Practical autonomous driving systems face two crucial challenges: memory constraints and domain gap issues. In this paper, we present a novel approach to learn domain adaptive knowledge in models with limited memory, thus bestowing the model with the ability to deal with these issues in a comprehensive manner. We term this as "Domain Adaptive Knowledge Distillation" and address the same in the context of unsupervised domain-adaptive semantic segmentation by proposing a multi-level distillation strategy to effectively distil knowledge at different levels. Further, we introduce a novel cross entropy loss that leverages pseudo labels from the teacher. These pseudo teacher labels play a multifaceted role towards: (i) knowledge distillation from the teacher network to the student network & (ii) serving as a proxy for the ground truth for target domain images, where the problem is completely unsupervised. We introduce four paradigms for distilling domain adaptive knowledge and carry out extensive experiments and ablation studies on real-to-real as well as synthetic-to-real scenarios. Our experiments demonstrate the profound success of our proposed method.
Harman International（哈曼国际）；University of Virginia（弗吉尼亚大学）
As the demand for enabling high-level autonomous driving has increased in recent years and visual perception is one of the critical features to enable fully autonomous driving, in this paper, we introduce an efficient approach for simultaneous object detection, depth estimation and pixel-level semantic segmentation using a shared convolutional architecture. The proposed network model, which we named Driving Scene Perception Network (DSPNet), uses multi-level feature maps and multi-task learning to improve the accuracy and efficiency of object detection, depth estimation and image segmentation …
Semantic segmentation of road scenes is one of the key technologies for realizing autonomous driving scene perception, and the effectiveness of deep Convolutional Neural Networks(CNNs) for this task has been demonstrated. State-of-art CNNs for semantic segmentation suffer from excessive computations as well as large-scale training data requirement. Inspired by the ideas of Fine-tuning-based Transfer Learning (FTT) and feature-based knowledge distillation, we propose a new knowledge distillation method for cross-domain knowledge transference and efficient data-insufficient network training, nam…
KAIST（韩国科学技术院）；MIT（麻省理工学院）；Lunit Inc.（卢尼特公司）；Microsoft Research Asia（微软亚洲研究院）
Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional sensing modality for free. In this work, we leverage the large-scale unlabeled yet naturally paired data for visual representation learning in the driving scenario. A representation is learned in an end-to-end self-supervised framework for predicting dense optical flow from a single frame with paired sensing data. We postulate that success on this task requires the network to le…
The Chinese University of Hong Kong（香港中文大学）；ShanghaiTech University（上海科技大学）；SenseTime Research（商汤科技研究院）
State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. The projection methods includes spherical projection, bird-eye view projection, etc. Although this process makes the point cloud suitable for the 2D CNN-based networks, it inevitably alters and abandons the 3D topology and geometric relations. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. In this work, we first perform an in-depth analysis for different repr…
Tsinghua University（清华大学）；University of Science and Technology, Beijing（北京科技大学）
Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process. For simple images that only include a few categories, researches based on image-level annotations have achieved acceptable performance. However, when facing complex scenes, since image contains a large amount of classes, it becomes difficult to learn visual appearance based on image tags. In this case, image-level annotations are not effective in providing information. Therefore, we set up a new task in which only one annotated pixel is provided for each category. B…
Feasibility of Indoor Frame-Wise Lidar Semantic Segmentation via Distillation from Visual Foundation Model
1 Department of Earth Observation Science, Faculty of Geo-Information Science；Earth Observation (ITC), University of Twente, 7522 NB Enschede, The Netherlands
Massachusetts Institute of Technology (MIT)（麻省理工学院）；Collaborative Safety Research Center, Toyota Motor North America（丰田北美汽车公司协作安全研究中心）
Semantic scene segmentation has primarily been addressed by forming representations of single images both with supervised and unsupervised methods. The problem of semantic segmentation in dynamic scenes has begun to recently receive attention with video object segmentation approaches. What is not known is how much extra information the temporal dynamics of the visual scene carries that is complimentary to the information available in the individual frames of the video. There is evidence that the human visual system can effectively perceive the scene from temporal dynamics information of the sc…
We focus on the very challenging task of semantic segmentation for autonomous driving system. It must deliver decent semantic segmentation result for traffic critical objects real-time. In this paper, we propose a very efficient yet powerful deep neural network for driving scene semantic segmentation termed as Driving Segmentation Network (DSNet). DSNet achieves state-of-the-art balance between accuracy and inference speed through efficient units and architecture design inspired by ShuffleNet V2 and ENet. More importantly, DSNet highlights classes most critical with driving decision making thr…
The University of Trento（特伦托大学）；The University of Sydney（悉尼大学）；The Chinese University of Hong Kong（香港中文大学）
Depth estimation and scene parsing are two particularly important tasks in visual scene understanding. In this paper we tackle the problem of simultaneous depth estimation and scene parsing in a joint CNN. The task can be typically treated as a deep multi-task learning problem [42]. Different from previous methods directly optimizing multiple tasks given the input training data, this paper proposes a novel multi-task guided prediction-and-distillation network (PAD-Net), which first predicts a set of intermediate auxiliary tasks ranging from low level to high level, and then the predictions fro…
In recent years, knowledge distillation (KD) has been widely used to derive efficient models. Through imitating a large teacher model, a lightweight student model can achieve comparable performance with more efficiency. However, most existing knowledge distillation methods are focused on classification tasks. Only a limited number of studies have applied knowledge distillation to object detection, especially in time-sensitive autonomous driving scenarios. In this paper, we propose Adaptive Instance Distillation (AID) to selectively impart teacher's knowledge to the student to improve the perfo…
Key Laboratory 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）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）
If an image tells a story, the image caption is the briefest narrator. Generally, a scene graph prefers to be an omniscient generalist, while the image caption is more willing to be a specialist, which outlines the gist. Lots of previous studies have found that a scene graph is not as practical as expected unless it can reduce the trivial contents and noises. In this respect, the image caption is a good tutor. To this end, we let the scene graph borrow the ability from the image caption so that it can be a specialist on the basis of remaining all-around, resulting in the so-called Topic Scene …
Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation
The Hong Kong Polytechnic University（香港理工大学）；Centre for Artificial Intelligence and Robotics, HKISI, CAS（中国科学院香港智能研究院人工智能与机器人中心）；State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）
Indoor scene semantic parsing from RGB images is very challenging due to occlusions, object distortion, and viewpoint variations. Going beyond prior works that leverage geometry information, typically paired depth maps, we present a new approach, a 3D-to-2D distillation framework, that enables us to leverage 3D features extracted from large-scale 3D data repository (e.g., ScanNet-v2) to enhance 2D features extracted from RGB images. Our work has three novel contributions. First, we distill 3D knowledge from a pretrained 3D network to supervise a 2D network to learn simulated 3D features from 2…
L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model
Institute of Cyber-Systems and Control, Zhejiang University（浙江大学网络系统与控制研究所）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；Zhejiang Guoli Security Technology Co., Ltd.（浙江国利安全科技有限公司）
Stanford University（斯坦福大学）；Toyota Research Institute（丰田研究院）
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance c…
The waterdrops on windshields during driving can cause severe visual obstructions, which may lead to car accidents. Meanwhile, the waterdrops can also degrade the performance of a computer vision system in autonomous driving. To address these issues, we propose an attention-based framework that fuses the spatio-temporal representations from multiple frames to restore visual information occluded by waterdrops. Due to the lack of training data for video waterdrop removal, we propose a large-scale synthetic dataset with simulated waterdrops in complex driving scenes on rainy days. To improve the …
The Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image. Although SGG has achieved remarkable progress over the last few years, almost all existing SGG models follow the same training paradigm: they treat both object and predicate classification in SGG as a single-label classification problem, and the ground-truths are one-hot target labels. However, this prevalent training paradigm has overlooked two characteristics of current SGG datasets: 1) For positive samples, some specific subject-object instances may have multiple re…
Generating Multimodal Driving Scenes via Next-Scene Prediction
School of Software Engineering, XJTU（西安交通大学软件学院）；Horizon Robotics（地平线机器人）；School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）；University of Chinese Academy of Sciences（中国科学院大学）
4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling
University of Toronto（多伦多大学）；Vector Institute（矢量研究所）；KAUST（阿卜杜拉国王科技大学）；Snap Inc.（Snap公司）；Stanford University（斯坦福大学）；University of Michigan（密歇根大学）；SFU（西蒙菲莎大学）；Google（谷歌公司）
InsightDrive: Insight Scene Representation for End-to-End Autonomous Driving
College of Surveying and Geo-informatics, Tongji University（同济大学测绘与地理信息学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Computer Science, Wuhan University（武汉大学计算机学院）；The School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Great Wall Motor（长城汽车）；IAIR, Xi’an Jiaotong University（西安交通大学IAIR）
Boston University（波士顿大学）；Honda Research Institute USA（美国本田研究院）
Driving Scene understanding is a key ingredient for intelligent transportation systems. To achieve systems that can operate in a complex physical and social environment, they need to understand and learn how humans drive and interact with traffic scenes. We present the Honda Research Institute Driving Dataset (HDD), a challenging dataset to enable research on learning driver behavior in real-life environments. The dataset includes 104 hours of real human driving in the San Francisco Bay Area collected using an instrumented vehicle equipped with different sensors. We provide a detailed analysis…
