PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2006.05485

Off-the-shelf sensor vs. experimental radar -- How much resolution is necessary in automotive radar classification?

Radar-based road user detection is an important topic in the context of autonomous driving applications. The resolution of conventional automotive radar sensors results in a sparse data representation which is tough to refine during subsequent signal processing. On the other hand, a new sensor generation is waiting in the wings for its application in this challenging field. In this article, two sensors of different radar generations are evaluated against each other. The evaluation criterion is the performance on moving road user object detection and classification tasks. To this end, two data sets originating from an off-the-shelf radar and a high resolution next generation radar are compared. Special attention is given on how the two data sets are assembled in order to make them comparable. The utilized object detector consists of a clustering algorithm, a feature extraction module, and a recurrent neural network ensemble for classification. For the assessment, all components are evaluated both individually and, for the first time, as a whole. This allows for indicating where overall performance improvements have their origin in the pipeline. Furthermore, the generalization capabilities of both data sets are evaluated and important comparison metrics for automotive radar object detection are discussed. Results show clear benefits of the next generation radar. Interestingly, those benefits do not actually occur due to better performance at the classification stage, but rather because of the vast improvements at the clustering stage.

arXiv:2610.09511v1cs.CV

LiG-DETR: 항공 객체 검출을 위한 잠재 공간 내 전역 속 국소 재구성

LiG-DETR: Local-in-Global Reassembly in Latent Space for Aerial Object Detection

항공 객체 검출(aerial object detection)은 상당한 스케일 및 밀도 변화 문제에 직면해 있습니다. 작은 객체는 다운샘플링과 특징 압축으로 인해 쉽게 손실되는 반면, 중형 및 대형 객체는 충분한 전역적 문맥(global context)을 필요로 합니다. 기존 방법들은 주로 두 가지 패러다임을 따릅니다. 이미지 슬라이싱(image slicing)은 더 선명한 국소적 증거를 제공하지만 독립적인 크롭 단위 예측 및 후처리에 의존하는 반면, 특징 및 쿼리 수준의 최적화는 통합 추론을 유지하지만 이미 압축된 전체 이미지 표현에서 작동하여 세밀한 정보의 복원을 제한합니다. 이는 핵심적인 질문을 제기합니다. 항공 객체 검출에서 특징 손실이 발생하기 전에 충실도 높은 국소적 증거를 직접 획득하고 이를 통합된 엔드투엔드 프레임워크로 통합할 수 있을까요? 이를 위해 본 논문에서는 이미지 슬라이싱을 고충실도 국소 특징 획득으로 재구성하는 효율적인 전역-국소 재구성 프레임워크인 LiG-DETR을 제안합니다. 공유 인코더는 전역 특징과 국소적으로 확대된 특징을 추출하며, 이는 검출기 특징 공간으로 투영됩니다. 투영된 국소 특징들은 원래의 공간적 위치에 따라 재구성되어 전역적으로 정렬된 국소 특징 레벨을 형성하고, 단일 DETR 디코더가 전역 및 국소 특징을 공동으로 디코딩합니다. 중복 계산을 줄이기 위해, 문맥 보존형 선택적 재구성(Context-Preserved Selective Reassembly)은 조밀한 특징 배치를 유지하면서 유익한 영역에 고해상도 인코딩을 집중시키며, 밀도 인식 적응형 쿼리 할당(Density-Aware Adaptive Query Allocation)은 인코더 제안 점수를 사용하여 디코더 쿼리 예산을 조정합니다. 실험 결과, 우수한 대형 객체 성능을 유지하면서 소형 및 중형 객체에서 상당한 성능 향상을 보였으며, 유리한 정확도-효율성 트레이드오프와 향상된 교차 도메인 일반화 성능을 달성했습니다. 코드는 공개될 예정입니다.

arXiv:1108.03525

Hamiltonian Streamline Guided Feature Extraction with Applications to Face Detection

We propose a new feature extraction method based on two dynamical systems induced by intensity landscape: the negative gradient system and the Hamiltonian system. We build features based on the Hamiltonian streamlines. These features contain nice global topological information about the intensity landscape, and can be used for object detection. We show that for training images of same size, our feature space is much smaller than that generated by Haar-like features. The training time is extremely short, and detection speed and accuracy is similar to Haar-like feature based classifiers.

arXiv:2210.00174공식 코드 · Papers with Code

Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022

In this work, we present the winning solution for ORBIT Few-Shot Video Object Recognition Challenge 2022. Built upon the ProtoNet baseline, the performance of our method is improved with three effective techniques. These techniques include the embedding adaptation, the uniform video clip sampler and the invalid frame detection. In addition, we re-factor and re-implement the official codebase to encourage modularity, compatibility and improved performance. Our implementation accelerates the data loading in both training and testing.

arXiv:2501.09456

On the Relation between Optical Aperture and Automotive Object Detection

We explore the impact of aperture size and shape on automotive camera systems for deep-learning-based tasks like traffic sign recognition and light state detection. A method is proposed to simulate optical effects using the point spread function (PSF), enhancing realism and reducing the domain gap between synthetic and real-world images. Computer-generated scenes are refined with this technique to model optical distortions and improve simulation accuracy.

arXiv:1611.08998

DeepSetNet: Predicting Sets with Deep Neural Networks

This paper addresses the task of set prediction using deep learning. This is important because the output of many computer vision tasks, including image tagging and object detection, are naturally expressed as sets of entities rather than vectors. As opposed to a vector, the size of a set is not fixed in advance, and it is invariant to the ordering of entities within it. We define a likelihood for a set distribution and learn its parameters using a deep neural network. We also derive a loss for predicting a discrete distribution corresponding to set cardinality. Set prediction is demonstrated on the problem of multi-class image classification. Moreover, we show that the proposed cardinality loss can also trivially be applied to the tasks of object counting and pedestrian detection. Our approach outperforms existing methods in all three cases on standard datasets.

arXiv:2012.10412

PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection

LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects. In this paper, we propose a novel two-stage approach, namely PC-RGNN, dealing with such challenges by two specific solutions. On the one hand, we introduce a point cloud completion module to recover high-quality proposals of dense points and entire views with original structures preserved. On the other hand, a graph neural network module is designed, which comprehensively captures relations among points through a local-global attention mechanism as well as multi-scale graph based context aggregation, substantially strengthening encoded features. Extensive experiments on the KITTI benchmark show that the proposed approach outperforms the previous state-of-the-art baselines by remarkable margins, highlighting its effectiveness.

arXiv:2608.04720v2cs.CV

YOLOv14: 다양한 이미징 조건을 위한 적응형 실시간 객체 검출

YOLOv14: Adaptive Real-Time Object Detection for Diverse Imaging Conditions

실시간 객체 검출기(object detector)들은 통제된 조건에서는 뛰어난 정확도를 달성하지만, 어안 왜곡, 게임 렌더링 캐릭터, 항공 시점, 360° 파노라마와 같은 비이상적인 입력에서는 성능이 급격히 저하됩니다. 본 논문에서는 특정 유형의 입력 변동을 위해 설계된 네 가지 적응형 메커니즘을 갖춘 검출 프레임워크인 YOLOv14를 제안합니다: (1) 기하학적 왜곡을 위한 윈도우 기반 연산 및 시프트된 윈도우를 갖춘 변형 가능한 영역 어텐션(Deformable Area-Attention), (2) 도메인 시프트(domain shift)를 위한 점진적 적대적 학습 기반의 다단계 Game2Real 정렬, (3) 시점 불변성을 위한 적응형 온도를 갖춘 시점 인식 대조 학습(View-Aware Contrastive Learning), (4) 장면 다양성을 위한 동적 손실 밸런싱 기반의 장면 적응형 증강. 이들을 결합한 YOLOv14는 T4 GPU 기준 2.91ms에서 COCO val2017 49.1 mAP를 달성하며, 어안(+4.1 mAP), 파노라마(+6.6 mAP), 드론(+6.4 mAP), 그리고 자체 합성한 게임 캐릭터 벤치마크(+26.1 mAP)에서 상당한 성능 향상을 제공합니다. 재현 가능한 연구를 촉진하기 위해 코드와 모델을 공개합니다.

arXiv:1910.00462공식 코드 · Papers with Code

Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image Interpretation

Semantic Image Interpretation is the task of extracting a structured semantic description from images. This requires the detection of visual relationships: triples (subject,relation,object) describing a semantic relation between a subject and an object. A pure supervised approach to visual relationship detection requires a complete and balanced training set for all the possible combinations of (subject, relation, object). However, such training sets are not available and would require a prohibitive human effort. This implies the ability of predicting triples which do not appear in the training set. This problem is called zero-shot learning. State-of-the-art approaches to zero-shot learning exploit similarities among relationships in the training set or external linguistic knowledge. In this paper, we perform zero-shot learning by using Logic Tensor Networks, a novel Statistical Relational Learning framework that exploits both the similarities with other seen relationships and background knowledge, expressed with logical constraints between subjects, relations and objects. The experiments on the Visual Relationship Dataset show that the use of logical constraints outperforms the current methods. This implies that background knowledge can be used to alleviate the incompleteness of training sets.

arXiv:1911.06091

EdgeNet: Balancing Accuracy and Performance for Edge-based Convolutional Neural Network Object Detectors

Visual intelligence at the edge is becoming a growing necessity for low latency applications and situations where real-time decision is vital. Object detection, the first step in visual data analytics, has enjoyed significant improvements in terms of state-of-the-art accuracy due to the emergence of Convolutional Neural Networks (CNNs) and Deep Learning. However, such complex paradigms intrude increasing computational demands and hence prevent their deployment on resource-constrained devices. In this work, we propose a hierarchical framework that enables to detect objects in high-resolution video frames, and maintain the accuracy of state-of-the-art CNN-based object detectors while outperforming existing works in terms of processing speed when targeting a low-power embedded processor using an intelligent data reduction mechanism. Moreover, a use-case for pedestrian detection from Unmanned-Areal-Vehicle (UAV) is presented showing the impact that the proposed approach has on sensitivity, average processing time and power consumption when is implemented on different platforms. Using the proposed selection process our framework manages to reduce the processed data by 100x leading to under 4W power consumption on different edge devices.

arXiv:2009.00189

Object Detection-Based Variable Quantization Processing

In this paper, we propose a preprocessing method for conventional image and video encoders that can make these existing encoders content-aware. By going through our process, a higher quality parameter could be set on a traditional encoder without increasing the output size. A still frame or an image will firstly go through an object detector. Either the properties of the detection result will decide the parameters of the following procedures, or the system will be bypassed if no object is detected in the given frame. The processing method utilizes an adaptive quantization process to determine the portion of data to be dropped. This method is primarily based on the JPEG compression theory and is optimum for JPEG-based encoders such as JPEG encoders and the Motion JPEG encoders. However, other DCT-based encoders like MPEG part 2, H.264, etc. can also benefit from this method. In the experiments, we compare the MS-SSIM under the same bitrate as well as similar MS-SSIM but enhanced bitrate. As this method is based on human perception, even with similar MS-SSIM, the overall watching experience will be better than the direct encoded ones.

arXiv:2408.06901

Divide and Conquer: Improving Multi-Camera 3D Perception with 2D Semantic-Depth Priors and Input-Dependent Queries

3D perception tasks, such as 3D object detection and Bird's-Eye-View (BEV) segmentation using multi-camera images, have drawn significant attention recently. Despite the fact that accurately estimating both semantic and 3D scene layouts are crucial for this task, existing techniques often neglect the synergistic effects of semantic and depth cues, leading to the occurrence of classification and position estimation errors. Additionally, the input-independent nature of initial queries also limits the learning capacity of Transformer-based models. To tackle these challenges, we propose an input-aware Transformer framework that leverages Semantics and Depth as priors (named SDTR). Our approach involves the use of an S-D Encoder that explicitly models semantic and depth priors, thereby disentangling the learning process of object categorization and position estimation. Moreover, we introduce a Prior-guided Query Builder that incorporates the semantic prior into the initial queries of the Transformer, resulting in more effective input-aware queries. Extensive experiments on the nuScenes and Lyft benchmarks demonstrate the state-of-the-art performance of our method in both 3D object detection and BEV segmentation tasks.

arXiv:2212.04441공식 코드 · Papers with Code

The Differentiable Lens: Compound Lens Search over Glass Surfaces and Materials for Object Detection

Most camera lens systems are designed in isolation, separately from downstream computer vision methods. Recently, joint optimization approaches that design lenses alongside other components of the image acquisition and processing pipeline -- notably, downstream neural networks -- have achieved improved imaging quality or better performance on vision tasks. However, these existing methods optimize only a subset of lens parameters and cannot optimize glass materials given their categorical nature. In this work, we develop a differentiable spherical lens simulation model that accurately captures geometrical aberrations. We propose an optimization strategy to address the challenges of lens design -- notorious for non-convex loss function landscapes and many manufacturing constraints -- that are exacerbated in joint optimization tasks. Specifically, we introduce quantized continuous glass variables to facilitate the optimization and selection of glass materials in an end-to-end design context, and couple this with carefully designed constraints to support manufacturability. In automotive object detection, we report improved detection performance over existing designs even when simplifying designs to two- or three-element lenses, despite significantly degrading the image quality.

arXiv:2402.03634공식 코드 · Papers with Code

Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection

Multi-view 3D object detection systems often struggle with generating precise predictions due to the challenges in estimating depth from images, increasing redundant and incorrect detections. Our paper presents Ray Denoising, an innovative method that enhances detection accuracy by strategically sampling along camera rays to construct hard negative examples. These examples, visually challenging to differentiate from true positives, compel the model to learn depth-aware features, thereby improving its capacity to distinguish between true and false positives. Ray Denoising is designed as a plug-and-play module, compatible with any DETR-style multi-view 3D detectors, and it only minimally increases training computational costs without affecting inference speed. Our comprehensive experiments, including detailed ablation studies, consistently demonstrate that Ray Denoising outperforms strong baselines across multiple datasets. It achieves a 1.9\% improvement in mean Average Precision (mAP) over the state-of-the-art StreamPETR method on the NuScenes dataset. It shows significant performance gains on the Argoverse 2 dataset, highlighting its generalization capability. The code will be available at https://github.com/LiewFeng/RayDN.

arXiv:2404.15451

CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection

Feature pyramids have been widely adopted in convolutional neural networks (CNNs) and transformers for tasks like medical image segmentation and object detection. However, the currently existing models generally focus on the Encoder-side Transformer to extract features, from which decoder improvement can bring further potential with well-designed architecture. We propose CFPFormer, a novel decoder block that integrates feature pyramids and transformers. Specifically, by leveraging patch embedding, cross-layer feature concatenation, and Gaussian attention mechanisms, CFPFormer enhances feature extraction capabilities while promoting generalization across diverse tasks. Benefiting from Transformer structure and U-shaped Connections, our introduced model gains the ability to capture long-range dependencies and effectively up-sample feature maps. Our model achieves superior performance in detecting small objects compared to existing methods. We evaluate CFPFormer on medical image segmentation datasets and object detection benchmarks (VOC 2007, VOC2012, MS-COCO), demonstrating its effectiveness and versatility. On the ACDC Post-2017-MICCAI-Challenge online test set, our model reaches exceptionally impressive accuracy, and performed well compared with the original decoder setting in Synapse multi-organ segmentation dataset.

arXiv:2405.06821공식 코드 · Papers with Code

Synchronized Object Detection for Autonomous Sorting, Mapping, and Quantification of Materials in Circular Healthcare

The circular economy paradigm is gaining interest as a solution to reducing both material supply uncertainties and waste generation. One of the main challenges in realizing this paradigm is monitoring materials, since in general, something that is not measured cannot be effectively managed. In this paper, we propose a real-time synchronized object detection framework that enables, at the same time, autonomous sorting, mapping, and quantification of solid materials. We begin by introducing the general framework for real-time wide-area material monitoring, and then, we illustrate it using a numerical example. Finally, we develop a first prototype whose working principle is underpinned by the proposed framework. The prototype detects 4 materials from 5 different models of inhalers and, through a synchronization mechanism, it combines the detection outputs of 2 vision units running at 12-22 frames per second (Fig. 1). This led us to introduce the notion of synchromaterial and to conceive a robotic waste sorter as a node compartment of a material network. Dataset, code, and demo videos are publicly available.

arXiv:2203.16421공식 코드 · Papers with Code

OPD: Single-view 3D Openable Part Detection

We address the task of predicting what parts of an object can open and how they move when they do so. The input is a single image of an object, and as output we detect what parts of the object can open, and the motion parameters describing the articulation of each openable part. To tackle this task, we create two datasets of 3D objects: OPDSynth based on existing synthetic objects, and OPDReal based on RGBD reconstructions of real objects. We then design OPDRCNN, a neural architecture that detects openable parts and predicts their motion parameters. Our experiments show that this is a challenging task especially when considering generalization across object categories, and the limited amount of information in a single image. Our architecture outperforms baselines and prior work especially for RGB image inputs. Short video summary at https://www.youtube.com/watch?v=P85iCaD0rfc

arXiv:2403.15127공식 코드 · Papers with Code

Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection

Current semi-supervised object detection (SSOD) algorithms typically assume class balanced datasets (PASCAL VOC etc.) or slightly class imbalanced datasets (MS-COCO, etc). This assumption can be easily violated since real world datasets can be extremely class imbalanced in nature, thus making the performance of semi-supervised object detectors far from satisfactory. Besides, the research for this problem in SSOD is severely under-explored. To bridge this research gap, we comprehensively study the class imbalance problem for SSOD under more challenging scenarios, thus forming the first experimental setting for class imbalanced SSOD (CI-SSOD). Moreover, we propose a simple yet effective gradient-based sampling framework that tackles the class imbalance problem from the perspective of two types of confirmation biases. To tackle confirmation bias towards majority classes, the gradient-based reweighting and gradient-based thresholding modules leverage the gradients from each class to fully balance the influence of the majority and minority classes. To tackle the confirmation bias from incorrect pseudo labels of minority classes, the class-rebalancing sampling module resamples unlabeled data following the guidance of the gradient-based reweighting module. Experiments on three proposed sub-tasks, namely MS-COCO, MS-COCO to Object365 and LVIS, suggest that our method outperforms current class imbalanced object detectors by clear margins, serving as a baseline for future research in CI-SSOD. Code will be available at https://github.com/nightkeepers/CI-SSOD.

arXiv:1712.01111

An End-to-end 3D Convolutional Neural Network for Action Detection and Segmentation in Videos

In this paper, we propose an end-to-end 3D CNN for action detection and segmentation in videos. The proposed architecture is a unified deep network that is able to recognize and localize action based on 3D convolution features. A video is first divided into equal length clips and next for each clip a set of tube proposals are generated based on 3D CNN features. Finally, the tube proposals of different clips are linked together and spatio-temporal action detection is performed using these linked video proposals. This top-down action detection approach explicitly relies on a set of good tube proposals to perform well and training the bounding box regression usually requires a large number of annotated samples. To remedy this, we further extend the 3D CNN to an encoder-decoder structure and formulate the localization problem as action segmentation. The foreground regions (i.e. action regions) for each frame are segmented first then the segmented foreground maps are used to generate the bounding boxes. This bottom-up approach effectively avoids tube proposal generation by leveraging the pixel-wise annotations of segmentation. The segmentation framework also can be readily applied to a general problem of video object segmentation. Extensive experiments on several video datasets demonstrate the superior performance of our approach for action detection and video object segmentation compared to the state-of-the-arts.

arXiv:2305.12724공식 코드 · Papers with Code

Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking

Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not surpassed non-end-to-end tracking-by-detection methods. One potential reason is its label assignment strategy during training that consistently binds the tracked objects with tracking queries and then assigns the few newborns to detection queries. With one-to-one bipartite matching, such an assignment will yield unbalanced training, i.e., scarce positive samples for detection queries, especially for an enclosed scene, as the majority of the newborns come on stage at the beginning of videos. Thus, e2e-MOT will be easier to yield a tracking terminal without renewal or re-initialization, compared to other tracking-by-detection methods. To alleviate this problem, we present Co-MOT, a simple and effective method to facilitate e2e-MOT by a novel coopetition label assignment with a shadow concept. Specifically, we add tracked objects to the matching targets for detection queries when performing the label assignment for training the intermediate decoders. For query initialization, we expand each query by a set of shadow counterparts with limited disturbance to itself. With extensive ablations, Co-MOT achieves superior performance without extra costs, e.g., 69.4% HOTA on DanceTrack and 52.8% TETA on BDD100K. Impressively, Co-MOT only requires 38\% FLOPs of MOTRv2 to attain a similar performance, resulting in the 1.4$\times$ faster inference speed.