Semantic scene understanding is crucial for robust and safe autonomous navigation, particularly so in off-road environments. Recent deep learning advances for 3D semantic segmentation rely heavily on large sets of training data, however existing autonomy datasets either represent urban environments or lack multimodal off-road data. We fill this gap with RELLIS-3D, a multimodal dataset collected in an off-road environment, which contains annotations for 13,556 LiDAR scans and 6,235 images. The data was collected on the Rellis Campus of Texas A\&M University and presents challenges to existing algorithms related to class imbalance and environmental topography. Additionally, we evaluate the current state-of-the-art deep learning semantic segmentation models on this dataset. Experimental results show that RELLIS-3D presents challenges for algorithms designed for segmentation in urban environments. This novel dataset provides the resources needed by researchers to continue to develop more advanced algorithms and investigate new research directions to enhance autonomous navigation in off-road environments. RELLIS-3D is available at https://github.com/unmannedlab/RELLIS-3D
Different environments pose a great challenge to the outdoor robust visual perception for long-term autonomous driving, and the generalization of learning-based algorithms on different environments is still an open problem. Although monocular depth prediction has been well studied recently, few works focus on the robustness of learning-based depth prediction across different environments, e.g. changing illumination and seasons, owing to the lack of such a multi-environment real-world dataset and benchmark. To this end, the first cross-season monocular depth prediction dataset and benchmark, SeasonDepth, is introduced to benchmark the depth estimation performance under different environments. We investigate several state-of-the-art representative open-source supervised and self-supervised depth prediction methods using newly-formulated metrics. Through extensive experimental evaluation on the proposed dataset and cross-dataset evaluation with current autonomous driving datasets, the performance and robustness against the influence of multiple environments are analyzed qualitatively and quantitatively. We show that long-term monocular depth prediction is still challenging and believe our work can boost further research on the long-term robustness and generalization for outdoor visual perception. The dataset is available on https://seasondepth.github.io, and the benchmark toolkit is available on https://github.com/ SeasonDepth/SeasonDepth.
Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which renders it unsuitable for high resolution imagery. In this paper, we explore the efficiency of context graph reasoning and propose a novel framework called Squeeze Reasoning. Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector and perform reasoning within the single vector where the computation cost can be significantly reduced. Specifically, we build the node graph in the vector where each node represents an abstract semantic concept. The refined feature within the same semantic category results to be consistent, which is thus beneficial for downstream tasks. We show that our approach can be modularized as an end-to-end trained block and can be easily plugged into existing networks. {Despite its simplicity and being lightweight, the proposed strategy allows us to establish the considerable results on different semantic segmentation datasets and shows significant improvements with respect to strong baselines on various other scene understanding tasks including object detection, instance segmentation and panoptic segmentation.} Code is available at \url{https://github.com/lxtGH/SFSegNets}.
For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-pixel ground truth labels from real images. We address this challenge by introducing Hypersim, a photorealistic synthetic dataset for holistic indoor scene understanding. To create our dataset, we leverage a large repository of synthetic scenes created by professional artists, and we generate 77,400 images of 461 indoor scenes with detailed per-pixel labels and corresponding ground truth geometry. Our dataset: (1) relies exclusively on publicly available 3D assets; (2) includes complete scene geometry, material information, and lighting information for every scene; (3) includes dense per-pixel semantic instance segmentations and complete camera information for every image; and (4) factors every image into diffuse reflectance, diffuse illumination, and a non-diffuse residual term that captures view-dependent lighting effects. We analyze our dataset at the level of scenes, objects, and pixels, and we analyze costs in terms of money, computation time, and annotation effort. Remarkably, we find that it is possible to generate our entire dataset from scratch, for roughly half the cost of training a popular open-source natural language processing model. We also evaluate sim-to-real transfer performance on two real-world scene understanding tasks - semantic segmentation and 3D shape prediction - where we find that pre-training on our dataset significantly improves performance on both tasks, and achieves state-of-the-art performance on the most challenging Pix3D test set. All of our rendered image data, as well as all the code we used to generate our dataset and perform our experiments, is available online.
Panoptic segmentation is posed as a new popular test-bed for the state-of-the-art holistic scene understanding methods with the requirement of simultaneously segmenting both foreground things and background stuff. The state-of-the-art panoptic segmentation network exhibits high structural complexity in different network components, i.e. backbone, proposal-based foreground branch, segmentation-based background branch, and feature fusion module across branches, which heavily relies on expert knowledge and tedious trials. In this work, we propose an efficient, cooperative and highly automated framework to simultaneously search for all main components including backbone, segmentation branches, and feature fusion module in a unified panoptic segmentation pipeline based on the prevailing one-shot Network Architecture Search (NAS) paradigm. Notably, we extend the common single-task NAS into the multi-component scenario by taking the advantage of the newly proposed intra-modular search space and problem-oriented inter-modular search space, which helps us to obtain an optimal network architecture that not only performs well in both instance segmentation and semantic segmentation tasks but also be aware of the reciprocal relations between foreground things and background stuff classes. To relieve the vast computation burden incurred by applying NAS to complicated network architectures, we present a novel path-priority greedy search policy to find a robust, transferrable architecture with significantly reduced searching overhead. Our searched architecture, namely Auto-Panoptic, achieves the new state-of-the-art on the challenging COCO and ADE20K benchmarks. Moreover, extensive experiments are conducted to demonstrate the effectiveness of path-priority policy and transferability of Auto-Panoptic across different datasets. Codes and models are available at: https://github.com/Jacobew/AutoPanoptic.
In many real-world applications, the relative depth of objects in an image is crucial for scene understanding. Recent approaches mainly tackle the problem of depth prediction in monocular images by treating the problem as a regression task. Yet, being interested in an order relation in the first place, ranking methods suggest themselves as a natural alternative to regression, and indeed, ranking approaches leveraging pairwise comparisons as training information ("object A is closer to the camera than B") have shown promising performance on this problem. In this paper, we elaborate on the use of so-called listwise ranking as a generalization of the pairwise approach. Our method is based on the Plackett-Luce (PL) model, a probability distribution on rankings, which we combine with a state-of-the-art neural network architecture and a simple sampling strategy to reduce training complexity. Moreover, taking advantage of the representation of PL as a random utility model, the proposed predictor offers a natural way to recover (shift-invariant) metric depth information from ranking-only data provided at training time. An empirical evaluation on several benchmark datasets in a "zero-shot" setting demonstrates the effectiveness of our approach compared to existing ranking and regression methods.
Panoptic Segmentation aims to provide an understanding of background (stuff) and instances of objects (things) at a pixel level. It combines the separate tasks of semantic segmentation (pixel level classification) and instance segmentation to build a single unified scene understanding task. Typically, panoptic segmentation is derived by combining semantic and instance segmentation tasks that are learned separately or jointly (multi-task networks). In general, instance segmentation networks are built by adding a foreground mask estimation layer on top of object detectors or using instance clustering methods that assign a pixel to an instance center. In this work, we present a fully convolution neural network that learns instance segmentation from semantic segmentation and instance contours (boundaries of things). Instance contours along with semantic segmentation yield a boundary aware semantic segmentation of things. Connected component labeling on these results produces instance segmentation. We merge semantic and instance segmentation results to output panoptic segmentation. We evaluate our proposed method on the CityScapes dataset to demonstrate qualitative and quantitative performances along with several ablation studies. Our overview video can be accessed from url:https://youtu.be/wBtcxRhG3e0.
Datasets for autonomous cars are essential for the development and benchmarking of perception systems. However, most existing datasets are captured with camera and LiDAR sensors in good weather conditions. In this paper, we present the RAdar Dataset In Adverse weaThEr (RADIATE), aiming to facilitate research on object detection, tracking and scene understanding using radar sensing for safe autonomous driving. RADIATE includes 3 hours of annotated radar images with more than 200K labelled road actors in total, on average about 4.6 instances per radar image. It covers 8 different categories of actors in a variety of weather conditions (e.g., sun, night, rain, fog and snow) and driving scenarios (e.g., parked, urban, motorway and suburban), representing different levels of challenge. To the best of our knowledge, this is the first public radar dataset which provides high-resolution radar images on public roads with a large amount of road actors labelled. The data collected in adverse weather, e.g., fog and snowfall, is unique. Some baseline results of radar based object detection and recognition are given to show that the use of radar data is promising for automotive applications in bad weather, where vision and LiDAR can fail. RADIATE also has stereo images, 32-channel LiDAR and GPS data, directed at other applications such as sensor fusion, localisation and mapping. The public dataset can be accessed at http://pro.hw.ac.uk/radiate/.
Given a simple request like Put a washed apple in the kitchen fridge, humans can reason in purely abstract terms by imagining action sequences and scoring their likelihood of success, prototypicality, and efficiency, all without moving a muscle. Once we see the kitchen in question, we can update our abstract plans to fit the scene. Embodied agents require the same abilities, but existing work does not yet provide the infrastructure necessary for both reasoning abstractly and executing concretely. We address this limitation by introducing ALFWorld, a simulator that enables agents to learn abstract, text based policies in TextWorld (C\^ot\'e et al., 2018) and then execute goals from the ALFRED benchmark (Shridhar et al., 2020) in a rich visual environment. ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions. In turn, as we demonstrate empirically, this fosters better agent generalization than training only in the visually grounded environment. BUTLER's simple, modular design factors the problem to allow researchers to focus on models for improving every piece of the pipeline (language understanding, planning, navigation, and visual scene understanding).
We address the challenging problem of semi-supervised learning in the context of multiple visual interpretations of the world by finding consensus in a graph of neural networks. Each graph node is a scene interpretation layer, while each edge is a deep net that transforms one layer at one node into another from a different node. During the supervised phase edge networks are trained independently. During the next unsupervised stage edge nets are trained on the pseudo-ground truth provided by consensus among multiple paths that reach the nets' start and end nodes. These paths act as ensemble teachers for any given edge and strong consensus is used for high-confidence supervisory signal. The unsupervised learning process is repeated over several generations, in which each edge becomes a "student" and also part of different ensemble "teachers" for training other students. By optimizing such consensus between different paths, the graph reaches consistency and robustness over multiple interpretations and generations, in the face of unknown labels. We give theoretical justifications of the proposed idea and validate it on a large dataset. We show how prediction of different representations such as depth, semantic segmentation, surface normals and pose from RGB input could be effectively learned through self-supervised consensus in our graph. We also compare to state-of-the-art methods for multi-task and semi-supervised learning and show superior performance.
To better understand scene images in the field of remote sensing, multi-label annotation of scene images is necessary. Moreover, to enhance the performance of deep learning models for dealing with semantic scene understanding tasks, it is vital to train them on large-scale annotated data. However, most existing datasets are annotated by a single label, which cannot describe the complex remote sensing images well because scene images might have multiple land cover classes. Few multi-label high spatial resolution remote sensing datasets have been developed to train deep learning models for multi-label based tasks, such as scene classification and image retrieval. To address this issue, in this paper, we construct a multi-label high spatial resolution remote sensing dataset named MLRSNet for semantic scene understanding with deep learning from the overhead perspective. It is composed of high-resolution optical satellite or aerial images. MLRSNet contains a total of 109,161 samples within 46 scene categories, and each image has at least one of 60 predefined labels. We have designed visual recognition tasks, including multi-label based image classification and image retrieval, in which a wide variety of deep learning approaches are evaluated with MLRSNet. The experimental results demonstrate that MLRSNet is a significant benchmark for future research, and it complements the current widely used datasets such as ImageNet, which fills gaps in multi-label image research. Furthermore, we will continue to expand the MLRSNet. MLRSNet and all related materials have been made publicly available at https://data.mendeley.com/datasets/7j9bv9vwsx/2 and https://github.com/cugbrs/MLRSNet.git.
Dense pixel-wise classification maps output by deep neural networks are of extreme importance for scene understanding. However, these maps are often partially inaccurate due to a variety of possible factors. Therefore, we propose to interactively refine them within a framework named DISCA (Deep Image Segmentation with Continual Adaptation). It consists of continually adapting a neural network to a target image using an interactive learning process with sparse user annotations as ground-truth. We show through experiments on three datasets using synthesized annotations the benefits of the approach, reaching an IoU improvement up to 4.7% for ten sampled clicks. Finally, we exhibit that our approach can be particularly rewarding when it is faced to additional issues such as domain adaptation.
An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly annotated datasets. However, publicly available datasets are either in relative small spatial scales or have limited semantic annotations due to the expensive cost of data acquisition and data annotation, which severely limits the development of fine-grained semantic understanding in the context of 3D point clouds. In this paper, we present an urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points, which is three times the number of labeled points than the existing largest photogrammetric point cloud dataset. Our dataset consists of large areas from three UK cities, covering about 7.6 km^2 of the city landscape. In the dataset, each 3D point is labeled as one of 13 semantic classes. We extensively evaluate the performance of state-of-the-art algorithms on our dataset and provide a comprehensive analysis of the results. In particular, we identify several key challenges towards urban-scale point cloud understanding. The dataset is available at https://github.com/QingyongHu/SensatUrban.
Semantic segmentation is a scene understanding task at the heart of safety-critical applications where robustness to corrupted inputs is essential. Implicit Background Estimation (IBE) has demonstrated to be a promising technique to improve the robustness to out-of-distribution inputs for semantic segmentation models for little to no cost. In this paper, we provide analysis comparing the structures learned as a result of optimization objectives that use Softmax, IBE, and Sigmoid in order to improve understanding their relationship to robustness. As a result of this analysis, we propose combining Sigmoid with IBE (SCrIBE) to improve robustness. Finally, we demonstrate that SCrIBE exhibits superior segmentation performance aggregated across all corruptions and severity levels with a mIOU of 42.1 compared to both IBE 40.3 and the Softmax Baseline 37.5.
Autonomous surgical procedures, in particular minimal invasive surgeries, are the next frontier for Artificial Intelligence research. However, the existing challenges include precise identification of the human anatomy and the surgical settings, and modeling the environment for training of an autonomous agent. To address the identification of human anatomy and the surgical settings, we propose a deep learning based semantic segmentation algorithm to identify and label the tissues and organs in the endoscopic video feed of the human torso region. We present an annotated dataset, m2caiSeg, created from endoscopic video feeds of real-world surgical procedures. Overall, the data consists of 307 images, each of which is annotated for the organs and different surgical instruments present in the scene. We propose and train a deep convolutional neural network for the semantic segmentation task. To cater for the low quantity of annotated data, we use unsupervised pre-training and data augmentation. The trained model is evaluated on an independent test set of the proposed dataset. We obtained a F1 score of 0.33 while using all the labeled categories for the semantic segmentation task. Secondly, we labeled all instruments into an 'Instruments' superclass to evaluate the model's performance on discerning the various organs and obtained a F1 score of 0.57. We propose a new dataset and a deep learning method for pixel level identification of various organs and instruments in a endoscopic surgical scene. Surgical scene understanding is one of the first steps towards automating surgical procedures.
In this paper, we introduce the MLM (Multiple Languages and Modalities) dataset - a new resource to train and evaluate multitask systems on samples in multiple modalities and three languages. The generation process and inclusion of semantic data provide a resource that further tests the ability for multitask systems to learn relationships between entities. The dataset is designed for researchers and developers who build applications that perform multiple tasks on data encountered on the web and in digital archives. A second version of MLM provides a geo-representative subset of the data with weighted samples for countries of the European Union. We demonstrate the value of the resource in developing novel applications in the digital humanities with a motivating use case and specify a benchmark set of tasks to retrieve modalities and locate entities in the dataset. Evaluation of baseline multitask and single task systems on the full and geo-representative versions of MLM demonstrate the challenges of generalising on diverse data. In addition to the digital humanities, we expect the resource to contribute to research in multimodal representation learning, location estimation, and scene understanding.
Learning on 3D scene-based point cloud has received extensive attention as its promising application in many fields, and well-annotated and multisource datasets can catalyze the development of those data-driven approaches. To facilitate the research of this area, we present a richly-annotated 3D point cloud dataset for multiple outdoor scene understanding tasks and also an effective learning framework for its hierarchical segmentation task. The dataset was generated via the photogrammetric processing on unmanned aerial vehicle (UAV) images of the National University of Singapore (NUS) campus, and has been point-wisely annotated with both hierarchical and instance-based labels. Based on it, we formulate a hierarchical learning problem for 3D point cloud segmentation and propose a measurement evaluating consistency across various hierarchies. To solve this problem, a two-stage method including multi-task (MT) learning and hierarchical ensemble (HE) with consistency consideration is proposed. Experimental results demonstrate the superiority of the proposed method and potential advantages of our hierarchical annotations. In addition, we benchmark results of semantic and instance segmentation, which is accessible online at https://3d.dataset.site with the dataset and all source codes.
Human-Object Interaction (HOI) detection is important to human-centric scene understanding tasks. Existing works tend to assume that the same verb has similar visual characteristics in different HOI categories, an approach that ignores the diverse semantic meanings of the verb. To address this issue, in this paper, we propose a novel Polysemy Deciphering Network (PD-Net) that decodes the visual polysemy of verbs for HOI detection in three distinct ways. First, we refine features for HOI detection to be polysemyaware through the use of two novel modules: namely, Language Prior-guided Channel Attention (LPCA) and Language Prior-based Feature Augmentation (LPFA). LPCA highlights important elements in human and object appearance features for each HOI category to be identified; moreover, LPFA augments human pose and spatial features for HOI detection using language priors, enabling the verb classifiers to receive language hints that reduce intra-class variation for the same verb. Second, we introduce a novel Polysemy-Aware Modal Fusion module (PAMF), which guides PD-Net to make decisions based on feature types deemed more important according to the language priors. Third, we propose to relieve the verb polysemy problem through sharing verb classifiers for semantically similar HOI categories. Furthermore, to expedite research on the verb polysemy problem, we build a new benchmark dataset named HOI-VerbPolysemy (HOIVP), which includes common verbs (predicates) that have diverse semantic meanings in the real world. Finally, through deciphering the visual polysemy of verbs, our approach is demonstrated to outperform state-of-the-art methods by significant margins on the HICO-DET, V-COCO, and HOI-VP databases. Code and data in this paper are available at https://github.com/MuchHair/PD-Net.
Human-object interaction(HOI) detection is a critical task in scene understanding. The goal is to infer the triplet <subject, predicate, object> in a scene. In this work, we note that the human pose itself as well as the relative spatial information of the human pose with respect to the target object can provide informative cues for HOI detection. We contribute a Pose-based Modular Network (PMN) which explores the absolute pose features and relative spatial pose features to improve HOI detection and is fully compatible with existing networks. Our module consists of a branch that first processes the relative spatial pose features of each joint independently. Another branch updates the absolute pose features via fully connected graph structures. The processed pose features are then fed into an action classifier. To evaluate our proposed method, we combine the module with the state-of-the-art model named VS-GATs and obtain significant improvement on two public benchmarks: V-COCO and HICO-DET, which shows its efficacy and flexibility. Code is available at \url{https://github.com/birlrobotics/PMN}.
A crucial task in scene understanding is 3D object detection, which aims to detect and localize the 3D bounding boxes of objects belonging to specific classes. Existing 3D object detectors heavily rely on annotated 3D bounding boxes during training, while these annotations could be expensive to obtain and only accessible in limited scenarios. Weakly supervised learning is a promising approach to reducing the annotation requirement, but existing weakly supervised object detectors are mostly for 2D detection rather than 3D. In this work, we propose VS3D, a framework for weakly supervised 3D object detection from point clouds without using any ground truth 3D bounding box for training. First, we introduce an unsupervised 3D proposal module that generates object proposals by leveraging normalized point cloud densities. Second, we present a cross-modal knowledge distillation strategy, where a convolutional neural network learns to predict the final results from the 3D object proposals by querying a teacher network pretrained on image datasets. Comprehensive experiments on the challenging KITTI dataset demonstrate the superior performance of our VS3D in diverse evaluation settings. The source code and pretrained models are publicly available at https://github.com/Zengyi-Qin/Weakly-Supervised-3D-Object-Detection.