixel to have similar features in different augmented views, which is a robust signal but neglects relationships with other pixels. In comparison, contrastive learning considers rich pairwise relationships, but it can be a conundrum to assign binary positive-negative supervision signals for pixel pairs. In this paper, we take the best of both worlds and propose multi-view correlation consistency (MVCC) learning: it considers rich pairwise relationships in self-corre…
We propose an approach to discover class-specific pixels for the weakly-supervised semantic segmentation task. We show that properly combining saliency and attention maps allows us to obtain reliable cues capable of significantly boosting the performance. First, we propose a simple yet powerful hierarchical approach to discover the class-agnostic salient regions, obtained using a salient object detector, which otherwise would be ignored. Second, we use fully convolutional attention maps to reliably localize the class-specific regions in a given image. We combine these two cues to discover clas…
Jilin University（吉林大学）；Baidu Research（百度研究院）；National Engineering Laboratory for Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）
Current semi-supervised semantic segmentation methods mainly focus on designing pixel-level consistency and contrastive regularization. However, pixel-level regularization is sensitive to noise from pixels with incorrect predictions, and pixel-level contrastive regularization has memory and computational cost with O(pixel_num^2). To address the issues, we propose a novel region-level contrastive and consistency learning framework (RC^2L) for semi-supervised semantic segmentation. Specifically, we first propose a Region Mask Contrastive (RMC) loss and a Region Feature Contrastive (RFC) loss to …
Pyramid Pixel Context Adaption Network for Medical Image Classification with Supervised Contrastive Learning
Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology（南方科技大学可信自主系统研究院）；Southern University of Science and Technology（南方科技大学）；Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology（南方科技大学广东省类脑智能计算重点实验室）；Singapore Eye Research Institute（新加坡眼科研究所）
Beihang University（北京航空航天大学）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to generate more complete and precise pseudo masks for segmentation. In this study, we propose weakly-supervised pixel-to-prototype contrast that can provide pixel-level supervisory signals to narrow the gap. Guided by two intuitive priors, our method is executed across different views and within per single view of an image, aiming to impose cross-view feature…
We propose a new self-supervised approach to image feature learning from motion cue. This new approach leverages recent advances in deep learning in two directions: 1) the success of training deep neural network in estimating optical flow in real data using synthetic flow data; and 2) emerging work in learning image features from motion cues, such as optical flow. Building on these, we demonstrate that image features can be learned in self-supervision by first training an optical flow estimator with synthetic flow data, and then learning image features from the estimated flows in real motion d…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
In this paper, we propose a self-supervised single-view pixel-level accurate depth estimation network, called PLADE-Net. The PLADE-Net is the first work that shows unprecedented accuracy levels, exceeding 95\% in terms of the $δ^1$ metric on the challenging KITTI dataset. Our PLADE-Net is based on a new network architecture with neural positional encoding and a novel loss function that borrows from the closed-form solution of the matting Laplacian to learn pixel-level accurate depth estimation from stereo images. Neural positional encoding allows our PLADE-Net to obtain more consistent depth e…
Throughout the world, breast cancer is one of the leading causes of female death. Recently, deep learning methods are developed to automatically grade breast cancer of histological slides. However, the performance of existing deep learning models is limited due to the lack of large annotated biomedical datasets. One promising way to relieve the annotating burden is to leverage the unannotated datasets to enhance the trained model. In this paper, we first apply active learning method in breast cancer grading, and propose a semi-supervised framework based on expectation maximization (EM) model. …
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）
The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images. A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability. We argue that every pixel matters to the model training, even its prediction is ambiguous. Intuitively, an unreliable prediction may get confused among the top classes (i.e., those with the highest probabilities), however, it should be confident about the pixel not belonging to the remaining clas…
University of Technology Sydney（悉尼科技大学）；National University of Singapore（新加坡国立大学）；Zhejiang University（浙江大学）
Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., video game, to unlabeled target domains, e.g., real-world scenarios, saving annotation expenses. Existing UDA methods for semantic segmentation usually focus on minimizing the inter-domain discrepancy of various levels, e.g., pixels, features, and predictions, for extracting domain-invariant knowledge. However, the primary intra-domain knowledge, such as context correlation inside an i…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Detecting curved text in the wild is very challenging. Recently, most state-of-the-art methods are segmentation based and require pixel-level annotations. We propose a novel scheme to train an accurate text detector using only a small amount of pixel-level annotated data and a large amount of data annotated with rectangles or even unlabeled data. A baseline model is first obtained by training with the pixel-level annotated data and then used to annotate unlabeled or weakly labeled data. A novel strategy which utilizes ground-truth bounding boxes to generate pseudo mask annotations is proposed …
Hyperspectral target detection is a pixel-level recognition problem. Given a few target samples, it aims to identify the specific target pixels such as airplane, vehicle, ship, from the entire hyperspectral image. In general, the background pixels take the majority of the image and complexly distributed. As a result, the datasets are weak annotated and extremely imbalanced. To address these problems, a spectral mixing based self-supervised paradigm is designed for hyperspectral data to obtain an effective feature representation. The model adopts a spectral similarity based matching network fra…
In this paper, we present a novel end-to-end deep neural network model for autonomous driving that takes monocular image sequence as input, and directly generates the steering control angle. Firstly, we model the end-to-end driving problem as a local path planning process. Inspired by the environmental representation in the classical planning algorithms(i.e. the beam curvature method), pixel-wise orientations are fed into the network to learn direction-aware features. Next, to handle the imbalanced distribution of steering values in training datasets, we propose an improvement on a cost-sensit…
Fully convolutional networks (FCN) have achieved great success in human parsing in recent years. In conventional human parsing tasks, pixel-level labeling is required for guiding the training, which usually involves enormous human labeling efforts. To ease the labeling efforts, we propose a novel weakly supervised human parsing method which only requires simple object keypoint annotations for learning. We develop an iterative learning method to generate pseudo part segmentation masks from keypoint labels. With these pseudo masks, we train an FCN network to output pixel-level human parsing pred…
Cardiac segmentation is an essential step for the diagnosis of cardiovascular diseases. However, pixel-wise dense labeling is both costly and time-consuming. Scribble, as a form of sparse annotation, is more accessible than full annotations. However, it's particularly challenging to train a segmentation network with weak supervision from scribbles. To tackle this problem, we propose a new scribble-guided method for cardiac segmentation, based on the Positive-Unlabeled (PU) learning framework and global consistency regularization, and termed as ShapePU. To leverage unlabeled pixels via PU learn…
Disney Research（迪士尼研究院）；University of Waterloo（滑铁卢大学）
Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supervised approaches generate full masks from partial input (e.g. scribbles or seeds) using standard interactive segmentation methods as preprocessing. But, errors in such masks result in poorer training since standard loss functions (e.g. cross-entropy) do not distinguish seeds from potentially mislabeled other pixels. Inspired by the general ideas in semi-supervised learning, we address these problems via a new princi…
Existing studies in weakly supervised semantic segmentation (WSSS) have utilized class activation maps (CAMs) to localize the class objects. However, since a classification loss is insufficient for providing precise object regions, CAMs tend to be biased towards discriminative patterns (i.e., sparseness) and do not provide precise object boundary information (i.e., impreciseness). To resolve these limitations, we propose a novel framework (composed of MainNet and SupportNet.) that derives pixel-level self-supervision from given image-level supervision. In our framework, with the help of the pr…
We introduce Ignition: an end-to-end neural network architecture for training unconstrained self-driving vehicles in simulated environments. The model is a ResNet-18 variant, which is fed in images from the front of a simulated F1 car, and outputs optimal labels for steering, throttle, braking. Importantly, we never explicitly train the model to detect road features like the outline of a track or distance to other cars; instead, we illustrate that these latent features can be automatically encapsulated by the network.
Robert Bosch Research and Technology Center North America（北美罗伯特·博世研究与技术中心）；Robert Bosch GmbH（罗伯特·博世有限公司）
Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for individual images, unsupervised semantic segmentation with pixel-level representations is still a challenging task and remains underexplored. In this work, we propose a self-supervised pixel representation learning method for semantic segmentation by using visual concepts (i.e., groups of pixels with semantic meanings, such as parts, objects, and scenes) extracted from images. To guide self-supervised learning, we lev…
The fast development of self-supervised learning lowers the bar learning feature representation from massive unlabeled data and has triggered a series of research on change detection of remote sensing images. Challenges in adapting self-supervised learning from natural images classification to remote sensing images change detection arise from difference between the two tasks. The learned patch-level feature representations are not satisfying for the pixel-level precise change detection. In this paper, we proposed a novel pixel-level self-supervised hyperspectral spatial-spectral understanding …
Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly supervised settings, e.g. where a fraction of pixels is labeled or when only image-level tags are available. It has been shown that regularized losses - originally developed for unsupervised low-level segmentation and representing geometric priors on pixel labels - can considerably improve the quality of weakly supervised training. However, many common priors require optimization stronger than gradient descent. Thus, …
Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation
Beihang University（北京航空航天大学）；State Key Laboratory of Virtual Reality Technology and Systems（虚拟现实技术与系统国家重点实验室）；School of Computer Science and Engineering（计算机科学与工程学院）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due to the gap between full and weak supervisions. In this paper, we propose a self-supervised equivariant attention mechanism (SEAM) to discover additional supervision and narrow the gap. Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation, whose pixel-level labels take the same spatial tr…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Centre for Artificial Intelligence and Robotics, HKISI_CAS（中国科学院香港创新研究院人工智能与机器人创新中心）
In this paper, we propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation. Instead of the dense pixel-level labels used by fully supervised methods, point-level labels only provide a single point for each target as supervision, significantly reducing the annotation burden. We formulate the problem in an end-to-end framework by simultaneously generating panoptic pseudo-masks from point-level labels and learning from them. To tackle the core challenge, i.e., panoptic pseudo-mask generation, we propose a principled approach to parsing pixels by minim…
Pixel-level crack segmentation is widely studied due to its high impact on building and road inspections. While recent studies have made significant improvements in accuracy, they typically heavily depend on pixel-level crack annotations, which are time-consuming to obtain. In earlier work, we proposed to reduce the annotation cost bottleneck by reformulating the crack segmentation problem as a weakly-supervised problem -- i.e. the annotation process is expedited by sacrificing the annotation quality. The loss in annotation quality was remedied by refining the inference with per-pixel brightne…
We developed a novel SSL approach to capture global consistency and pixel-level local consistencies between differently augmented views of the same images to accommodate downstream discriminative and dense predictive tasks. We adopted the teacher-student architecture used in previous contrastive SSL methods. In our method, the global consistency is enforced by aggregating the compressed representations of augmented views of the same image. The pixel-level consistency is enforced by pursuing similar representations for the same pixel in differently augmented views. Importantly, we introduced an…
Plug-and-Play DISep: Separating Dense Instances for Scene-to-Pixel Weakly-Supervised Change Detection in High-Resolution Remote Sensing Images
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）；Institute of Artificial Intelligence, Wuhan University（武汉大学人工智能研究院）；School of Computer Science, Wuhan University（武汉大学计算机学院）；Graduate School of Frontier Sciences, University of Tokyo（东京大学前沿科学研究生院）；Institute of Geodesy and Photogrammetry, ETH Zürich（苏黎世联邦理工学院大地测量与摄影测量研究所）
Toulouse Hyperspectral Data Set: a benchmark data set to assess semi-supervised spectral representation learning and pixel-wise classification techniques
CNES（法国国家空间研究中心）；Toulouse Mathematics Institute（图卢兹数学研究所）；CNRS（法国国家科学研究中心）；University of Toulouse（图卢兹大学）；ONERA-DOTA（法国航空航天研究院DOTA部门）；Magellium（马哲利姆公司）
针对现有高光谱数据集不适合评估泛化性能的问题，发布大规模Toulouse Hyperspectral Data Set基准，并基于Masked Autoencoder等自监督技术建立像素级分类基线，实现85%准确率。
Northeastern University（东北大学）；The University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）
Recent breakthroughs in semi-supervised semantic segmentation have been developed through contrastive learning. In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the latent space. However, there exist inaccurate pseudo-labels which map the ambiguous representations of pixels to the wrong classes due to the limited cognitive ability of the model. In this paper, we define pixel-wise representations from a new perspective of probability theory and propose a Probabilistic Representation Contrastive Learning (PRCL)…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Mashang Consumer Finance Co., Ltd.（马上消费金融股份有限公司）
Self-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance, whereas there still exists a non-negligible gap between pre-trained model and downstream dense prediction tasks. Concretely, these downstream tasks require more accurate representation, in other words, the pixels from the same object must belong to a shared semantic category, which is lacking in the previous methods. In this work, we present Dense Semantic Contrast (DSC) for modeling semantic category decision bounda…
KTH Royal Institute of Technology（瑞典皇家理工学院）；Univrses AB（Univrses公司）
We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the application of FixMatch in semi-supervised learning problems beyond image classification by adding a matching operation on the pseudo-labels. This allows us to still use the full strength of data augmentation pipelines, including geometric transformations. We evaluate it on semi-supervised semantic segmentation on Cityscapes and Pascal VOC with different percentages of labeled…
Towards Pixel-Wise Anomaly Location for High-Resolution PCBA via Self-Supervised Image Reconstruction
Huazhong University of Science and Technology（华中科技大学）；Siemens AG（西门子股份公司）；University of Electronic Science and Technology of China（电子科技大学）；Peking University（北京大学）
University of Zagreb, Faculty of Electrical Engineering and Computing（萨格勒布大学电气工程与计算学院）；Yamagata University, Faculty of Science（山形大学理学部）
This paper proposes to use keypoints as a self-supervision clue for learning depth map estimation from a collection of input images. As ground truth depth from real images is difficult to obtain, there are many unsupervised and self-supervised approaches to depth estimation that have been proposed. Most of these unsupervised approaches use depth map and ego-motion estimations to reproject the pixels from the current image into the adjacent image from the image collection. Depth and ego-motion estimations are evaluated based on pixel intensity differences between the correspondent original and …
University of Science and Technology of China（中国科学技术大学）
Contrastive learning (CL) is a form of self-supervised learning and has been widely used for various tasks. Different from widely studied instance-level contrastive learning, pixel-wise contrastive learning mainly helps with pixel-wise tasks such as medical landmark detection. The counterpart to an instance in instance-level CL is a pixel, along with its neighboring context, in pixel-wise CL. Aiming to build better feature representation, there is a vast literature about designing instance augmentation strategies for instance-level CL; but there is little similar work on pixel augmentation for…
Idiap Research Institute（Idiap研究所）；Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Facebook AI Research（Facebook人工智能研究院）
We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as a kind of weakly supervised segmentation task, and naturally fits the Multiple Instance Learning (MIL) framework: every training image is known to have (or not) at least one pixel corresponding to the image class label, and the segmentation task can be rewritten as inferring the pixels belonging to the class of the object (given one image, and its object class). We propose a Convolutional Neural N…
