In this paper, we address the problem of detecting unseen objects from RGB images and estimating their poses in 3D. We propose two mobile friendly networks: MobilePose-Base and MobilePose-Shape. The former is used when there is only pose supervision, and the latter is for the case when shape supervision is available, even a weak one. We revisit shape features used in previous methods, including segmentation and coordinate map. We explain when and why pixel-level shape supervision can improve pose estimation. Consequently, we add shape prediction as an intermediate layer in the MobilePose-Shape, and let the network learn pose from shape. Our models are trained on mixed real and synthetic data, with weak and noisy shape supervision. They are ultra lightweight that can run in real-time on modern mobile devices (e.g. 36 FPS on Galaxy S20). Comparing with previous single-shot solutions, our method has higher accuracy, while using a significantly smaller model (2~3% in model size or number of parameters).
We present a meta-learning framework for weakly supervised anomaly detection in videos, where the detector learns to adapt to unseen types of abnormal activities effectively when only video-level annotations of binary labels are available. Our work is motivated by the fact that existing methods suffer from poor generalization to diverse unseen examples. We claim that an anomaly detector equipped with a meta-learning scheme alleviates the limitation by leading the model to an initialization point for better optimization. We evaluate the performance of our framework on two challenging datasets, …
Many real-world tasks require models to compare images along multiple similarity conditions (e.g. similarity in color, category or shape). Existing methods often reason about these complex similarity relationships by learning condition-aware embeddings. While such embeddings aid models in learning different notions of similarity, they also limit their capability to generalize to unseen categories since they require explicit labels at test time. To address this deficiency, we propose an approach that jointly learns representations for the different similarity conditions and their contributions …
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background. Our method relies on moving objects being equivariant with respect to their transformation across frames and the background being constant. After training, we can manipulate and render the scenes in real time to create unseen combinations of objects, transformations, and backgrounds. We show results on moving MNIST with backgrounds.
A common problem with most zero and few-shot learning approaches is they suffer from bias towards seen classes resulting in sub-optimal performance. Existing efforts aim to utilize unlabeled images from unseen classes (i.e transductive zero-shot) during training to enable generalization. However, this limits their use in practical scenarios where data from target unseen classes is unavailable or infeasible to collect. In this work, we present a practical setting of inductive zero and few-shot learning, where unlabeled images from other out-of-data classes, that do not belong to seen or unseen …
We study the problem of learning how to predict attribute-object compositions from images, and its generalization to unseen compositions missing from the training data. To the best of our knowledge, this is a first large-scale study of this problem, involving hundreds of thousands of compositions. We train our framework with images from Instagram using hashtags as noisy weak supervision. We make careful design choices for data collection and modeling, in order to handle noisy annotations and unseen compositions. Finally, extensive evaluations show that learning to compose classifiers outperfor…
Novel View Synthesis (NVS) is concerned with synthesizing views under camera viewpoint transformations from one or multiple input images. NVS requires explicit reasoning about 3D object structure and unseen parts of the scene to synthesize convincing results. As a result, current approaches typically rely on supervised training with either ground truth 3D models or multiple target images. We propose Continuous Object Representation Networks (CORN), a conditional architecture that encodes an input image's geometry and appearance that map to a 3D consistent scene representation. We can train COR…
Current class-agnostic counting methods can generalise to unseen classes but usually require reference images to define the type of object to be counted, as well as instance annotations during training. Reference-less class-agnostic counting is an emerging field that identifies counting as, at its core, a repetition-recognition task. Such methods facilitate counting on a changing set composition. We show that a general feature space with global context can enumerate instances in an image without a prior on the object type present. Specifically, we demonstrate that regression from vision transf…
Split Matching for Inductive Zero-shot Semantic Segmentation
Graduate School of Informatics, Nagoya University (NU)（名古屋大学信息研究生院）；Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou) (HKUST (GZ))（香港科学与技术大学（广州）人工智能推进部）；Institute for Computer Science, Artificial Intelligence and Technology (INSAIT), Sofia University, St. Kliment Ohridski（索菲亚大学计算机科学、人工智能与技术研究所）
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…
University of Technology Sydney（悉尼科技大学）；Wenzhou University（温州大学）
Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy, which may lead to suboptimal ZSD results: 1) the learning process of those models ignores the available unseen class information, and thus can be easily biased towards the seen categories; 2) the original visual feature space is not well-structured and lack of discriminative information. To address these issues, we develop a novel…
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）；University of Rochester（罗切斯特大学）
Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs). However, existing approaches are mostly designed in an unsupervised manner while little attention has been paid to domain information within unpaired data. In this paper, we treat domain information as explicit supervision and design an unpaired image-to-image translation framework, Domain-supervised GAN (DosGAN), which takes the first step towards the exploration of explicit domain supervision. In contrast to representing domain characteristics using different generators or domain codes…
For many real-world robotics applications, robots need to continually adapt and learn new concepts. Further, robots need to learn through limited data because of scarcity of labeled data in the real-world environments. To this end, my research focuses on developing robots that continually learn in dynamic unseen environments/scenarios, learn from limited human supervision, remember previously learned knowledge and use that knowledge to learn new concepts. I develop machine learning models that not only produce State-of-the-results on benchmark datasets but also allow robots to learn new object…
Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose estimation models developed using supervision on large-scale in-studio datasets remains questionable, as these models often perform unsatisfactorily on unseen in-the-wild environments. Though weakly-supervised models have been proposed to address this shortcoming, performance of such models relies on availability of paired supervision on some related tasks, such as 2D pose or multi-view image pairs. In contrast, we prop…
Nowadays, deep neural networks outperform humans in many tasks. However, if the input distribution drifts away from the one used in training, their performance drops significantly. Recently published research has shown that adapting the model parameters to the test sample can mitigate this performance degradation. In this paper, we therefore propose a novel modification of the self-supervised training algorithm SwAV that adds the ability to adapt to single test samples. Using the provided prototypes of SwAV and our derived test-time loss, we align the representation of unseen test samples with…
Semantic scene understanding is an essential task for self-driving vehicles and mobile robots. In our work, we aim to estimate a semantic segmentation map, in which the foreground objects are removed and semantically inpainted with background classes, from a single RGB image. This semantic foreground inpainting task is performed by a single-stage convolutional neural network (CNN) that contains our novel max-pooling as inpainting (MPI) module, which is trained with weak supervision, i.e., it does not require manual background annotations for the foreground regions to be inpainted. Our approach…
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）；INRIA（法国国家信息与自动化研究所）；Universite Grenoble Alpes（格勒诺布尔阿尔卑斯大学）
Recent progress towards learning from limited supervision has encouraged efforts towards designing models that can recognize novel classes at test time (generalized zero-shot learning or GZSL). GZSL approaches assume knowledge of all classes, with or without labeled data, beforehand. However, practical scenarios demand models that are adaptable and can handle dynamic addition of new seen and unseen classes on the fly (that is continual generalized zero-shot learning or CGZSL). One solution is to sequentially retrain and reuse conventional GZSL methods, however, such an approach suffers from ca…
Politecnico di Torino（都灵理工大学）；Italian Institute of Technology（意大利理工学院）
Deep detection approaches are powerful in controlled conditions, but appear brittle and fail when source models are used off-the-shelf on unseen domains. Most of the existing works on domain adaptation simplify the setting and access jointly both a large source dataset and a sizable amount of target samples. However this scenario is unrealistic in many practical cases as when monitoring image feeds from social media: only a pretrained source model is available and every target image uploaded by the users belongs to a different domain not foreseen during training. We address this challenging se…
Recent approaches to drape garments quickly over arbitrary human bodies leverage self-supervision to eliminate the need for large training sets. However, they are designed to train one network per clothing item, which severely limits their generalization abilities. In our work, we rely on self-supervision to train a single network to drape multiple garments. This is achieved by predicting a 3D deformation field conditioned on the latent codes of a generative network, which models garments as unsigned distance fields. Our pipeline can generate and drape previously unseen garments of any topolog…
Seoul National University（首尔国立大学）；V.DO Inc（V.DO公司）
In this work, we introduce a novel weakly supervised object detection (WSOD) paradigm to detect objects belonging to rare classes that have not many examples using transferable knowledge from human-object interactions (HOI). While WSOD shows lower performance than full supervision, we mainly focus on HOI as the main context which can strongly supervise complex semantics in images. Therefore, we propose a novel module called RRPN (relational region proposal network) which outputs an object-localizing attention map only with human poses and action verbs. In the source domain, we fully train an o…
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；Huawei International Pte Ltd（华为国际私人有限公司）
Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses. In this paper, we propose a novel self-supervised approach that allows us to explicitly generate 2D-3D pose pairs for augmenting supervision, through a self-enhancing dual-loop learning framework. This is made possible via introducing a reinforcement-learning-based imitator, which is learned jointly with a pose estimator alongside a pose hallucinator; the three comp…
University of Oxford（牛津大学）；Centre for Medical Image Computing（医学图像计算中心）；InstaDeep（InstaDeep公司）
Despite the success of deep learning methods for semantic segmentation, few-shot semantic segmentation remains a challenging task due to the limited training data and the generalisation requirement for unseen classes. While recent progress has been particularly encouraging, we discover that existing methods tend to have poor performance in terms of meanIoU when query images contain other semantic classes besides the target class. To address this issue, we propose a novel self-supervised task that generates random pseudo-classes in the background of the query images, providing extra training da…
Meta AI Research（元人工智能研究院）；Carnegie Mellon University（卡内基梅隆大学）
Our work learns a unified model for single-view 3D reconstruction of objects from hundreds of semantic categories. As a scalable alternative to direct 3D supervision, our work relies on segmented image collections for learning 3D of generic categories. Unlike prior works that use similar supervision but learn independent category-specific models from scratch, our approach of learning a unified model simplifies the training process while also allowing the model to benefit from the common structure across categories. Using image collections from standard recognition datasets, we show that our ap…
To obtain 3D annotations, we are restricted to controlled environments or synthetic datasets, leading us to 3D datasets with less generalizability to real-world scenarios. To tackle this issue in the context of semi-supervised 3D hand shape and pose estimation, we propose the Pose Alignment network to propagate 3D annotations from labelled frames to nearby unlabelled frames in sparsely annotated videos. We show that incorporating the alignment supervision on pairs of labelled-unlabelled frames allows us to improve the pose estimation accuracy. Besides, we show that the proposed Pose Alignment …
ETH Zürich（苏黎世联邦理工学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（图宾根大学）
Neural implicit surface representations have emerged as a promising paradigm to capture 3D shapes in a continuous and resolution-independent manner. However, adapting them to articulated shapes is non-trivial. Existing approaches learn a backward warp field that maps deformed to canonical points. However, this is problematic since the backward warp field is pose dependent and thus requires large amounts of data to learn. To address this, we introduce SNARF, which combines the advantages of linear blend skinning (LBS) for polygonal meshes with those of neural implicit surfaces by learning a for…
United Imaging Intelligence（联影智能）；University at Buffalo（纽约州立大学布法罗分校）
To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-view ambiguities. Existing solutions typically suffer from poor generalization performance to new settings, largely due to the limited diversity of image-mesh pairs in multi-view training data. To address this shortcoming, people have explored the use of synthetic images. But besides the usual impact of visual gap between rendered and target data, synthetic-data-driven multi-view estimators also suffer from overfitting …
Salient Sparse Visual Odometry With Pose-Only Supervision
School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；State University of New York at Buffalo（纽约州立大学布法罗分校）
University of Technology Sydney（悉尼科技大学）；University of Washington（华盛顿大学）
Zero-shot learning (ZSL) aims to classify images of an unseen class only based on a few attributes describing that class but no access to any training sample. A popular strategy is to learn a mapping between the semantic space of class attributes and the visual space of images based on the seen classes and their data. Thus, an unseen class image can be ideally mapped to its corresponding class attributes. The key challenge is how to align the representations in the two spaces. For most ZSL settings, the attributes for each seen/unseen class are only represented by a vector while the seen-class…
James Cook University（詹姆斯·库克大学）；National Research Council of Italy（意大利国家研究委员会）
Given a sufficiently large training dataset, it is relatively easy to train a modern convolution neural network (CNN) as a required image classifier. However, for the task of fish classification and/or fish detection, if a CNN was trained to detect or classify particular fish species in particular background habitats, the same CNN exhibits much lower accuracy when applied to new/unseen fish species and/or fish habitats. Therefore, in practice, the CNN needs to be continuously fine-tuned to improve its classification accuracy to handle new project-specific fish species or habitats. In this work…
