PyTorchKR Papers

최신 논문

총 10,566편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2209.07061

PROB-SLAM: Real-time Visual SLAM Based on Probabilistic Graph Optimization

Traditional SLAM algorithms are typically based on artificial features, which lack high-level information. By introducing semantic information, SLAM can own higher stability and robustness rather than purely hand-crafted features. However, the high uncertainty of semantic detection networks prohibits the practical functionality of high-level information. To solve the uncertainty property introduced by semantics, this paper proposed a novel probability map based on the Gaussian distribution assumption. This map transforms the semantic binary object detection into probability results, which help establish a probabilistic data association between artificial features and semantic info. Through our algorithm, the higher confidence will be given higher weights in each update step while the edge of the detection area will be endowed with lower confidence. Then the uncertainty is undermined and has less effect on nonlinear optimization. The experiments are carried out in the TUM RGBD dataset, results show that our system improves ORB-SLAM2 by about 15% in indoor environments' errors. We have demonstrated that the method can be successfully applied to environments containing dynamic objects.

arXiv:2209.07419

FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection

Promising complementarity exists between the texture features of color images and the geometric information of LiDAR point clouds. However, there still present many challenges for efficient and robust feature fusion in the field of 3D object detection. In this paper, first, unstructured 3D point clouds are filled in the 2D plane and 3D point cloud features are extracted faster using projection-aware convolution layers. Further, the corresponding indexes between different sensor signals are established in advance in the data preprocessing, which enables faster cross-modal feature fusion. To address LiDAR points and image pixels misalignment problems, two new plug-and-play fusion modules, LiCamFuse and BiLiCamFuse, are proposed. In LiCamFuse, soft query weights with perceiving the Euclidean distance of bimodal features are proposed. In BiLiCamFuse, the fusion module with dual attention is proposed to deeply correlate the geometric and textural features of the scene. The quantitative results on the KITTI dataset demonstrate that the proposed method achieves better feature-level fusion. In addition, the proposed network shows a shorter running time compared to existing methods.

arXiv:2209.07042

Efficient Perception, Planning, and Control Algorithm for Vision-Based Automated Vehicles

Autonomous vehicles have limited computational resources and thus require efficient control systems. The cost and size of sensors have limited the development of self-driving cars. To overcome these restrictions, this study proposes an efficient framework for the operation of vision-based automatic vehicles; the framework requires only a monocular camera and a few inexpensive radars. The proposed algorithm comprises a multi-task UNet (MTUNet) network for extracting image features and constrained iterative linear quadratic regulator (CILQR) and vision predictive control (VPC) modules for rapid motion planning and control. MTUNet is designed to simultaneously solve lane line segmentation, the ego vehicle's heading angle regression, road type classification, and traffic object detection tasks at approximately 40 FPS for 228 x 228 pixel RGB input images. The CILQR controllers then use the MTUNet outputs and radar data as inputs to produce driving commands for lateral and longitudinal vehicle guidance within only 1 ms. In particular, the VPC algorithm is included to reduce steering command latency to below actuator latency, preventing performance degradation during tight turns. The VPC algorithm uses road curvature data from MTUNet to estimate the appropriate correction for the current steering angle at a look-ahead point to adjust the turning amount. The inclusion of the VPC algorithm in a VPC-CILQR controller leads to higher performance on curvy roads than the use of CILQR alone. Our experiments demonstrate that the proposed autonomous driving system, which does not require high-definition maps, can be applied in current autonomous vehicles.

arXiv:2209.06641

CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection

Existing deep learning-based 3D object detectors typically rely on the appearance of individual objects and do not explicitly pay attention to the rich contextual information of the scene. In this work, we propose Contextualized Multi-Stage Refinement for 3D Object Detection (CMR3D) framework, which takes a 3D scene as input and strives to explicitly integrate useful contextual information of the scene at multiple levels to predict a set of object bounding-boxes along with their corresponding semantic labels. To this end, we propose to utilize a context enhancement network that captures the contextual information at different levels of granularity followed by a multi-stage refinement module to progressively refine the box positions and class predictions. Extensive experiments on the large-scale ScanNetV2 benchmark reveal the benefits of our proposed method, leading to an absolute improvement of 2.0% over the baseline. In addition to 3D object detection, we investigate the effectiveness of our CMR3D framework for the problem of 3D object counting. Our source code will be publicly released.

arXiv:2209.06584

One-Shot Doc Snippet Detection: Powering Search in Document Beyond Text

Active consumption of digital documents has yielded scope for research in various applications, including search. Traditionally, searching within a document has been cast as a text matching problem ignoring the rich layout and visual cues commonly present in structured documents, forms, etc. To that end, we ask a mostly unexplored question: "Can we search for other similar snippets present in a target document page given a single query instance of a document snippet?". We propose MONOMER to solve this as a one-shot snippet detection task. MONOMER fuses context from visual, textual, and spatial modalities of snippets and documents to find query snippet in target documents. We conduct extensive ablations and experiments showing MONOMER outperforms several baselines from one-shot object detection (BHRL), template matching, and document understanding (LayoutLMv3). Due to the scarcity of relevant data for the task at hand, we train MONOMER on programmatically generated data having many visually similar query snippets and target document pairs from two datasets - Flamingo Forms and PubLayNet. We also do a human study to validate the generated data.

arXiv:2209.06399

A Survey on Evolutionary Computation for Computer Vision and Image Analysis: Past, Present, and Future Trends

Computer vision (CV) is a big and important field in artificial intelligence covering a wide range of applications. Image analysis is a major task in CV aiming to extract, analyse and understand the visual content of images. However, image-related tasks are very challenging due to many factors, e.g., high variations across images, high dimensionality, domain expertise requirement, and image distortions. Evolutionary computation (EC) approaches have been widely used for image analysis with significant achievement. However, there is no comprehensive survey of existing EC approaches to image analysis. To fill this gap, this paper provides a comprehensive survey covering all essential EC approaches to important image analysis tasks including edge detection, image segmentation, image feature analysis, image classification, object detection, and others. This survey aims to provide a better understanding of evolutionary computer vision (ECV) by discussing the contributions of different approaches and exploring how and why EC is used for CV and image analysis. The applications, challenges, issues, and trends associated to this research field are also discussed and summarised to provide further guidelines and opportunities for future research.

arXiv:2209.06535

CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer

Camera and radar sensors have significant advantages in cost, reliability, and maintenance compared to LiDAR. Existing fusion methods often fuse the outputs of single modalities at the result-level, called the late fusion strategy. This can benefit from using off-the-shelf single sensor detection algorithms, but late fusion cannot fully exploit the complementary properties of sensors, thus having limited performance despite the huge potential of camera-radar fusion. Here we propose a novel proposal-level early fusion approach that effectively exploits both spatial and contextual properties of camera and radar for 3D object detection. Our fusion framework first associates image proposal with radar points in the polar coordinate system to efficiently handle the discrepancy between the coordinate system and spatial properties. Using this as a first stage, following consecutive cross-attention based feature fusion layers adaptively exchange spatio-contextual information between camera and radar, leading to a robust and attentive fusion. Our camera-radar fusion approach achieves the state-of-the-art 41.1% mAP and 52.3% NDS on the nuScenes test set, which is 8.7 and 10.8 points higher than the camera-only baseline, as well as yielding competitive performance on the LiDAR method.

arXiv:2209.06407공식 코드 · Papers with Code

Viewer-Centred Surface Completion for Unsupervised Domain Adaptation in 3D Object Detection

Every autonomous driving dataset has a different configuration of sensors, originating from distinct geographic regions and covering various scenarios. As a result, 3D detectors tend to overfit the datasets they are trained on. This causes a drastic decrease in accuracy when the detectors are trained on one dataset and tested on another. We observe that lidar scan pattern differences form a large component of this reduction in performance. We address this in our approach, SEE-VCN, by designing a novel viewer-centred surface completion network (VCN) to complete the surfaces of objects of interest within an unsupervised domain adaptation framework, SEE. With SEE-VCN, we obtain a unified representation of objects across datasets, allowing the network to focus on learning geometry, rather than overfitting on scan patterns. By adopting a domain-invariant representation, SEE-VCN can be classed as a multi-target domain adaptation approach where no annotations or re-training is required to obtain 3D detections for new scan patterns. Through extensive experiments, we show that our approach outperforms previous domain adaptation methods in multiple domain adaptation settings. Our code and data are available at https://github.com/darrenjkt/SEE-VCN.

arXiv:2209.05946공식 코드 · Papers with Code

OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network

The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision. This work introduces OmDet, a novel language-aware object detection architecture, and an innovative training mechanism that harnesses continual learning and multi-dataset vision-language pre-training. Leveraging natural language as a universal knowledge representation, OmDet accumulates a "visual vocabulary" from diverse datasets, unifying the task as a language-conditioned detection framework. Our multimodal detection network (MDN) overcomes the challenges of multi-dataset joint training and generalizes to numerous training datasets without manual label taxonomy merging. We demonstrate superior performance of OmDet over strong baselines in object detection in the wild, open-vocabulary detection, and phrase grounding, achieving state-of-the-art results. Ablation studies reveal the impact of scaling the pre-training visual vocabulary, indicating a promising direction for further expansion to larger datasets. The effectiveness of our deep fusion approach is underscored by its ability to learn jointly from multiple datasets, enhancing performance through knowledge sharing.

arXiv:2209.05687공식 코드 · Papers with Code

PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers

Data-free quantization can potentially address data privacy and security concerns in model compression, and thus has been widely investigated. Recently, PSAQ-ViT designs a relative value metric, patch similarity, to generate data from pre-trained vision transformers (ViTs), achieving the first attempt at data-free quantization for ViTs. In this paper, we propose PSAQ-ViT V2, a more accurate and general data-free quantization framework for ViTs, built on top of PSAQ-ViT. More specifically, following the patch similarity metric in PSAQ-ViT, we introduce an adaptive teacher-student strategy, which facilitates the constant cyclic evolution of the generated samples and the quantized model (student) in a competitive and interactive fashion under the supervision of the full-precision model (teacher), thus significantly improving the accuracy of the quantized model. Moreover, without the auxiliary category guidance, we employ the task- and model-independent prior information, making the general-purpose scheme compatible with a broad range of vision tasks and models. Extensive experiments are conducted on various models on image classification, object detection, and semantic segmentation tasks, and PSAQ-ViT V2, with the naive quantization strategy and without access to real-world data, consistently achieves competitive results, showing potential as a powerful baseline on data-free quantization for ViTs. For instance, with Swin-S as the (backbone) model, 8-bit quantization reaches 82.13 top-1 accuracy on ImageNet, 50.9 box AP and 44.1 mask AP on COCO, and 47.2 mIoU on ADE20K. We hope that accurate and general PSAQ-ViT V2 can serve as a potential and practice solution in real-world applications involving sensitive data. Code is released and merged at: https://github.com/zkkli/PSAQ-ViT.

arXiv:2209.05654

ComplETR: Reducing the cost of annotations for object detection in dense scenes with vision transformers

Annotating bounding boxes for object detection is expensive, time-consuming, and error-prone. In this work, we propose a DETR based framework called ComplETR that is designed to explicitly complete missing annotations in partially annotated dense scene datasets. This reduces the need to annotate every object instance in the scene thereby reducing annotation cost. ComplETR augments object queries in DETR decoder with patch information of objects in the image. Combined with a matching loss, it can effectively find objects that are similar to the input patch and complete the missing annotations. We show that our framework outperforms the state-of-the-art methods such as Soft Sampling and Unbiased Teacher by itself, while at the same time can be used in conjunction with these methods to further improve their performance. Our framework is also agnostic to the choice of the downstream object detectors; we show performance improvement for several popular detectors such as Faster R-CNN, Cascade R-CNN, CenterNet2, and Deformable DETR on multiple dense scene datasets.

arXiv:2209.05588공식 코드 · Papers with Code

CenterFormer: Center-based Transformer for 3D Object Detection

Query-based transformer has shown great potential in constructing long-range attention in many image-domain tasks, but has rarely been considered in LiDAR-based 3D object detection due to the overwhelming size of the point cloud data. In this paper, we propose CenterFormer, a center-based transformer network for 3D object detection. CenterFormer first uses a center heatmap to select center candidates on top of a standard voxel-based point cloud encoder. It then uses the feature of the center candidate as the query embedding in the transformer. To further aggregate features from multiple frames, we design an approach to fuse features through cross-attention. Lastly, regression heads are added to predict the bounding box on the output center feature representation. Our design reduces the convergence difficulty and computational complexity of the transformer structure. The results show significant improvements over the strong baseline of anchor-free object detection networks. CenterFormer achieves state-of-the-art performance for a single model on the Waymo Open Dataset, with 73.7% mAPH on the validation set and 75.6% mAPH on the test set, significantly outperforming all previously published CNN and transformer-based methods. Our code is publicly available at https://github.com/TuSimple/centerformer

arXiv:2209.06013

Virtual Underwater Datasets for Autonomous Inspections

Underwater Vehicles have become more sophisticated, driven by the off-shore sector and the scientific community's rapid advancements in underwater operations. Notably, many underwater tasks, including the assessment of subsea infrastructure, are performed with the assistance of Autonomous Underwater Vehicles (AUVs). There have been recent breakthroughs in Artificial Intelligence (AI) and, notably, Deep Learning (DL) models and applications, which have widespread usage in a variety of fields, including aerial unmanned vehicles, autonomous car navigation, and other applications. However, they are not as prevalent in underwater applications due to the difficulty of obtaining underwater datasets for a specific application. In this sense, the current study utilises recent advancements in the area of DL to construct a bespoke dataset generated from photographs of items captured in a laboratory environment. Generative Adversarial Networks (GANs) were utilised to translate the laboratory object dataset into the underwater domain by combining the collected images with photographs containing the underwater environment. The findings demonstrated the feasibility of creating such a dataset, since the resulting images closely resembled the real underwater environment when compared with real-world underwater ship hull images. Therefore, the artificial datasets of the underwater environment can overcome the difficulties arising from the limited access to real-world underwater images and are used to enhance underwater operations through underwater object image classification and detection.

arXiv:2209.05911

Computer vision based vehicle tracking as a complementary and scalable approach to RFID tagging

Logging of incoming/outgoing vehicles serves as a piece of critical information for root-cause analysis to combat security breach incidents in various sensitive organizations. RFID tagging hampers the scalability of vehicle tracking solutions on both logistics as well as technical fronts. For instance, requiring each incoming vehicle(departmental or private) to be RFID tagged is a severe constraint and coupling video analytics with RFID to detect abnormal vehicle movement is non-trivial. We leverage publicly available implementations of computer vision algorithms to develop an interpretable vehicle tracking algorithm using finite-state machine formalism. The state-machine consumes input from the cascaded object detection and optical character recognition(OCR) models for state transitions. We evaluated the proposed method on 75 video clips of 285 vehicles from our system deployment site. We observed that the detection rate is most affected by the speed and the type of vehicle. The highest detection rate is achieved when the vehicle movement is restricted to follow a movement restrictions(SOP) at the checkpoint similar to RFID tagging. We further analyzed 700 vehicle tracking predictions on live-data and identified that the majority of vehicle number prediction errors are due to illegible-text, image-blur, text occlusion and out-of-vocab letters in vehicle numbers. Towards system deployment and performance enhancement, we expect our ongoing system monitoring to provide evidences to establish a higher vehicle-throughput SOP at the security checkpoint as well as to drive the fine-tuning of the deployed computer-vision models and the state-machine to establish the proposed approach as a promising alternative to RFID-tagging.

arXiv:2209.04766공식 코드 · Papers with Code

Towards Sparsification of Graph Neural Networks

As real-world graphs expand in size, larger GNN models with billions of parameters are deployed. High parameter count in such models makes training and inference on graphs expensive and challenging. To reduce the computational and memory costs of GNNs, optimization methods such as pruning the redundant nodes and edges in input graphs have been commonly adopted. However, model compression, which directly targets the sparsification of model layers, has been mostly limited to traditional Deep Neural Networks (DNNs) used for tasks such as image classification and object detection. In this paper, we utilize two state-of-the-art model compression methods (1) train and prune and (2) sparse training for the sparsification of weight layers in GNNs. We evaluate and compare the efficiency of both methods in terms of accuracy, training sparsity, and training FLOPs on real-world graphs. Our experimental results show that on the ia-email, wiki-talk, and stackoverflow datasets for link prediction, sparse training with much lower training FLOPs achieves a comparable accuracy with the train and prune method. On the brain dataset for node classification, sparse training uses a lower number FLOPs (less than 1/7 FLOPs of train and prune method) and preserves a much better accuracy performance under extreme model sparsity.

arXiv:2209.04680공식 코드 · Papers with Code

IR-LPR: Large Scale of Iranian License Plate Recognition Dataset

Object detection has always been practical. There are so many things in our world that recognizing them can not only increase our automatic knowledge of the surroundings, but can also be lucrative for those interested in starting a new business. One of these attractive objects is the license plate (LP). In addition to the security uses that license plate detection can have, it can also be used to create creative businesses. With the development of object detection methods based on deep learning models, an appropriate and comprehensive dataset becomes doubly important. But due to the frequent commercial use of license plate datasets, there are limited datasets not only in Iran but also in the world. The largest Iranian dataset for detection license plates has 1,466 images. Also, the largest Iranian dataset for recognizing the characters of a license plate has 5,000 images. We have prepared a complete dataset including 20,967 car images along with all the detection annotation of the whole license plate and its characters, which can be useful for various purposes. Also, the total number of license plate images for character recognition application is 27,745 images.

arXiv:2209.04639

Large-Field Contextual Feature Learning for Glass Detection

Glass is very common in our daily life. Existing computer vision systems neglect it and thus may have severe consequences, e.g., a robot may crash into a glass wall. However, sensing the presence of glass is not straightforward. The key challenge is that arbitrary objects/scenes can appear behind the glass. In this paper, we propose an important problem of detecting glass surfaces from a single RGB image. To address this problem, we construct the first large-scale glass detection dataset (GDD) and propose a novel glass detection network, called GDNet-B, which explores abundant contextual cues in a large field-of-view via a novel large-field contextual feature integration (LCFI) module and integrates both high-level and low-level boundary features with a boundary feature enhancement (BFE) module. Extensive experiments demonstrate that our GDNet-B achieves satisfying glass detection results on the images within and beyond the GDD testing set. We further validate the effectiveness and generalization capability of our proposed GDNet-B by applying it to other vision tasks, including mirror segmentation and salient object detection. Finally, we show the potential applications of glass detection and discuss possible future research directions.

arXiv:2209.04966

Multi-modal Streaming 3D Object Detection

Modern autonomous vehicles rely heavily on mechanical LiDARs for perception. Current perception methods generally require 360{\deg} point clouds, collected sequentially as the LiDAR scans the azimuth and acquires consecutive wedge-shaped slices. The acquisition latency of a full scan (~ 100ms) may lead to outdated perception which is detrimental to safe operation. Recent streaming perception works proposed directly processing LiDAR slices and compensating for the narrow field of view (FOV) of a slice by reusing features from preceding slices. These works, however, are all based on a single modality and require past information which may be outdated. Meanwhile, images from high-frequency cameras can support streaming models as they provide a larger FoV compared to a LiDAR slice. However, this difference in FoV complicates sensor fusion. To address this research gap, we propose an innovative camera-LiDAR streaming 3D object detection framework that uses camera images instead of past LiDAR slices to provide an up-to-date, dense, and wide context for streaming perception. The proposed method outperforms prior streaming models on the challenging NuScenes benchmark. It also outperforms powerful full-scan detectors while being much faster. Our method is shown to be robust to missing camera images, narrow LiDAR slices, and small camera-LiDAR miscalibration.

arXiv:2209.04796

Multiple Object Tracking in Recent Times: A Literature Review

Multiple object tracking gained a lot of interest from researchers in recent years, and it has become one of the trending problems in computer vision, especially with the recent advancement of autonomous driving. MOT is one of the critical vision tasks for different issues like occlusion in crowded scenes, similar appearance, small object detection difficulty, ID switching, etc. To tackle these challenges, as researchers tried to utilize the attention mechanism of transformer, interrelation of tracklets with graph convolutional neural network, appearance similarity of objects in different frames with the siamese network, they also tried simple IOU matching based CNN network, motion prediction with LSTM. To take these scattered techniques under an umbrella, we have studied more than a hundred papers published over the last three years and have tried to extract the techniques that are more focused on by researchers in recent times to solve the problems of MOT. We have enlisted numerous applications, possibilities, and how MOT can be related to real life. Our review has tried to show the different perspectives of techniques that researchers used overtimes and give some future direction for the potential researchers. Moreover, we have included popular benchmark datasets and metrics in this review.

arXiv:2209.05407

Segmenting Known Objects and Unseen Unknowns without Prior Knowledge

Panoptic segmentation methods assign a known class to each pixel given in input. Even for state-of-the-art approaches, this inevitably enforces decisions that systematically lead to wrong predictions for objects outside the training categories. However, robustness against out-of-distribution samples and corner cases is crucial in safety-critical settings to avoid dangerous consequences. Since real-world datasets cannot contain enough data points to adequately sample the long tail of the underlying distribution, models must be able to deal with unseen and unknown scenarios as well. Previous methods targeted this by re-identifying already-seen unlabeled objects. In this work, we propose the necessary step to extend segmentation with a new setting which we term holistic segmentation. Holistic segmentation aims to identify and separate objects of unseen, unknown categories into instances without any prior knowledge about them while performing panoptic segmentation of known classes. We tackle this new problem with U3HS, which finds unknowns as highly uncertain regions and clusters their corresponding instance-aware embeddings into individual objects. By doing so, for the first time in panoptic segmentation with unknown objects, our U3HS is trained without unknown categories, reducing assumptions and leaving the settings as unconstrained as in real-life scenarios. Extensive experiments on public data from MS COCO, Cityscapes, and Lost&Found demonstrate the effectiveness of U3HS for this new, challenging, and assumptions-free setting called holistic segmentation. Project page: https://holisticseg.github.io.