This repository has been archived by the owner on Feb 11, 2023. It is now read-only.
New submissions for Fri, 29 Jul 22 #205
Assignees
Comments
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
New submissions for Fri, 29 Jul 22
Keyword: SLAM
There is no result
Keyword: odometry
There is no result
Keyword: livox
There is no result
Keyword: loam
There is no result
Keyword: lidar
A Probabilistic Framework for Estimating the Risk of Pedestrian-Vehicle Conflicts at Intersections
Pedestrian safety has become an important research topic among various studies due to the increased number of pedestrian-involved crashes. To evaluate pedestrian safety proactively, surrogate safety measures (SSMs) have been widely used in traffic conflict-based studies as they do not require historical crashes as inputs. However, most existing SSMs were developed based on the assumption that road users would maintain constant velocity and direction. Risk estimations based on this assumption are less unstable, more likely to be exaggerated, and unable to capture the evasive maneuvers of drivers. Considering the limitations among existing SSMs, this study proposes a probabilistic framework for estimating the risk of pedestrian-vehicle conflicts at intersections. The proposed framework loosen restrictions of constant speed by predicting trajectories using a Gaussian Process Regression and accounts for the different possible driver maneuvers with a Random Forest model. Real-world LiDAR data collected at an intersection was used to evaluate the performance of the proposed framework. The newly developed framework is able to identify all pedestrian-vehicle conflicts. Compared to the Time-to-Collision, the proposed framework provides a more stable risk estimation and captures the evasive maneuvers of vehicles. Moreover, the proposed framework does not require expensive computation resources, which makes it an ideal choice for real-time proactive pedestrian safety solutions at intersections.
Keyword: loop detection
There is no result
Keyword: nerf
There is no result
Keyword: mapping
Exploiting and Defending Against the Approximate Linearity of Apple's NeuralHash
Perceptual hashes map images with identical semantic content to the same
Depth Field Networks for Generalizable Multi-view Scene Representation
Modern 3D computer vision leverages learning to boost geometric reasoning, mapping image data to classical structures such as cost volumes or epipolar constraints to improve matching. These architectures are specialized according to the particular problem, and thus require significant task-specific tuning, often leading to poor domain generalization performance. Recently, generalist Transformer architectures have achieved impressive results in tasks such as optical flow and depth estimation by encoding geometric priors as inputs rather than as enforced constraints. In this paper, we extend this idea and propose to learn an implicit, multi-view consistent scene representation, introducing a series of 3D data augmentation techniques as a geometric inductive prior to increase view diversity. We also show that introducing view synthesis as an auxiliary task further improves depth estimation. Our Depth Field Networks (DeFiNe) achieve state-of-the-art results in stereo and video depth estimation without explicit geometric constraints, and improve on zero-shot domain generalization by a wide margin.
Initialization and Alignment for Adversarial Texture Optimization
While recovery of geometry from image and video data has received a lot of attention in computer vision, methods to capture the texture for a given geometry are less mature. Specifically, classical methods for texture generation often assume clean geometry and reasonably well-aligned image data. While very recent methods, e.g., adversarial texture optimization, better handle lower-quality data obtained from hand-held devices, we find them to still struggle frequently. To improve robustness, particularly of recent adversarial texture optimization, we develop an explicit initialization and an alignment procedure. It deals with complex geometry due to a robust mapping of the geometry to the texture map and a hard-assignment-based initialization. It deals with misalignment of geometry and images by integrating fast image-alignment into the texture refinement optimization. We demonstrate efficacy of our texture generation on a dataset of 11 scenes with a total of 2807 frames, observing 7.8% and 11.1% relative improvements regarding perceptual and sharpness measurements.
Keyword: localization
Robust Self-Tuning Data Association for Geo-Referencing Using Lane Markings
Localization in aerial imagery-based maps offers many advantages, such as global consistency, geo-referenced maps, and the availability of publicly accessible data. However, the landmarks that can be observed from both aerial imagery and on-board sensors is limited. This leads to ambiguities or aliasing during the data association. Building upon a highly informative representation (that allows efficient data association), this paper presents a complete pipeline for resolving these ambiguities. Its core is a robust self-tuning data association that adapts the search area depending on the entropy of the measurements. Additionally, to smooth the final result, we adjust the information matrix for the associated data as a function of the relative transform produced by the data association process. We evaluate our method on real data from urban and rural scenarios around the city of Karlsruhe in Germany. We compare state-of-the-art outlier mitigation methods with our self-tuning approach, demonstrating a considerable improvement, especially for outer-urban scenarios.
WiVelo: Fine-grained Walking Velocity Estimation for Wi-Fi Passive Tracking
Passive human tracking via Wi-Fi has been researched broadly in the past decade. Besides straight-forward anchor point localization, velocity is another vital sign adopted by the existing approaches to infer user trajectory. However, state-of-the-art Wi-Fi velocity estimation relies on Doppler-Frequency-Shift (DFS) which suffers from the inevitable signal noise incurring unbounded velocity errors, further degrading the tracking accuracy. In this paper, we present WiVelo\footnote{Code&datasets are available at \textit{https://github.com/liecn/WiVelo\_SECON22}} that explores new spatial-temporal signal correlation features observed from different antennas to achieve accurate velocity estimation. First, we use subcarrier shift distribution (SSD) extracted from channel state information (CSI) to define two correlation features for direction and speed estimation, separately. Then, we design a mesh model calculated by the antennas' locations to enable a fine-grained velocity estimation with bounded direction error. Finally, with the continuously estimated velocity, we develop an end-to-end trajectory recovery algorithm to mitigate velocity outliers with the property of walking velocity continuity. We implement WiVelo on commodity Wi-Fi hardware and extensively evaluate its tracking accuracy in various environments. The experimental results show our median and 90% tracking errors are 0.47
m and 1.06m, which are half and a quarter of state-of-the-arts.Humans disagree with the IoU for measuring object detector localization error
The localization quality of automatic object detectors is typically evaluated by the Intersection over Union (IoU) score. In this work, we show that humans have a different view on localization quality. To evaluate this, we conduct a survey with more than 70 participants. Results show that for localization errors with the exact same IoU score, humans might not consider that these errors are equal, and express a preference. Our work is the first to evaluate IoU with humans and makes it clear that relying on IoU scores alone to evaluate localization errors might not be sufficient.
Keyword: transformer
Remote Medication Status Prediction for Individuals with Parkinson's Disease using Time-series Data from Smartphones
Medication for neurological diseases such as the Parkinson's disease usually happens remotely at home, away from hospitals. Such out-of-lab environments pose challenges in collecting timely and accurate health status data using the limited professional care devices for health condition analysis, medication adherence measurement and future dose or treatment planning. Individual differences in behavioral signals collected from wearable sensors also lead to difficulties in adopting current general machine learning analysis pipelines. To address these challenges, we present a method for predicting medication status of Parkinson's disease patients using the public mPower dataset, which contains 62,182 remote multi-modal test records collected on smartphones from 487 patients. The proposed method shows promising results in predicting three medication status objectively: Before Medication (AUC=0.95), After Medication (AUC=0.958), and Another Time (AUC=0.976) by examining patient-wise historical records with the attention weights learned through a Transformer model. We believe our method provides an innovative way for personalized remote health sensing in a timely and objective fashion which could benefit a broad range of similar applications.
AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
Today's Mixed Reality head-mounted displays track the user's head pose in world space as well as the user's hands for interaction in both Augmented Reality and Virtual Reality scenarios. While this is adequate to support user input, it unfortunately limits users' virtual representations to just their upper bodies. Current systems thus resort to floating avatars, whose limitation is particularly evident in collaborative settings. To estimate full-body poses from the sparse input sources, prior work has incorporated additional trackers and sensors at the pelvis or lower body, which increases setup complexity and limits practical application in mobile settings. In this paper, we present AvatarPoser, the first learning-based method that predicts full-body poses in world coordinates using only motion input from the user's head and hands. Our method builds on a Transformer encoder to extract deep features from the input signals and decouples global motion from the learned local joint orientations to guide pose estimation. To obtain accurate full-body motions that resemble motion capture animations, we refine the arm joints' positions using an optimization routine with inverse kinematics to match the original tracking input. In our evaluation, AvatarPoser achieved new state-of-the-art results in evaluations on large motion capture datasets (AMASS). At the same time, our method's inference speed supports real-time operation, providing a practical interface to support holistic avatar control and representation for Metaverse applications.
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers
Transformer encoder architectures have recently achieved state-of-the-art results on monocular 3D human mesh reconstruction, but they require a substantial number of parameters and expensive computations. Due to the large memory overhead and slow inference speed, it is difficult to deploy such models for practical use. In this paper, we propose a novel transformer encoder-decoder architecture for 3D human mesh reconstruction from a single image, called FastMETRO. We identify the performance bottleneck in the encoder-based transformers is caused by the token design which introduces high complexity interactions among input tokens. We disentangle the interactions via an encoder-decoder architecture, which allows our model to demand much fewer parameters and shorter inference time. In addition, we impose the prior knowledge of human body's morphological relationship via attention masking and mesh upsampling operations, which leads to faster convergence with higher accuracy. Our FastMETRO improves the Pareto-front of accuracy and efficiency, and clearly outperforms image-based methods on Human3.6M and 3DPW. Furthermore, we validate its generalizability on FreiHAND.
Dive into Machine Learning Algorithms for Influenza Virus Host Prediction with Hemagglutinin Sequences
Influenza viruses mutate rapidly and can pose a threat to public health, especially to those in vulnerable groups. Throughout history, influenza A viruses have caused pandemics between different species. It is important to identify the origin of a virus in order to prevent the spread of an outbreak. Recently, there has been increasing interest in using machine learning algorithms to provide fast and accurate predictions for viral sequences. In this study, real testing data sets and a variety of evaluation metrics were used to evaluate machine learning algorithms at different taxonomic levels. As hemagglutinin is the major protein in the immune response, only hemagglutinin sequences were used and represented by position-specific scoring matrix and word embedding. The results suggest that the 5-grams-transformer neural network is the most effective algorithm for predicting viral sequence origins, with approximately 99.54% AUCPR, 98.01% F1 score and 96.60% MCC at a higher classification level, and approximately 94.74% AUCPR, 87.41% F1 score and 80.79% MCC at a lower classification level.
DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer
Real-world image denoising is a practical image restoration problem that aims to obtain clean images from in-the-wild noisy input. Recently, Vision Transformer (ViT) exhibits a strong ability to capture long-range dependencies and many researchers attempt to apply ViT to image denoising tasks. However, real-world image is an isolated frame that makes the ViT build the long-range dependencies on the internal patches, which divides images into patches and disarranges the noise pattern and gradient continuity. In this article, we propose to resolve this issue by using a continuous Wavelet Sliding-Transformer that builds frequency correspondence under real-world scenes, called DnSwin. Specifically, we first extract the bottom features from noisy input images by using a CNN encoder. The key to DnSwin is to separate high-frequency and low-frequency information from the features and build frequency dependencies. To this end, we propose Wavelet Sliding-Window Transformer that utilizes discrete wavelet transform, self-attention and inverse discrete wavelet transform to extract deep features. Finally, we reconstruct the deep features into denoised images using a CNN decoder. Both quantitative and qualitative evaluations on real-world denoising benchmarks demonstrate that the proposed DnSwin performs favorably against the state-of-the-art methods.
Neural Architecture Search on Efficient Transformers and Beyond
Recently, numerous efficient Transformers have been proposed to reduce the quadratic computational complexity of standard Transformers caused by the Softmax attention. However, most of them simply swap Softmax with an efficient attention mechanism without considering the customized architectures specially for the efficient attention. In this paper, we argue that the handcrafted vanilla Transformer architectures for Softmax attention may not be suitable for efficient Transformers. To address this issue, we propose a new framework to find optimal architectures for efficient Transformers with the neural architecture search (NAS) technique. The proposed method is validated on popular machine translation and image classification tasks. We observe that the optimal architecture of the efficient Transformer has the reduced computation compared with that of the standard Transformer, but the general accuracy is less comparable. It indicates that the Softmax attention and efficient attention have their own distinctions but neither of them can simultaneously balance the accuracy and efficiency well. This motivates us to mix the two types of attention to reduce the performance imbalance. Besides the search spaces that commonly used in existing NAS Transformer approaches, we propose a new search space that allows the NAS algorithm to automatically search the attention variants along with architectures. Extensive experiments on WMT' 14 En-De and CIFAR-10 demonstrate that our searched architecture maintains comparable accuracy to the standard Transformer with notably improved computational efficiency.
Video Mask Transfiner for High-Quality Video Instance Segmentation
While Video Instance Segmentation (VIS) has seen rapid progress, current approaches struggle to predict high-quality masks with accurate boundary details. Moreover, the predicted segmentations often fluctuate over time, suggesting that temporal consistency cues are neglected or not fully utilized. In this paper, we set out to tackle these issues, with the aim of achieving highly detailed and more temporally stable mask predictions for VIS. We first propose the Video Mask Transfiner (VMT) method, capable of leveraging fine-grained high-resolution features thanks to a highly efficient video transformer structure. Our VMT detects and groups sparse error-prone spatio-temporal regions of each tracklet in the video segment, which are then refined using both local and instance-level cues. Second, we identify that the coarse boundary annotations of the popular YouTube-VIS dataset constitute a major limiting factor. Based on our VMT architecture, we therefore design an automated annotation refinement approach by iterative training and self-correction. To benchmark high-quality mask predictions for VIS, we introduce the HQ-YTVIS dataset, consisting of a manually re-annotated test set and our automatically refined training data. We compare VMT with the most recent state-of-the-art methods on the HQ-YTVIS, as well as the Youtube-VIS, OVIS and BDD100K MOTS benchmarks. Experimental results clearly demonstrate the efficacy and effectiveness of our method on segmenting complex and dynamic objects, by capturing precise details.
Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer
Large-scale deployment of autonomous vehicles has been continually delayed due to safety concerns. On the one hand, comprehensive scene understanding is indispensable, a lack of which would result in vulnerability to rare but complex traffic situations, such as the sudden emergence of unknown objects. However, reasoning from a global context requires access to sensors of multiple types and adequate fusion of multi-modal sensor signals, which is difficult to achieve. On the other hand, the lack of interpretability in learning models also hampers the safety with unverifiable failure causes. In this paper, we propose a safety-enhanced autonomous driving framework, named Interpretable Sensor Fusion Transformer(InterFuser), to fully process and fuse information from multi-modal multi-view sensors for achieving comprehensive scene understanding and adversarial event detection. Besides, intermediate interpretable features are generated from our framework, which provide more semantics and are exploited to better constrain actions to be within the safe sets. We conducted extensive experiments on CARLA benchmarks, where our model outperforms prior methods, ranking the first on the public CARLA Leaderboard.
Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion
The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection. However, DETR suffers from slow training convergence, which hinders its applicability to various detection tasks. We observe that DETR's slow convergence is largely attributed to the difficulty in matching object queries to relevant regions due to the unaligned semantics between object queries and encoded image features. With this observation, we design Semantic-Aligned-Matching DETR++ (SAM-DETR++) to accelerate DETR's convergence and improve detection performance. The core of SAM-DETR++ is a plug-and-play module that projects object queries and encoded image features into the same feature embedding space, where each object query can be easily matched to relevant regions with similar semantics. Besides, SAM-DETR++ searches for multiple representative keypoints and exploits their features for semantic-aligned matching with enhanced representation capacity. Furthermore, SAM-DETR++ can effectively fuse multi-scale features in a coarse-to-fine manner on the basis of the designed semantic-aligned matching. Extensive experiments show that the proposed SAM-DETR++ achieves superior convergence speed and competitive detection accuracy. Additionally, as a plug-and-play method, SAM-DETR++ can complement existing DETR convergence solutions with even better performance, achieving 44.8% AP with merely 12 training epochs and 49.1% AP with 50 training epochs on COCO val2017 with ResNet-50. Codes are available at https://github.com/ZhangGongjie/SAM-DETR .
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions
Recent progress in vision Transformers exhibits great success in various tasks driven by the new spatial modeling mechanism based on dot-product self-attention. In this paper, we show that the key ingredients behind the vision Transformers, namely input-adaptive, long-range and high-order spatial interactions, can also be efficiently implemented with a convolution-based framework. We present the Recursive Gated Convolution ($\textit{g}^\textit{n}$Conv) that performs high-order spatial interactions with gated convolutions and recursive designs. The new operation is highly flexible and customizable, which is compatible with various variants of convolution and extends the two-order interactions in self-attention to arbitrary orders without introducing significant extra computation. $\textit{g}^\textit{n}$Conv can serve as a plug-and-play module to improve various vision Transformers and convolution-based models. Based on the operation, we construct a new family of generic vision backbones named HorNet. Extensive experiments on ImageNet classification, COCO object detection and ADE20K semantic segmentation show HorNet outperform Swin Transformers and ConvNeXt by a significant margin with similar overall architecture and training configurations. HorNet also shows favorable scalability to more training data and a larger model size. Apart from the effectiveness in visual encoders, we also show $\textit{g}^\textit{n}$Conv can be applied to task-specific decoders and consistently improve dense prediction performance with less computation. Our results demonstrate that $\textit{g}^\textit{n}$Conv can be a new basic module for visual modeling that effectively combines the merits of both vision Transformers and CNNs. Code is available at https://github.com/raoyongming/HorNet
Depth Field Networks for Generalizable Multi-view Scene Representation
Modern 3D computer vision leverages learning to boost geometric reasoning, mapping image data to classical structures such as cost volumes or epipolar constraints to improve matching. These architectures are specialized according to the particular problem, and thus require significant task-specific tuning, often leading to poor domain generalization performance. Recently, generalist Transformer architectures have achieved impressive results in tasks such as optical flow and depth estimation by encoding geometric priors as inputs rather than as enforced constraints. In this paper, we extend this idea and propose to learn an implicit, multi-view consistent scene representation, introducing a series of 3D data augmentation techniques as a geometric inductive prior to increase view diversity. We also show that introducing view synthesis as an auxiliary task further improves depth estimation. Our Depth Field Networks (DeFiNe) achieve state-of-the-art results in stereo and video depth estimation without explicit geometric constraints, and improve on zero-shot domain generalization by a wide margin.
Keyword: autonomous driving
Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer
Large-scale deployment of autonomous vehicles has been continually delayed due to safety concerns. On the one hand, comprehensive scene understanding is indispensable, a lack of which would result in vulnerability to rare but complex traffic situations, such as the sudden emergence of unknown objects. However, reasoning from a global context requires access to sensors of multiple types and adequate fusion of multi-modal sensor signals, which is difficult to achieve. On the other hand, the lack of interpretability in learning models also hampers the safety with unverifiable failure causes. In this paper, we propose a safety-enhanced autonomous driving framework, named Interpretable Sensor Fusion Transformer(InterFuser), to fully process and fuse information from multi-modal multi-view sensors for achieving comprehensive scene understanding and adversarial event detection. Besides, intermediate interpretable features are generated from our framework, which provide more semantics and are exploited to better constrain actions to be within the safe sets. We conducted extensive experiments on CARLA benchmarks, where our model outperforms prior methods, ranking the first on the public CARLA Leaderboard.
Ever heard of ethical AI? Investigating the salience of ethical AI issues among the German population
Building and implementing ethical AI systems that benefit the whole society is cost-intensive and a multi-faceted task fraught with potential problems. While computer science focuses mostly on the technical questions to mitigate social issues, social science addresses citizens' perceptions to elucidate social and political demands that influence the societal implementation of AI systems. Thus, in this study, we explore the salience of AI issues in the public with an emphasis on ethical criteria to investigate whether it is likely that ethical AI is actively requested by the population. Between May 2020 and April 2021, we conducted 15 surveys asking the German population about the most important AI-related issues (total of N=14,988 respondents). Our results show that the majority of respondents were not concerned with AI at all. However, it can be seen that general interest in AI and a higher educational level are predictive of some engagement with AI. Among those, who reported having thought about AI, specific applications (e.g., autonomous driving) were by far the most mentioned topics. Ethical issues are voiced only by a small subset of citizens with fairness, accountability, and transparency being the least mentioned ones. These have been identified in several ethical guidelines (including the EU Commission's proposal) as key elements for the development of ethical AI. The salience of ethical issues affects the behavioral intentions of citizens in the way that they 1) tend to avoid AI technology and 2) engage in public discussions about AI. We conclude that the low level of ethical implications may pose a serious problem for the actual implementation of ethical AI for the Common Good and emphasize that those who are presumably most affected by ethical issues of AI are especially unaware of ethical risks. Yet, once ethical AI is top of the mind, there is some potential for activism.
The text was updated successfully, but these errors were encountered: