Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of data, few-shot object detection aims to learn from few object instances of new categories in the target domain. In this survey, we provide an overview of the state of the art in few-shot object detection. We categorize approaches according to their training scheme and architectural layout. For each type of approaches, we describe the general realization as well as concepts to improve the performance on novel categories. Whenever appropriate, we give short takeaways regarding these concepts in order to highlight the best ideas. Eventually, we introduce commonly used datasets and their evaluation protocols and analyze reported benchmark results. As a result, we emphasize common challenges in evaluation and identify the most promising current trends in this emerging field of few-shot object detection.
Unsupervised video object segmentation (UVOS) is a per-pixel binary labeling problem which aims at separating the foreground object from the background in the video without using the ground truth (GT) mask of the foreground object. Most of the previous UVOS models use the first frame or the entire video as a reference frame to specify the mask of the foreground object. Our question is why the first frame should be selected as a reference frame or why the entire video should be used to specify the mask. We believe that we can select a better reference frame to achieve the better UVOS performance than using only the first frame or the entire video as a reference frame. In our paper, we propose Easy Frame Selector (EFS). The EFS enables us to select an 'easy' reference frame that makes the subsequent VOS become easy, thereby improving the VOS performance. Furthermore, we propose a new framework named as Iterative Mask Prediction (IMP). In the framework, we repeat applying EFS to the given video and selecting an 'easier' reference frame from the video than the previous iteration, increasing the VOS performance incrementally. The IMP consists of EFS, Bi-directional Mask Prediction (BMP), and Temporal Information Updating (TIU). From the proposed framework, we achieve state-of-the-art performance in three UVOS benchmark sets: DAVIS16, FBMS, and SegTrack-V2.
Image segmentation is an essential component in many image processing and computer vision tasks. The primary goal of image segmentation is to simplify an image for easier analysis, and there are two broad approaches for achieving this: edge based methods, which extract the boundaries of specific known objects, and region based methods, which partition the image into regions that are statistically homogeneous. One of the more prominent edge finding methods, known as the level set method, evolves a zero-level contour in the image plane with gradient descent until the contour has converged to the object boundaries. While the classical level set method and its variants have proved successful in segmenting real images, they are susceptible to becoming stuck in noisy regions of the image plane without a priori knowledge of the image and they are unable to provide details beyond object outer boundary locations. We propose a modification to the variational level set image segmentation method that can quickly detect object boundaries by making use of random point initialization. We demonstrate the efficacy of our approach by comparing the performance of our method on real images to that of the prominent Canny Method.
Template-based discriminative trackers are currently the dominant tracking paradigm due to their robustness, but are restricted to bounding box tracking and a limited range of transformation models, which reduces their localization accuracy. We propose a discriminative single-shot segmentation tracker -- D3S2, which narrows the gap between visual object tracking and video object segmentation. A single-shot network applies two target models with complementary geometric properties, one invariant to a broad range of transformations, including non-rigid deformations, the other assuming a rigid object to simultaneously achieve robust online target segmentation. The overall tracking reliability is further increased by decoupling the object and feature scale estimation. Without per-dataset finetuning, and trained only for segmentation as the primary output, D3S2 outperforms all published trackers on the recent short-term tracking benchmark VOT2020 and performs very close to the state-of-the-art trackers on the GOT-10k, TrackingNet, OTB100 and LaSoT. D3S2 outperforms the leading segmentation tracker SiamMask on video object segmentation benchmarks and performs on par with top video object segmentation algorithms.
Object recognition for the most part has been approached as a one-hot problem that treats classes to be discrete and unrelated. Each image region has to be assigned to one member of a set of objects, including a background class, disregarding any similarities in the object types. In this work, we compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs that are widely applied in open world object detection. Extensive experimental results on multiple knowledge-embeddings as well as distance metrics indicate that knowledge-based class representations result in more semantically grounded misclassifications while performing on par compared to one-hot methods on the challenging COCO and Cityscapes object detection benchmarks. We generalize our findings to multiple object detection architectures by proposing a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.
Rendering articulated objects while controlling their poses is critical to applications such as virtual reality or animation for movies. Manipulating the pose of an object, however, requires the understanding of its underlying structure, that is, its joints and how they interact with each other. Unfortunately, assuming the structure to be known, as existing methods do, precludes the ability to work on new object categories. We propose to learn both the appearance and the structure of previously unseen articulated objects by observing them move from multiple views, with no joints annotation supervision, or information about the structure. We observe that 3D points that are static relative to one another should belong to the same part, and that adjacent parts that move relative to each other must be connected by a joint. To leverage this insight, we model the object parts in 3D as ellipsoids, which allows us to identify joints. We combine this explicit representation with an implicit one that compensates for the approximation introduced. We show that our method works for different structures, from quadrupeds, to single-arm robots, to humans.
We examined the feasibility of generative adversarial networks (GANs) to generate photo-realistic images from LiDAR point clouds. For this purpose, we created a dataset of point cloud image pairs and trained the GAN to predict photorealistic images from LiDAR point clouds containing reflectance and distance information. Our models learned how to predict realistically looking images from just point cloud data, even images with black cars. Black cars are difficult to detect directly from point clouds because of their low level of reflectivity. This approach might be used in the future to perform visual object recognition on photorealistic images generated from LiDAR point clouds. In addition to the conventional LiDAR system, a second system that generates photorealistic images from LiDAR point clouds would run simultaneously for visual object recognition in real-time. In this way, we might preserve the supremacy of LiDAR and benefit from using photo-realistic images for visual object recognition without the usage of any camera. In addition, this approach could be used to colorize point clouds without the usage of any camera images.
The accelerating development of autonomous driving technology has placed greater demands on obtaining large amounts of high-quality data. Representative, labeled, real world data serves as the fuel for training deep learning networks, critical for improving self-driving perception algorithms. In this paper, we introduce PandaSet, the first dataset produced by a complete, high-precision autonomous vehicle sensor kit with a no-cost commercial license. The dataset was collected using one 360{\deg} mechanical spinning LiDAR, one forward-facing, long-range LiDAR, and 6 cameras. The dataset contains more than 100 scenes, each of which is 8 seconds long, and provides 28 types of labels for object classification and 37 types of labels for semantic segmentation. We provide baselines for LiDAR-only 3D object detection, LiDAR-camera fusion 3D object detection and LiDAR point cloud segmentation. For more details about PandaSet and the development kit, see https://scale.com/open-datasets/pandaset.
Audiovisual scenes are pervasive in our daily life. It is commonplace for humans to discriminatively localize different sounding objects but quite challenging for machines to achieve class-aware sounding objects localization without category annotations, i.e., localizing the sounding object and recognizing its category. To address this problem, we propose a two-stage step-by-step learning framework to localize and recognize sounding objects in complex audiovisual scenarios using only the correspondence between audio and vision. First, we propose to determine the sounding area via coarse-grained audiovisual correspondence in the single source cases. Then visual features in the sounding area are leveraged as candidate object representations to establish a category-representation object dictionary for expressive visual character extraction. We generate class-aware object localization maps in cocktail-party scenarios and use audiovisual correspondence to suppress silent areas by referring to this dictionary. Finally, we employ category-level audiovisual consistency as the supervision to achieve fine-grained audio and sounding object distribution alignment. Experiments on both realistic and synthesized videos show that our model is superior in localizing and recognizing objects as well as filtering out silent ones. We also transfer the learned audiovisual network into the unsupervised object detection task, obtaining reasonable performance.
The synthesis of human grasping has numerous applications including AR/VR, video games and robotics. While methods have been proposed to generate realistic hand-object interaction for object grasping and manipulation, these typically only consider interacting hand alone. Our goal is to synthesize whole-body grasping motions. Starting from an arbitrary initial pose, we aim to generate diverse and natural whole-body human motions to approach and grasp a target object in 3D space. This task is challenging as it requires modeling both whole-body dynamics and dexterous finger movements. To this end, we propose SAGA (StochAstic whole-body Grasping with contAct), a framework which consists of two key components: (a) Static whole-body grasping pose generation. Specifically, we propose a multi-task generative model, to jointly learn static whole-body grasping poses and human-object contacts. (b) Grasping motion infilling. Given an initial pose and the generated whole-body grasping pose as the start and end of the motion respectively, we design a novel contact-aware generative motion infilling module to generate a diverse set of grasp-oriented motions. We demonstrate the effectiveness of our method, which is a novel generative framework to synthesize realistic and expressive whole-body motions that approach and grasp randomly placed unseen objects. Code and models are available at https://jiahaoplus.github.io/SAGA/saga.html.
If a robotic agent wants to exploit symbolic planning techniques to achieve some goal, it must be able to properly ground an abstract planning domain in the environment in which it operates. However, if the environment is initially unknown by the agent, the agent needs to explore it and discover the salient aspects of the environment needed to reach its goals. Namely, the agent has to discover: (i) the objects present in the environment, (ii) the properties of these objects and their relations, and finally (iii) how abstract actions can be successfully executed. The paper proposes a framework that aims to accomplish the aforementioned perspective for an agent that perceives the environment partially and subjectively, through real value sensors (e.g., GPS, and on-board camera) and can operate in the environment through low level actuators (e.g., move forward of 20 cm). We evaluate the proposed architecture in photo-realistic simulated environments, where the sensors are RGB-D on-board camera, GPS and compass, and low level actions include movements, grasping/releasing objects, and manipulating objects. The agent is placed in an unknown environment and asked to find objects of a certain type, place an object on top of another, close or open an object of a certain type. We compare our approach with the state of the art methods on object goal navigation based on reinforcement learning, showing better performances.
This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive performance in image classification tasks. To adopt ViT to object detection and dense prediction tasks, many works inherit the multistage design from convolutional networks and highly customized ViT architectures. Behind this design, the goal is to pursue a better trade-off between computational cost and effective aggregation of multiscale global contexts. However, existing works adopt the multistage architectural design as a black-box solution without a clear understanding of its true benefits. In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy. We further complete a scaling rule to optimize our model's trade-off on accuracy and computation cost / model size. By leveraging a constant feature resolution and hidden size throughout the encoder blocks, we propose a simple and compact ViT architecture called Universal Vision Transformer (UViT) that achieves strong performance on COCO object detection and instance segmentation tasks.
Difficulties in following speech due to loud background sounds are common in broadcasting. Object-based audio, e.g., MPEG-H Audio solves this problem by providing a user-adjustable speech level. While object-based audio is gaining momentum, transitioning to it requires time and effort. Also, lots of content exists, produced and archived outside the object-based workflows. To address this, Fraunhofer IIS has developed a deep-learning solution called Dialog+, capable of enabling speech level personalization also for content with only the final audio tracks available. This paper reports on public field tests evaluating Dialog+, conducted together with Westdeutscher Rundfunk (WDR) and Bayerischer Rundfunk (BR), starting from September 2020. To our knowledge, these are the first large-scale tests of this kind. As part of one of these, a survey with more than 2,000 participants showed that 90% of the people above 60 years old have problems in understanding speech in TV "often" or "very often". Overall, 83% of the participants liked the possibility to switch to Dialog+, including those who do not normally struggle with speech intelligibility. Dialog+ introduces a clear benefit for the audience, filling the gap between object-based broadcasting and traditionally produced material.
We base our work on the teleosemantic modelling of concepts as abilities implementing the distinct functions of recognition and classification. Accordingly, we model two types of concepts - substance concepts suited for object recognition exploiting visual properties, and classification concepts suited for classification of substance concepts exploiting linguistically grounded properties. The goal in this paper is to demonstrate that object recognition can be construed as classification via visual properties, as distinct from work in mainstream computer vision. Towards that, we present an object recognition process based on Ranganathan's four-phased faceted knowledge organization process, grounded in the teleosemantic distinctions of substance concept and classification concept. We also briefly introduce the ongoing project MultiMedia UKC, whose aim is to build an object recognition resource following our proposed process
We propose a new 3D spatial understanding task of 3D Question Answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of the rich RGB-D indoor scan and answer the given textual questions about the 3D scene. Unlike the 2D-question answering of VQA, the conventional 2D-QA models suffer from problems with spatial understanding of object alignment and directions and fail the object identification from the textual questions in 3D-QA. We propose a baseline model for 3D-QA, named ScanQA model, where the model learns a fused descriptor from 3D object proposals and encoded sentence embeddings. This learned descriptor correlates the language expressions with the underlying geometric features of the 3D scan and facilitates the regression of 3D bounding boxes to determine described objects in textual questions and outputs correct answers. We collected human-edited question-answer pairs with free-form answers that are grounded to 3D objects in each 3D scene. Our new ScanQA dataset contains over 40K question-answer pairs from the 800 indoor scenes drawn from the ScanNet dataset. To the best of our knowledge, the proposed 3D-QA task is the first large-scale effort to perform object-grounded question-answering in 3D environments.
In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computing and storage resources which are not feasible to deploy on the limited memory device. Some others shallow layer network will not maintain the same accuracy compared with U-shape structure and the deep network structure with more parameters will not converge to a global minimum loss with great speed. To overcome all of these disadvantages, we proposed a new deep convolution network architecture with three contributions: (1) using smaller convolution neural networks (CNNs) to compress the model in our improved salient object features compression and reinforcement extraction module (ISFCREM) to reduce parameters of the model. (2) introducing channel attention mechanism in ISFCREM to weigh different channels for improving the ability of feature representation. (3) applying a new optimizer to accumulate the long-term gradient information during training to adaptively tune the learning rate. The results demonstrate that the proposed method can compress the model to 1/3 of the original size nearly without losing the accuracy and converging faster and more smoothly on six widely used datasets of salient object detection compared with the others models. Our code is published in https://gitee.com/binzhangbinzhangbin/code-a-novel-attention-based-network-for-fast-salient-object-detection.git
Modeling spatial-temporal relations is imperative for recognizing human actions, especially when a human is interacting with objects, while multiple objects appear around the human differently over time. Most existing action recognition models focus on learning overall visual cues of a scene but disregard informative fine-grained features, which can be captured by learning human-object relationships and interactions. In this paper, we learn human-object relationships by exploiting the interaction of their local and global contexts. We hence propose the Global-Local Interaction Distillation Network (GLIDN), learning human and object interactions through space and time via knowledge distillation for fine-grained scene understanding. GLIDN encodes humans and objects into graph nodes and learns local and global relations via graph attention network. The local context graphs learn the relation between humans and objects at a frame level by capturing their co-occurrence at a specific time step. The global relation graph is constructed based on the video-level of human and object interactions, identifying their long-term relations throughout a video sequence. More importantly, we investigate how knowledge from these graphs can be distilled to their counterparts for improving human-object interaction (HOI) recognition. We evaluate our model by conducting comprehensive experiments on two datasets including Charades and CAD-120 datasets. We have achieved better results than the baselines and counterpart approaches.
Object detection in high-resolution satellite imagery is emerging as a scalable alternative to on-the-ground survey data collection in many environmental and socioeconomic monitoring applications. However, performing object detection over large geographies can still be prohibitively expensive due to the high cost of purchasing imagery and compute. Inspired by traditional survey data collection strategies, we propose an approach to estimate object count statistics over large geographies through sampling. Given a cost budget, our method selects a small number of representative areas by sampling from a learnable proposal distribution. Using importance sampling, we are able to accurately estimate object counts after processing only a small fraction of the images compared to an exhaustive approach. We show empirically that the proposed framework achieves strong performance on estimating the number of buildings in the United States and Africa, cars in Kenya, brick kilns in Bangladesh, and swimming pools in the U.S., while requiring as few as 0.01% of satellite images compared to an exhaustive approach.
We introduce the first comprehensive 3D dataset for the task of unsupervised anomaly detection and localization. It is inspired by real-world visual inspection scenarios in which a model has to detect various types of defects on manufactured products, even if it is trained only on anomaly-free data. There are defects that manifest themselves as anomalies in the geometric structure of an object. These cause significant deviations in a 3D representation of the data. We employed a high-resolution industrial 3D sensor to acquire depth scans of 10 different object categories. For all object categories, we present a training and validation set, each of which solely consists of scans of anomaly-free samples. The corresponding test sets contain samples showing various defects such as scratches, dents, holes, contaminations, or deformations. Precise ground-truth annotations are provided for every anomalous test sample. An initial benchmark of 3D anomaly detection methods on our dataset indicates a considerable room for improvement.
Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel, uniquely segmenting and identifying all object instances consistently across all frames. Classic solutions usually decompose the VPS task into several sub-tasks and utilize multiple surrogates (e.g. boxes and masks, centres and offsets) to represent objects. However, this divide-and-conquer strategy requires complex post-processing in both spatial and temporal domains and is vulnerable to failures from surrogate tasks. In this paper, inspired by object-centric learning which learns compact and robust object representations, we present Slot-VPS, the first end-to-end framework for this task. We encode all panoptic entities in a video, including both foreground instances and background semantics, with a unified representation called panoptic slots. The coherent spatio-temporal object's information is retrieved and encoded into the panoptic slots by the proposed Video Panoptic Retriever, enabling it to localize, segment, differentiate, and associate objects in a unified manner. Finally, the output panoptic slots can be directly converted into the class, mask, and object ID of panoptic objects in the video. We conduct extensive ablation studies and demonstrate the effectiveness of our approach on two benchmark datasets, Cityscapes-VPS (\textit{val} and test sets) and VIPER (\textit{val} set), achieving new state-of-the-art performance of 63.7, 63.3 and 56.2 VPQ, respectively.