Classification between thousands of classes in high-resolution images is one of the heavily studied problems in deep learning over the last decade. However, the challenge of fine-grained multi-class classification of objects in aerial images, especially in low resource cases, is still challenging and an active area of research in the literature. Solving this problem can give rise to various applications in the field of scene understanding and classification and re-identification of specific objects from aerial images. In this paper, we provide a description of our dataset - COFGA of multi-class annotated objects in aerial images. We examine the results of existing state-of-the-art models and modified deep neural networks. Finally, we explain in detail the first published competition for solving this task.
Indoor navigation aims at performing navigation within buildings. In scenes like home and factory, most intelligent mobile devices require an functionality of routing to guide itself precisely through indoor scenes to complete various tasks in order to serve human. In most scenarios, we expected an intelligent device capable of navigating itself in unseen environment. Although several solutions have been proposed to deal with this issue, they usually require pre-installed beacons or a map pre-built with SLAM, which means that they are not capable of working in novel environments. To address this, we proposed NavigationNet, a computer vision dataset and benchmark to allow the utilization of deep reinforcement learning on scene-understanding-based indoor navigation. We also proposed and formalized several typical indoor routing problems that are suitable for deep reinforcement learning.
Aggregated second-order features extracted from deep convolutional networks have been shown to be effective for texture generation, fine-grained recognition, material classification, and scene understanding. In this paper, we study a class of orderless aggregation functions designed to minimize interference or equalize contributions in the context of second-order features and we show that they can be computed just as efficiently as their first-order counterparts and they have favorable properties over aggregation by summation. Another line of work has shown that matrix power normalization after aggregation can significantly improve the generalization of second-order representations. We show that matrix power normalization implicitly equalizes contributions during aggregation thus establishing a connection between matrix normalization techniques and prior work on minimizing interference. Based on the analysis we present {\gamma}-democratic aggregators that interpolate between sum ({\gamma}=1) and democratic pooling ({\gamma}=0) outperforming both on several classification tasks. Moreover, unlike power normalization, the {\gamma}-democratic aggregations can be computed in a low dimensional space by sketching that allows the use of very high-dimensional second-order features. This results in a state-of-the-art performance on several datasets.
3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep convolutional neural network architecture with an auto-encoder. A data set of synthetic depth views and voxelized 3D representations is built based on ModelNet, a large-scale collection of CAD models, to train networks. The proposed method offers a significant advantage over current, explicit reconstruction methods in that it learns key geometric features offline and makes use of those to predict the most probable reconstruction of an unseen object. The relatively small network, consisting of roughly 4 million weights, achieves a 92.9% reconstruction accuracy at a 30x30x30 resolution through the use of a pre-trained decompression layer. This is roughly 1/4 the weights of the current leading network. The fast execution time of the model makes it suitable for real-time applications.
Monocular depth estimation aims at estimating a pixelwise depth map for a single image, which has wide applications in scene understanding and autonomous driving. Existing supervised and unsupervised methods face great challenges. Supervised methods require large amounts of depth measurement data, which are generally difficult to obtain, while unsupervised methods are usually limited in estimation accuracy. Synthetic data generated by graphics engines provide a possible solution for collecting large amounts of depth data. However, the large domain gaps between synthetic and realistic data make directly training with them challenging. In this paper, we propose to use the stereo matching network as a proxy to learn depth from synthetic data and use predicted stereo disparity maps for supervising the monocular depth estimation network. Cross-domain synthetic data could be fully utilized in this novel framework. Different strategies are proposed to ensure learned depth perception capability well transferred across different domains. Our extensive experiments show state-of-the-art results of monocular depth estimation on KITTI dataset.
We propose a computational framework to jointly parse a single RGB image and reconstruct a holistic 3D configuration composed by a set of CAD models using a stochastic grammar model. Specifically, we introduce a Holistic Scene Grammar (HSG) to represent the 3D scene structure, which characterizes a joint distribution over the functional and geometric space of indoor scenes. The proposed HSG captures three essential and often latent dimensions of the indoor scenes: i) latent human context, describing the affordance and the functionality of a room arrangement, ii) geometric constraints over the scene configurations, and iii) physical constraints that guarantee physically plausible parsing and reconstruction. We solve this joint parsing and reconstruction problem in an analysis-by-synthesis fashion, seeking to minimize the differences between the input image and the rendered images generated by our 3D representation, over the space of depth, surface normal, and object segmentation map. The optimal configuration, represented by a parse graph, is inferred using Markov chain Monte Carlo (MCMC), which efficiently traverses through the non-differentiable solution space, jointly optimizing object localization, 3D layout, and hidden human context. Experimental results demonstrate that the proposed algorithm improves the generalization ability and significantly outperforms prior methods on 3D layout estimation, 3D object detection, and holistic scene understanding.
Real-life man-made objects often exhibit strong and easily-identifiable structure, as a direct result of their design or their intended functionality. Structure typically appears in the form of individual parts and their arrangement. Knowing about object structure can be an important cue for object recognition and scene understanding - a key goal for various AR and robotics applications. However, commodity RGB-D sensors used in these scenarios only produce raw, unorganized point clouds, without structural information about the captured scene. Moreover, the generated data is commonly partial and susceptible to artifacts and noise, which makes inferring the structure of scanned objects challenging. In this paper, we organize large shape collections into parameterized shape templates to capture the underlying structure of the objects. The templates allow us to transfer the structural information onto new objects and incomplete scans. We employ a deep neural network that matches the partial scan with one of the shape templates, then match and fit it to complete and detailed models from the collection. This allows us to faithfully label its parts and to guide the reconstruction of the scanned object. We showcase the effectiveness of our method by comparing it to other state-of-the-art approaches.
This work addresses the problem of semantic scene understanding under dense fog. Although considerable progress has been made in semantic scene understanding, it is mainly related to clear-weather scenes. Extending recognition methods to adverse weather conditions such as fog is crucial for outdoor applications. In this paper, we propose a novel method, named Curriculum Model Adaptation (CMAda), which gradually adapts a semantic segmentation model from light synthetic fog to dense real fog in multiple steps, using both synthetic and real foggy data. In addition, we present three other main stand-alone contributions: 1) a novel method to add synthetic fog to real, clear-weather scenes using semantic input; 2) a new fog density estimator; 3) the Foggy Zurich dataset comprising $3808$ real foggy images, with pixel-level semantic annotations for $16$ images with dense fog. Our experiments show that 1) our fog simulation slightly outperforms a state-of-the-art competing simulation with respect to the task of semantic foggy scene understanding (SFSU); 2) CMAda improves the performance of state-of-the-art models for SFSU significantly by leveraging unlabeled real foggy data. The datasets and code are publicly available.
Target tracking in a camera network is an important task for surveillance and scene understanding. The task is challenging due to disjoint views and illumination variation in different cameras. In this direction, many graph-based methods were proposed using appearance-based features. However, the appearance information fades with high illumination variation in the different camera FOVs. We, in this paper, use spatial and temporal information as the state of the target to learn a policy that predicts the next camera given the current state. The policy is trained using Q-learning and it does not assume any information about the topology of the camera network. We will show that the policy learns the camera network topology. We demonstrate the performance of the proposed method on the NLPR MCT dataset.
Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image. A multi-task framework called UPerNet and a training strategy are developed to learn from heterogeneous image annotations. We benchmark our framework on Unified Perceptual Parsing and show that it is able to effectively segment a wide range of concepts from images. The trained networks are further applied to discover visual knowledge in natural scenes. Models are available at \url{https://github.com/CSAILVision/unifiedparsing}.
Optical flow, semantic segmentation, and surface normals represent different information modalities, yet together they bring better cues for scene understanding problems. In this paper, we study the influence between the three modalities: how one impacts on the others and their efficiency in combination. We employ a modular approach using a convolutional refinement network which is trained supervised but isolated from RGB images to enforce joint modality features. To assist the training process, we create a large-scale synthetic outdoor dataset that supports dense annotation of semantic segmentation, optical flow, and surface normals. The experimental results show positive influence among the three modalities, especially for objects' boundaries, region consistency, and scene structures.
While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately. In this paper, we propose to tackle these problems from a bottom-up perspective, where we simply need a semantic segmentation of the scene as input. We employ the DeepLab architecture, based on the ResNet deep network, which leverages multi-scale inputs to later fuse their responses to perform a precise pixel labeling of the scene. This semantic segmentation mask is used to localize the objects and to recognize the scene, following two simple yet effective strategies. We evaluate the benefits of our solutions, performing a thorough experimental evaluation on the NYU Depth V2 dataset. Our approach achieves a performance that beats the leading results by a significant margin, defining the new state of the art in this benchmark for the three tasks comprising the scene understanding: semantic segmentation, object detection and scene categorization.
Nowadays, robots are dominating the manufacturing, entertainment and healthcare industries. Robot vision aims to equip robots with the ability to discover information, understand it and interact with the environment. These capabilities require an agent to effectively understand object affordances and functionalities in complex visual domains. In this literature survey, we first focus on Visual affordances and summarize the state of the art as well as open problems and research gaps. Specifically, we discuss sub-problems such as affordance detection, categorization, segmentation and high-level reasoning. Furthermore, we cover functional scene understanding and the prevalent functional descriptors used in the literature. The survey also provides necessary background to the problem, sheds light on its significance and highlights the existing challenges for affordance and functionality learning.
Recent approaches on visual scene understanding attempt to build a scene graph -- a computational representation of objects and their pairwise relationships. Such rich semantic representation is very appealing, yet difficult to obtain from a single image, especially when considering complex spatial arrangements in the scene. Differently, an image sequence conveys useful information using the multi-view geometric relations arising from camera motion. Indeed, in such cases, object relationships are naturally related to the 3D scene structure. To this end, this paper proposes a system that first computes the geometrical location of objects in a generic scene and then efficiently constructs scene graphs from video by embedding such geometrical reasoning. Such compelling representation is obtained using a new model where geometric and visual features are merged using an RNN framework. We report results on a dataset we created for the task of 3D scene graph generation in multiple views.
Shadows are common aspect of images and when left undetected can hinder scene understanding and visual processing. We propose a simple yet effective approach based on reflectance to detect shadows from single image. An image is first segmented and based on the reflectance, illumination and texture characteristics, segments pairs are identified as shadow and non-shadow pairs. The proposed method is tested on two publicly available and widely used datasets. Our method achieves higher accuracy in detecting shadows compared to previous reported methods despite requiring fewer parameters. We also show results of shadow-free images by relighting the pixels in the detected shadow regions.
Within the realm of service robotics, researchers have placed a great amount of effort into learning, understanding, and representing motions as manipulations for task execution by robots. The task of robot learning and problem-solving is very broad, as it integrates a variety of tasks such as object detection, activity recognition, task/motion planning, localization, knowledge representation and retrieval, and the intertwining of perception/vision and machine learning techniques. In this paper, we solely focus on knowledge representations and notably how knowledge is typically gathered, represented, and reproduced to solve problems as done by researchers in the past decades. In accordance with the definition of knowledge representations, we discuss the key distinction between such representations and useful learning models that have extensively been introduced and studied in recent years, such as machine learning, deep learning, probabilistic modelling, and semantic graphical structures. Along with an overview of such tools, we discuss the problems which have existed in robot learning and how they have been built and used as solutions, technologies or developments (if any) which have contributed to solving them. Finally, we discuss key principles that should be considered when designing an effective knowledge representation.
We present research using the latest reinforcement learning algorithm for end-to-end driving without any mediated perception (object recognition, scene understanding). The newly proposed reward and learning strategies lead together to faster convergence and more robust driving using only RGB image from a forward facing camera. An Asynchronous Actor Critic (A3C) framework is used to learn the car control in a physically and graphically realistic rally game, with the agents evolving simultaneously on tracks with a variety of road structures (turns, hills), graphics (seasons, location) and physics (road adherence). A thorough evaluation is conducted and generalization is proven on unseen tracks and using legal speed limits. Open loop tests on real sequences of images show some domain adaption capability of our method.
We position a narrative-centred computational model for high-level knowledge representation and reasoning in the context of a range of assistive technologies concerned with "visuo-spatial perception and cognition" tasks. Our proposed narrative model encompasses aspects such as \emph{space, events, actions, change, and interaction} from the viewpoint of commonsense reasoning and learning in large-scale cognitive systems. The broad focus of this paper is on the domain of "human-activity interpretation" in smart environments, ambient intelligence etc. In the backdrop of a "smart meeting cinematography" domain, we position the proposed narrative model, preliminary work on perceptual narrativisation, and the immediate outlook on constructing general-purpose open-source tools for perceptual narrativisation. ACM Classification: I.2 Artificial Intelligence: I.2.0 General -- Cognitive Simulation, I.2.4 Knowledge Representation Formalisms and Methods, I.2.10 Vision and Scene Understanding: Architecture and control structures, Motion, Perceptual reasoning, Shape, Video analysis General keywords: cognitive systems; human-computer interaction; spatial cognition and computation; commonsense reasoning; spatial and temporal reasoning; assistive technologies
Images seen during test time are often not from the same distribution as images used for learning. This problem, known as domain shift, occurs when training classifiers from object-centric internet image databases and trying to apply them directly to scene understanding tasks. The consequence is often severe performance degradation and is one of the major barriers for the application of classifiers in real-world systems. In this paper, we show how to learn transform-based domain adaptation classifiers in a scalable manner. The key idea is to exploit an implicit rank constraint, originated from a max-margin domain adaptation formulation, to make optimization tractable. Experiments show that the transformation between domains can be very efficiently learned from data and easily applied to new categories. This begins to bridge the gap between large-scale internet image collections and object images captured in everyday life environments.
In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models. This algorithm blends the learning and inference tasks, which results in a significant speedup over traditional approaches, such as conditional random fields and structured support vector machines. For this purpose we utilize the structures of the predictors to describe a low dimensional structured prediction task which encourages local consistencies within the different structures while learning the parameters of the model. Convexity of the learning task provides the means to enforce the consistencies between the different parts. The inference-learning blending algorithm that we propose is guaranteed to converge to the optimum of the low dimensional primal and dual programs. Unlike many of the existing approaches, the inference-learning blending allows us to learn efficiently high-order graphical models, over regions of any size, and very large number of parameters. We demonstrate the effectiveness of our approach, while presenting state-of-the-art results in stereo estimation, semantic segmentation, shape reconstruction, and indoor scene understanding.