In robotic applications, we often face the challenge of discovering new objects while having very little or no labelled training data. In this paper we explore the use of self-supervision provided by a robot traversing an environment to learn representations of encountered objects. Knowledge of ego-motion and depth perception enables the agent to effectively associate multiple object proposals, which serve as training data for learning object representations from unlabelled images. We demonstrate the utility of this representation in two ways. First, we can automatically discover objects by performing clustering in the learned embedding space. Each resulting cluster contains examples of one instance seen from various viewpoints and scales. Second, given a small number of labeled images, we can efficiently learn detectors for these labels. In the few-shot regime, these detectors have a substantially higher mAP of 0.22 compared to 0.12 of off-the-shelf standard detectors trained on this limited data. Thus, the proposed self-supervision results in effective environment specific object discovery and detection at no or very small human labeling cost.
Self-supervised monocular depth estimation has achieved impressive performance on outdoor datasets. Its performance however degrades notably in indoor environments because of the lack of textures. Without rich textures, the photometric consistency is too weak to train a good depth network. Inspired by the early works on indoor modeling, we leverage the structural regularities exhibited in indoor scenes, to train a better depth network. Specifically, we adopt two extra supervisory signals for self-supervised training: 1) the Manhattan normal constraint and 2) the co-planar constraint. The Manha…
Training effective embodied AI agents often involves manual reward engineering, expert imitation, specialized components such as maps, or leveraging additional sensors for depth and localization. Another approach is to use neural architectures alongside self-supervised objectives which encourage better representation learning. In practice, there are few guarantees that these self-supervised objectives encode task-relevant information. We propose the Scene Graph Contrastive (SGC) loss, which uses scene graphs as general-purpose, training-only, supervisory signals. The SGC loss does away with ex…
In this paper, we propose a self-supervised learning procedure for training a robust multi-object tracking (MOT) model given only unlabeled video. While several self-supervisory learning signals have been proposed in prior work on single-object tracking, such as color propagation and cycle-consistency, these signals cannot be directly applied for training RNN models, which are needed to achieve accurate MOT: they yield degenerate models that, for instance, always match new detections to tracks with the closest initial detections. We propose a novel self-supervisory signal that we call cross-in…
Inria（法国国家信息与自动化研究所）；École Normale Supérieure（巴黎高等师范学院）；PSL Research University（巴黎文理研究大学）
This paper addresses the problem of automatically localizing dominant objects as spatio-temporal tubes in a noisy collection of videos with minimal or even no supervision. We formulate the problem as a combination of two complementary processes: discovery and tracking. The first one establishes correspondences between prominent regions across videos, and the second one associates successive similar object regions within the same video. Interestingly, our algorithm also discovers the implicit topology of frames associated with instances of the same object class across different videos, a role n…
Unsupervised depth learning takes the appearance difference between a target view and a view synthesized from its adjacent frame as supervisory signal. Since the supervisory signal only comes from images themselves, the resolution of training data significantly impacts the performance. High-resolution images contain more fine-grained details and provide more accurate supervisory signal. However, due to the limitation of memory and computation power, the original images are typically down-sampled during training, which suffers heavy loss of details and disparity accuracy. In order to fully expl…
We address the task of active learning in the context of semantic segmentation and show that self-consistency can be a powerful source of self-supervision to greatly improve the performance of a data-driven model with access to only a small amount of labeled data. Self-consistency uses the simple observation that the results of semantic segmentation for a specific image should not change under transformations like horizontal flipping (i.e., the results should only be flipped). In other words, the output of a model should be consistent under equivariant transformations. The self-supervisory sig…
Creating high-quality articulated 3D models of animals is challenging either via manual creation or using 3D scanning tools. Therefore, techniques to reconstruct articulated 3D objects from 2D images are crucial and highly useful. In this work, we propose a practical problem setting to estimate 3D pose and shape of animals given only a few (10-30) in-the-wild images of a particular animal species (say, horse). Contrary to existing works that rely on pre-defined template shapes, we do not assume any form of 2D or 3D ground-truth annotations, nor do we leverage any multi-view or temporal informa…
NEC Labs America（NEC美国实验室）；Rutgers University（罗格斯大学）
We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e.g., videos and audios) under self-supervision. Specifically, we exploit the benefits of some readily accessible supervisory signals from input data itself or some off-the-shelf functional models and accordingly design auxiliary tasks for our model to utilize these signals. With the supervision of the signals, our model can easily disentangle the representation of an input sequence into static factors and dynamic factors (i.e., time-invariant and time-varying parts). Comprehensive experim…
We introduce Correlational Image Modeling (CIM), a novel and surprisingly effective approach to self-supervised visual pre-training. Our CIM performs a simple pretext task: we randomly crop image regions (exemplars) from an input image (context) and predict correlation maps between the exemplars and the context. Three key designs enable correlational image modeling as a nontrivial and meaningful self-supervisory task. First, to generate useful exemplar-context pairs, we consider cropping image regions with various scales, shapes, rotations, and transformations. Second, we employ a bootstrap le…
University of Amsterdam（阿姆斯特丹大学）；Bosch Center for AI（博世人工智能中心）
The standard approach to contrastive learning is to maximize the agreement between different views of the data. The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative, corresponding to views of different objects. The supervisory signal comes from maximizing the total similarity over positive pairs, while the negative pairs are needed to avoid collapse. In this work, we note that the approach of considering individual pairs cannot account for both intra-set and inter-set similarities when the sets are formed from the views of…
Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging problem due to the lack of sufficient amounts of manipulated training data. In this paper, we propose a learning algorithm for detecting visual image manipulations that is trained only using a large dataset of real photographs. The algorithm uses the automatically recorded photo EXIF metadata as supervisory signal for training a model to determine whether an image is self-consistent -- that is, whether its content could…
Autonomous driving can benefit from motion behavior comprehension when interacting with diverse traffic participants in highly dynamic environments. Recently, there has been a growing interest in estimating class-agnostic motion directly from point clouds. Current motion estimation methods usually require vast amount of annotated training data from self-driving scenes. However, manually labeling point clouds is notoriously difficult, error-prone and time-consuming. In this paper, we seek to answer the research question of whether the abundant unlabeled data collections can be utilized for accu…
Despite the success of deep learning in disparity estimation, the domain generalization gap remains an issue. We propose a semi-supervised pipeline that successfully adapts DispNet to a real-world domain by joint supervised training on labeled synthetic data and self-supervised training on unlabeled real data. Furthermore, accounting for the limitations of the widely-used photometric loss, we analyze the impact of deep feature reconstruction as a promising supervisory signal for disparity estimation.
The Robotics Institute（机器人研究所）；Carnegie Mellon University（卡内基梅隆大学）；Kohli Center of Intelligent Systems (KCIS)（科利智能系统中心（KCIS））；IIIT-Hyderabad（海得拉巴国际信息技术学院）
Localizing natural language phrases in images is a challenging problem that requires joint understanding of both the textual and visual modalities. In the unsupervised setting, lack of supervisory signals exacerbate this difficulty. In this paper, we propose a novel framework for unsupervised visual grounding which uses concept learning as a proxy task to obtain self-supervision. The simple intuition behind this idea is to encourage the model to localize to regions which can explain some semantic property in the data, in our case, the property being the presence of a concept in a set of images…
The ability to both recognize and discover terrain characteristics is an important function required for many autonomous ground robots such as social robots, assistive robots, autonomous vehicles, and ground exploration robots. Recognizing and discovering terrain characteristics is challenging because similar terrains may have very different appearances (e.g., carpet comes in many colors), while terrains with very similar appearance may have very different physical properties (e.g. mulch versus dirt). In order to address the inherent ambiguity in vision-based terrain recognition and discovery,…
University of Chicago（芝加哥大学）；TTI Chicago（芝加哥丰田技术研究所）
We investigate and improve self-supervision as a drop-in replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has been shown to be more promising for utilizing unlabeled data than other, traditional unsupervised learning methods. We build on this success and evaluate the ability of our self-supervised network in several contexts. On VOC segmentation and classification tasks, we present results that are state-of-the-art among methods not using ImageNet labels for pretraining representations. Moreover, we present the first in-depth …
Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks. Obtaining such a dataset for any new domain can be very expensive and time-consuming. In addition, models trained on certain annotated categories do not generalize well to unseen objects. The goal of this paper is to propose a method that can perform unsupervised discovery of long-tail categories in instance segmentation, through learning instance embeddings of masked regions. Leveraging rich relationship and hierarc…
Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS)（中国科学院智能信息处理重点实验室）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学学院）
Multimedia event detection has been receiving increasing attention in recent years. Besides recognizing an event, the discovery of evidences (which is refered to as "recounting") is also crucial for user to better understand the searching result. Due to the difficulty of evidence annotation, only limited supervision of event labels are available for training a recounting model. To deal with the problem, we propose a weakly supervised evidence discovery method based on self-paced learning framework, which follows a learning process from easy "evidences" to gradually more complex ones, and simul…
Politecnico di Torino（都灵理工大学）；Istituto Italiano di Tecnologia（意大利理工学院）；Sapienza Università di Roma（罗马第一大学）
Domain adaptation approaches have shown promising results in reducing the marginal distribution difference among visual domains. They allow to train reliable models that work over datasets of different nature (photos, paintings etc), but they still struggle when the domains do not share an identical label space. In the partial domain adaptation setting, where the target covers only a subset of the source classes, it is challenging to reduce the domain gap without incurring in negative transfer. Many solutions just keep the standard domain adaptation techniques by adding heuristic sample weight…
University of Oxford（牛津大学）；University of Amsterdam（阿姆斯特丹大学）；Meta AI
We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-visual data, using the audio component to "teach" the object detector. While this problem is related to sound source localisation, it is considerably harder because the detector must classify the objects by type, enumerate each instance of the object, and do so even when the object is silent. We tackle this problem by first designing a self-supervised framework with a contrasti…
Nanyang Technological University（南洋理工大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Surrey（萨里大学）
In this paper, we tackle for the first time, the problem of self-supervised representation learning for free-hand sketches. This importantly addresses a common problem faced by the sketch community -- that annotated supervisory data are difficult to obtain. This problem is very challenging in that sketches are highly abstract and subject to different drawing styles, making existing solutions tailored for photos unsuitable. Key for the success of our self-supervised learning paradigm lies with our sketch-specific designs: (i) we propose a set of pretext tasks specifically designed for sketches …
Training deep neural networks to estimate the viewpoint of objects requires large labeled training datasets. However, manually labeling viewpoints is notoriously hard, error-prone, and time-consuming. On the other hand, it is relatively easy to mine many unlabelled images of an object category from the internet, e.g., of cars or faces. We seek to answer the research question of whether such unlabeled collections of in-the-wild images can be successfully utilized to train viewpoint estimation networks for general object categories purely via self-supervision. Self-supervision here refers to the…
Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）；Zhejiang University（浙江大学）
While few-shot learning (FSL) aims for rapid generalization to new concepts with little supervision, self-supervised learning (SSL) constructs supervisory signals directly computed from unlabeled data. Exploiting the complementarity of these two manners, few-shot auxiliary learning has recently drawn much attention to deal with few labeled data. Previous works benefit from sharing inductive bias between the main task (FSL) and auxiliary tasks (SSL), where the shared parameters of tasks are optimized by minimizing a linear combination of task losses. However, it is challenging to select a prope…
Caltech（加州理工学院）；Samsung Advanced Institute of Technology（三星先进技术研究院）；Northwestern University（西北大学）；Argo AI
We propose a method for learning the posture and structure of agents from unlabelled behavioral videos. Starting from the observation that behaving agents are generally the main sources of movement in behavioral videos, our method, Behavioral Keypoint Discovery (B-KinD), uses an encoder-decoder architecture with a geometric bottleneck to reconstruct the spatiotemporal difference between video frames. By focusing only on regions of movement, our approach works directly on input videos without requiring manual annotations. Experiments on a variety of agent types (mouse, fly, human, jellyfish, an…
Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns in the low data regime. Self-supervised learning focuses instead on unlabeled data and looks into it for the supervisory signal to feed high capacity deep neural networks. In this work we exploit the complementarity of these two domains and propose an approach for improving few-shot learning through self-supervision. We use self-supervision as …
To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors. In this paper, we seek to achieve the similar goal but do not involve more human efforts. To this end, we introduce a novel framework, which successfully encodes both geometric local features and global representations to distinguish vehicle instances, optimized only by the supervision from official ID labels. Specifically, given our insight that objects in ReID share similar geometric ch…
To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors. In this paper, we seek to achieve the similar goal but do not involve more human efforts. To this end, we introduce a novel framework, which successfully encodes both geometric local features and global representations to distinguish vehicle instances, optimized only by the supervision from official ID labels. Specifically, given our insight that objects in ReID share similar geometric ch…
AVS-Net: Audio-Visual Scale Net for Self-supervised Monocular Metric Depth Estimation
SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University（上海交通大学巴黎卓越工程师学院）；Center for Robotics, MINES Paris, PSL University（巴黎矿业学院机器人中心（巴黎文理研究大学））
University of Nottingham（诺丁汉大学）；Samsung AI Center Cambridge（三星剑桥人工智能中心）；Hartpury University（哈特伯瑞大学）；Queen Mary University of London（伦敦玛丽女王大学）
This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. Contrary to existing methods that build on auxiliary tasks such as image generation or equivariance, we propose a self-training approach where, departing from generic keypoints, a landmark detector and descriptor is trained to improve itself, tuning the keypoints into distinctive landmarks. To this end, we propose an iterative algorithm that alternates between producing new pseudo-labels through feature clustering and learning distinctive features for each pseudo-class through contrastive learning.…
Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Heidelberg（海德堡大学）；Information Technology University of Punjab（旁遮普信息技术大学）
This paper introduces the task of visual named entity discovery in videos without the need for task-specific supervision or task-specific external knowledge sources. Assigning specific names to entities (e.g. faces, scenes, or objects) in video frames is a long-standing challenge. Commonly, this problem is addressed as a supervised learning objective by manually annotating faces with entity labels. To bypass the annotation burden of this setup, several works have investigated the problem by utilizing external knowledge sources such as movie databases. While effective, such approaches do not wo…
The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to train the model. This is associated with a costly human annotation effort. To address this concern, with the long-term goal of leveraging the abundance of cheap unlabeled data, we explore methods of unsupervised "pre-training." In particular, we propose to use self-supervised automatic image colorization. We show that traditional methods for unsupervised lea…
University of Science and Technology Beijing（北京科技大学）
This paper develops a novel self-training U-net (STU-net) based method for the automated WPC model generation without requiring data pre-processing. The self-training (ST) process of STU-net has two steps. First, different from traditional studies regarding the WPC modeling as a curve fitting problem, in this paper, we renovate the WPC modeling formulation from a machine vision aspect. To develop sufficiently diversified training samples, we synthesize supervisory control and data acquisition (SCADA) data based on a set of S-shape functions depicting WPCs. These synthesized SCADA data and WPC …
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）
Video representation learning is a vital problem for classification task. Recently, a promising unsupervised paradigm termed self-supervised learning has emerged, which explores inherent supervisory signals implied in massive data for feature learning via solving auxiliary tasks. However, existing methods in this regard suffer from two limitations when extended to video classification. First, they focus only on a single task, whereas ignoring complementarity among different task-specific features and thus resulting in suboptimal video representation. Second, high computational and memory cost …
Shanghai Jiao Tong University（上海交通大学）；The Chinese University of Hong Kong（香港中文大学）；Huawei Inc.（华为技术有限公司）
In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However, taking flow as input brings about two drawbacks. First, flow cannot capture sufficient cues when objects remain static or partially occluded. Second, it is challenging to establish temporal coherency from flow-only input, due to the missing texture information. To tackle these limitations, we propose a model for directly processing consecutive RGB frames, and infer the optical flow between any pair of frames using …
Carnegie Mellon University（卡内基梅隆大学）；University of California, Berkeley（加州大学伯克利分校）
This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image and train a convolutional neural net to predict the position of the second patch relative to the first. We argue that doing well on this task requires the model to learn to recognize objects and their parts. We demonstrate that the feature representation learned using this within-image context indeed captures visual similarity across images. For example, th…
Multimedia Laboratory（多媒体实验室）；The Chinese University of Hong Kong（香港中文大学）
Domain adaptive object re-ID aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain to tackle the open-class re-identification problems. Although state-of-the-art pseudo-label-based methods have achieved great success, they did not make full use of all valuable information because of the domain gap and unsatisfying clustering performance. To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory. The hybrid memory dynamically generates source-domain class-level, target-domain cluster-level and un-clust…
Imperial College London（伦敦帝国理工学院）；Queen Mary University of London（伦敦玛丽女王大学）
In the recent years, convolutional neural networks have transformed the field of medical image analysis due to their capacity to learn discriminative image features for a variety of classification and regression tasks. However, successfully learning these features requires a large amount of manually annotated data, which is expensive to acquire and limited by the available resources of expert image analysts. Therefore, unsupervised, weakly-supervised and self-supervised feature learning techniques receive a lot of attention, which aim to utilise the vast amount of available data, while at the …
Self-supervised Multi-view Clustering in Computer Vision: A Survey
Inner Mongolia University of Technology（内蒙古工业大学）；OPPO Research Institute（OPPO研究院）；Haihe Laboratory of Information Technology Application Innovation（海河信息技术应用创新实验室）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；InnoPeak Technology, Inc（InnoPeak科技公司）
Surface-volume self-supervised representation learning of brain MRI for genetic discovery
The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）；Yale School of Medicine（耶鲁大学医学院）；Texas A&M University（德克萨斯A&M大学）；Stanford University School of Medicine（斯坦福大学医学院）
SelfAI: A self-directed framework for long-horizon scientific discovery
University of Electronic Science and Technology of China（电子科技大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Xian Jiaotong University（西安交通大学）；Yale University（耶鲁大学）；Washington University in St. Louis（圣路易斯华盛顿大学）；Monash University（莫纳什大学）
Arizona State University（亚利桑那州立大学）；Mayo Clinic（梅奥诊所）
Medical images are naturally associated with rich semantics about the human anatomy, reflected in an abundance of recurring anatomical patterns, offering unique potential to foster deep semantic representation learning and yield semantically more powerful models for different medical applications. But how exactly such strong yet free semantics embedded in medical images can be harnessed for self-supervised learning remains largely unexplored. To this end, we train deep models to learn semantically enriched visual representation by self-discovery, self-classification, and self-restoration of th…
Salesforce Research（赛富时研究院）；University of Michigan（密歇根大学）
Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when trained on larger sets of uncurated images. We hypothesize that current SSL methods perform best on iconic images, and struggle on complex scene images with many objects. Analyzing contrastive SSL methods shows that they have poor visual grounding and receive poor supervisory signal when trained on scene images. We propose Contrastive Attention-Supervised Tun…
We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted relations as pseudo labels. At the heart of our framework lies an algorithm that investigates contexts of data on the embedding space to predict their class-equivalence relations as pseudo labels. The algorithm enables efficient end-to-end training since it demands no off-the-shelf module for pseudo labeling. Also, the class-equivalence relations provide ri…
Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios. One scalable solution is to make the model generate the supervision for itself by leveraging some part of the input data, which is known as self-supervised learning. In this paper, we use the prediction task as self-supervision and build a novel object-centric model for image sequence representation. In addition to disentangling the notion of objects and the m…
We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free supervisory signal for learning visual representations from scratch. At training time, our model learns a feature map representation to be useful for performing cycle-consistent tracking. At test time, we use the acquired representation to find nearest neighbors across space and time. We demonstrate the generalizability of the representation -- without finetuning -- across a range of visual correspondence tasks, including video object segmenta…
TCS Research（塔塔咨询服务研究部）；Flytxt Mobile Solutions（Flytxt 移动解决方案公司）；Indian Institute of Space Science and Technology（印度空间科学技术研究所）
Several methods for discovering interpretable directions in the latent space of pre-trained GANs have been proposed. Latent semantics discovered by unsupervised methods are relatively less disentangled than supervised methods since they do not use pre-trained attribute classifiers. We propose Scale Ranking Estimator (SRE), which is trained using self-supervision. SRE enhances the disentanglement in directions obtained by existing unsupervised disentanglement techniques. These directions are updated to preserve the ordering of variation within each direction in latent space. Qualitative and qua…
