PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2406.05755공식 코드 · Papers with Code

A DeNoising FPN With Transformer R-CNN for Tiny Object Detection

Despite notable advancements in the field of computer vision, the precise detection of tiny objects continues to pose a significant challenge, largely owing to the minuscule pixel representation allocated to these objects in imagery data. This challenge resonates profoundly in the domain of geoscience and remote sensing, where high-fidelity detection of tiny objects can facilitate a myriad of applications ranging from urban planning to environmental monitoring. In this paper, we propose a new framework, namely, DeNoising FPN with Trans R-CNN (DNTR), to improve the performance of tiny object detection. DNTR consists of an easy plug-in design, DeNoising FPN (DN-FPN), and an effective Transformer-based detector, Trans R-CNN. Specifically, feature fusion in the feature pyramid network is important for detecting multiscale objects. However, noisy features may be produced during the fusion process since there is no regularization between the features of different scales. Therefore, we introduce a DN-FPN module that utilizes contrastive learning to suppress noise in each level's features in the top-down path of FPN. Second, based on the two-stage framework, we replace the obsolete R-CNN detector with a novel Trans R-CNN detector to focus on the representation of tiny objects with self-attention. Experimental results manifest that our DNTR outperforms the baselines by at least 17.4% in terms of APvt on the AI-TOD dataset and 9.6% in terms of AP on the VisDrone dataset, respectively. Our code will be available at https://github.com/hoiliu-0801/DNTR.

arXiv:2607.28996v1cs.CV

SULAND v2: 도메인 시프트 환경의 무인 항공/지상체 기반 지표 지뢰 탐지를 위한 정제된 RGB 데이터셋 및 딥러닝 객체 검출 벤치마크

SULAND v2: A Refined RGB Dataset and Deep Learning Object Detection Benchmark for UAV/UGV-Based SUrface LANDmine Detection Under Domain Shift

RGB 영상은 지표 지뢰 탐지에서 무인 항공체 및 무인 지상체(UAV/UGV) 탐색 지원을 위한 실용적이고 저비용인 대안을 제공하지만, 안전성이 중요한 이 도메인에서 객체 검출기는 여전히 충분히 연구되지 않았습니다. 아키텍처 간 벤치마킹의 부재와 불충분한 분포 외(OOD) 분석으로 인해 실제 배치 환경 전반에서 검출기가 일반화되는지 여부가 명확하지 않습니다. 이러한 문제는 공개 RGB 지뢰 데이터셋의 희소성으로 인해 더욱 두드러지며, 이로 인해 SULAND는 PFM-1 및 PMA-2 탐지를 위한 핵심 벤치마크로 활용되어 왔습니다. 그러나 데이터 검토 결과, SULAND에는 누락되거나 잘못된 주석, 위치 추정 오류, 일관되지 않은 가시성 기준, 시각적 아티팩트, 시계열 라벨링 불일치, 그리고 반전된 OOD 클래스 ID 표기법 등의 문제가 있는 것으로 나타났습니다. 이에 본 연구에서는 정제된 RGB 지표 지뢰 데이터셋이자 벤치마크인 SULAND_v2를 제시합니다. 원본 이미지와 데이터 분할(split)을 유지하면서 주석을 수동으로 수정하여 완전성, 정밀한 위치 추정, 라벨 유효성, 클래스 일관성을 확보했습니다. SULAND_v2는 33,771장의 이미지와 12,433개의 바운딩 박스를 포함합니다. 9개 제품군에 걸쳐 35개 검출기 구성을 벤치마킹한 결과, 주석 정제를 통해 YOLOv8의 분포 내(IID) 테스트 mAP@50이 14.6~19.6%포인트 향상되었으며, OOD 클래스 ID 표기법을 수정한 덕분에 YOLOv8의 평균 OOD mAP@50이 약 25%포인트 증가했습니다. SULAND_v2에서 YOLOv12-Small은 가장 높은 IID mAP@50(0.908)을 달성한 반면, RF-DETR-Large는 가장 강력한 OOD 성능(0.799 mAP@50, 재현율 0.675)을 보였습니다. 본 연구 결과는 높은 IID 정확도가 실제 운영 준비 상태를 보장하지 않는다는 점을 입증합니다. SULAND_v2는 RGB 기반 지뢰 대응 탐색 지원에서 도메인 시프트 강건성을 평가하기 위한 신뢰할 수 있는 벤치마크를 제공합니다.

arXiv:1902.01569

Learning to Learn in Simulation

Deep learning often requires the manual collection and annotation of a training set. On robotic platforms, can we partially automate this task by training the robot to be curious, i.e., to seek out beneficial training information in the environment? In this work, we address the problem of curiosity as it relates to online, real-time, human-in-the-loop training of an object detection algorithm onboard a drone, where motion is constrained to two dimensions. We use a 3D simulation environment and deep reinforcement learning to train a curiosity agent to, in turn, train the object detection model. This agent could have one of two conflicting objectives: train as quickly as possible, or train with minimal human input. We outline a reward function that allows the curiosity agent to learn either of these objectives, while taking into account some of the physical characteristics of the drone platform on which it is meant to run. In addition, We show that we can weigh the importance of achieving these objectives by adjusting a parameter in the reward function.

arXiv:2005.09007공식 코드 · Papers with Code

U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection

In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD). The architecture of our U$^2$-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U$^2$-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U$^2$-Net$^{\dagger}$ (4.7 MB, 40 FPS), to facilitate the usage in different environments. Both models achieve competitive performance on six SOD datasets. The code is available: https://github.com/NathanUA/U-2-Net.

arXiv:2202.06256

RandomSEMO: Normality Learning Of Moving Objects For Video Anomaly Detection

Recent anomaly detection algorithms have shown powerful performance by adopting frame predicting autoencoders. However, these methods face two challenging circumstances. First, they are likely to be trained to be excessively powerful, generating even abnormal frames well, which leads to failure in detecting anomalies. Second, they are distracted by the large number of objects captured in both foreground and background. To solve these problems, we propose a novel superpixel-based video data transformation technique named Random Superpixel Erasing on Moving Objects (RandomSEMO) and Moving Object Loss (MOLoss), built on top of a simple lightweight autoencoder. RandomSEMO is applied to the moving object regions by randomly erasing their superpixels. It enforces the network to pay attention to the foreground objects and learn the normal features more effectively, rather than simply predicting the future frame. Moreover, MOLoss urges the model to focus on learning normal objects captured within RandomSEMO by amplifying the loss on the pixels near the moving objects. The experimental results show that our model outperforms state-of-the-arts on three benchmarks.

arXiv:2208.10773

Adversarial Vulnerability of Temporal Feature Networks for Object Detection

Taking into account information across the temporal domain helps to improve environment perception in autonomous driving. However, it has not been studied so far whether temporally fused neural networks are vulnerable to deliberately generated perturbations, i.e. adversarial attacks, or whether temporal history is an inherent defense against them. In this work, we study whether temporal feature networks for object detection are vulnerable to universal adversarial attacks. We evaluate attacks of two types: imperceptible noise for the whole image and locally-bound adversarial patch. In both cases, perturbations are generated in a white-box manner using PGD. Our experiments confirm, that attacking even a portion of a temporal input suffices to fool the network. We visually assess generated perturbations to gain insights into the functioning of attacks. To enhance the robustness, we apply adversarial training using 5-PGD. Our experiments on KITTI and nuScenes datasets demonstrate, that a model robustified via K-PGD is able to withstand the studied attacks while keeping the mAP-based performance comparable to that of an unattacked model.

arXiv:2304.03177

Mutual Interference Mitigation for MIMO-FMCW Automotive Radar

This paper considers mutual interference mitigation among automotive radars using frequency-modulated continuous wave (FMCW) signal and multiple-input multiple-output (MIMO) virtual arrays. For the first time, we derive a general interference signal model that fully accounts for not only the time-frequency incoherence, e.g., different FMCW configuration parameters and time offsets, but also the slow-time code MIMO incoherence and array configuration differences between the victim and interfering radars. Along with a standard MIMO-FMCW object signal model, we turn the interference mitigation into a spatial-domain object detection under incoherent MIMO-FMCW interference described by the explicit interference signal model, and propose a constant false alarm rate (CFAR) detector. More specifically, the proposed detector exploits the structural property of the derived interference model at both \emph{transmit} and \emph{receive} steering vector space. We also derive analytical closed-form expressions for probabilities of detection and false alarm. Performance evaluation using both synthetic-level and phased array system-level simulation confirms the effectiveness of our proposed detector over selected baseline methods.

arXiv:2402.17420공식 코드 · Papers with Code

PANDAS: Prototype-based Novel Class Discovery and Detection

Object detectors are typically trained once and for all on a fixed set of classes. However, this closed-world assumption is unrealistic in practice, as new classes will inevitably emerge after the detector is deployed in the wild. In this work, we look at ways to extend a detector trained for a set of base classes so it can i) spot the presence of novel classes, and ii) automatically enrich its repertoire to be able to detect those newly discovered classes together with the base ones. We propose PANDAS, a method for novel class discovery and detection. It discovers clusters representing novel classes from unlabeled data, and represents old and new classes with prototypes. During inference, a distance-based classifier uses these prototypes to assign a label to each detected object instance. The simplicity of our method makes it widely applicable. We experimentally demonstrate the effectiveness of PANDAS on the VOC 2012 and COCO-to-LVIS benchmarks. It performs favorably against the state of the art for this task while being computationally more affordable.

arXiv:2406.12395

SDNIA-YOLO: A Robust Object Detection Model for Extreme Weather Conditions

Though current object detection models based on deep learning have achieved excellent results on many conventional benchmark datasets, their performance will dramatically decline on real-world images taken under extreme conditions. Existing methods either used image augmentation based on traditional image processing algorithms or applied customized and scene-limited image adaptation technologies for robust modeling. This study thus proposes a stylization data-driven neural-image-adaptive YOLO (SDNIA-YOLO), which improves the model's robustness by enhancing image quality adaptively and learning valuable information related to extreme weather conditions from images synthesized by neural style transfer (NST). Experiments show that the developed SDNIA-YOLOv3 achieves significant mAP@.5 improvements of at least 15% on the real-world foggy (RTTS) and lowlight (ExDark) test sets compared with the baseline model. Besides, the experiments also highlight the outstanding potential of stylization data in simulating extreme weather conditions. The developed SDNIA-YOLO remains excellent characteristics of the native YOLO to a great extent, such as end-to-end one-stage, data-driven, and fast.

arXiv:2409.19972공식 코드 · Papers with Code

DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction

Multi-sensor fusion significantly enhances the accuracy and robustness of 3D semantic occupancy prediction, which is crucial for autonomous driving and robotics. However, most existing approaches depend on large image resolutions and complex networks to achieve top performance, hindering their application in practical scenarios. Additionally, most multi-sensor fusion approaches focus on improving fusion features while overlooking the exploration of supervision strategies for these features. To this end, we propose DAOcc, a novel multi-modal occupancy prediction framework that leverages 3D object detection supervision to assist in achieving superior performance, while using a deployment-friendly image feature extraction network and practical input image resolution. Furthermore, we introduce a BEV View Range Extension strategy to mitigate the adverse effects of reduced image resolution. Experimental results show that DAOcc achieves new state-of-the-art performance on the Occ3D-nuScenes and SurroundOcc benchmarks, and surpasses other methods by a significant margin while using only ResNet50 and 256*704 input image resolution. Code will be made available at https://github.com/AlphaPlusTT/DAOcc.

arXiv:2502.01565

GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection

Oriented Object Detection (OOD) has received increased attention in the past years, being a suitable solution for detecting elongated objects in remote sensing analysis. In particular, using regression loss functions based on Gaussian distributions has become attractive since they yield simple and differentiable terms. However, existing solutions are still based on regression heads that produce Oriented Bounding Boxes (OBBs), and the known problem of angular boundary discontinuity persists. In this work, we propose a regression head for OOD that directly produces Gaussian distributions based on the Cholesky matrix decomposition. The proposed head, named GauCho, theoretically mitigates the boundary discontinuity problem and is fully compatible with recent Gaussian-based regression loss functions. Furthermore, we advocate using Oriented Ellipses (OEs) to represent oriented objects, which relates to GauCho through a bijective function and alleviates the encoding ambiguity problem for circular objects. Our experimental results show that GauCho can be a viable alternative to the traditional OBB head, achieving results comparable to or better than state-of-the-art detectors for the challenging dataset DOTA

arXiv:2611.14857v1cs.CV

해양 영역에 적용한 객체 기반 변화 탐지의 궤도상 실증

In-orbit demonstration of object-based change detection applied to the maritime domain

본 논문은 CogniSAT-6 임무에 탑재된 저지연 해양 모니터링용 객체 기반 변화 탐지 파이프라인의 궤도상 검증 성공 사례를 제시한다. 우리는 최적화된 지상 기반 이중 촬영 스케줄링, 실시간 온보드 AI 기반 선박 분할, 다중 시점 매칭의 세 단계로 구성된 경량 운용 절차를 제안하고 검증한다. 대상 관심 영역(AoI)에서 연속 영상을 획득하면, 온보드 시스템은 최적 할당을 위한 헝가리안 알고리즘과 이상치 제거를 위한 RANSAC 기반 공간 및 크기 필터를 결합한 하이브리드 매칭 방식으로 선박 탐지 결과를 대응시킨다. 일련의 궤도상 검증에서 11개의 다양한 해양 시나리오에 걸쳐 견고한 성능을 보였으며, 선박의 크기와 위치만을 고려한 유효 재현율과 정밀도가 0.8을 넘었다. 이 검증은 시스템이 기하학적 일관성만으로 협조 대상과 비협조 "다크" 선박을 모두 추적할 수 있음을 보여 주었다. 실시간 정보를 자율적으로 생성하고 이에 따라 행동하는 이러한 능력은 차세대 IaaS(Insight-as-a-Service) 및 팁앤큐잉(tipping-and-cueing) 아키텍처의 기반을 마련한다.

arXiv:2608.04833v1cs.CV

RegisterBridgeMM: RGB-적외선 객체 검출을 위한 레지스터 중심 프레임워크

RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection

RGB-적외선(RGB-IR) 객체 검출(object detection)은 상호 보완적인 가시광선 및 열화상 단서의 이점을 활용하지만, 조명 변화, 기상 변화, 복잡한 배경 속에서 효과적인 융합을 달성하는 것은 여전히 어려운 과제입니다. 기존의 RGB-IR 융합 방식들은 종종 표현력이 풍부한 패치 수준의 상호작용을 포기하는 대신 더 가볍지만 제약이 큰 적응 메커니즘을 채택합니다. 본 연구에서는 쌍을 이루는 RGB-IR 입력에서 사전학습된 레지스터 토큰(register token)들이 모달리티 공통 정보와 모달리티 특화 정보를 모두 포함하고 있음을 경험적으로 관찰하였으며, 이는 이들이 모달리티 간 소통을 위한 압축된 기반으로 기능할 수 있음을 시사합니다. 이러한 관찰을 바탕으로, 본 논문에서는 3단계 레지스터 수명 주기로 구성된 레지스터 매개 융합 프레임워크인 RegisterBridgeMM을 제안합니다. Aggregate 단계는 사전학습에서 계승된 모달리티별 레지스터 요약을 보존하고, Bridge 단계는 합의-잔차(consensus-residual) 조절을 통해 양방향 레지스터-패치 읽기를 수행하며, Project 단계는 도출된 레지스터 요약을 패치 특징의 공간 적응적 캘리브레이션으로 변환합니다. 이러한 레지스터 경로는 사전학습된 패치 표현을 보존하면서도 밀집된 패치 간 교차 모달 상호작용을 피합니다. 두 백본 스트림을 모두 동결한 상태에서도 RegisterBridgeMM은 평가 대상인 LLVIP, M3FD, DroneVehicle, FLIR-Aligned 네 가지 벤치마크 모두에서 가장 높은 mAP50-95를 달성합니다.

arXiv:2408.08555

Detection and Tracking of MAVs Using a Rosette Scanning Pattern LiDAR

The use of commercial Micro Aerial Vehicles (MAVs) has surged in the past decade, offering societal benefits but also raising risks such as airspace violations and privacy concerns. Due to the increased security risks, the development of autonomous drone detection and tracking systems has become a priority. In this study, we tackle this challenge, by using non-repetitive rosette scanning pattern LiDARs, particularly focusing on increasing the detection distance by leveraging the characteristics of the sensor. The presented method utilizes a particle filter with a velocity component for the detection and tracking of the drone, which offers added re-detection capability. A Pan-Tilt platform is utilized to take advantage of the specific characteristics of the rosette scanning pattern LiDAR by keeping the tracked object in the center where the measurement is most dense. The detection capabilities and accuracy of the system are validated through indoor experiments, while the maximum detection distance is shown in our outdoor experiments. Our approach achieved accuracy on par with the state-of-the-art indoor method while increasing the maximum detection range by approximately 80\% beyond the state-of-the-art outdoor method.

arXiv:2104.13437

Incident Detection on Junctions Using Image Processing

In traffic management, it is a very important issue to shorten the response time by detecting the incidents (accident, vehicle breakdown, an object falling on the road, etc.) and informing the corresponding personnel. In this study, an anomaly detection framework for road junctions is proposed. The final judgment is based on the trajectories followed by the vehicles. Trajectory information is provided by vehicle detection and tracking algorithms on visual data streamed from a fisheye camera. Deep learning algorithms are used for vehicle detection, and Kalman Filter is used for tracking. To observe the trajectories more accurately, the detected vehicle coordinates are transferred to the bird's eye view coordinates using the lens distortion model prediction algorithm. The system determines whether there is an abnormality in trajectories by comparing historical trajectory data and instantaneous incoming data. The proposed system has achieved 84.6% success in vehicle detection and 96.8% success in abnormality detection on synthetic data. The system also works with a 97.3% success rate in detecting abnormalities on real data.

arXiv:2112.11798공식 코드 · Papers with Code

YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles

As autonomous vehicles and autonomous racing rise in popularity, so does the need for faster and more accurate detectors. While our naked eyes are able to extract contextual information almost instantly, even from far away, image resolution and computational resources limitations make detecting smaller objects (that is, objects that occupy a small pixel area in the input image) a genuinely challenging task for machines and a wide-open research field. This study explores how the popular YOLOv5 object detector can be modified to improve its performance in detecting smaller objects, with a particular application in autonomous racing. To achieve this, we investigate how replacing certain structural elements of the model (as well as their connections and other parameters) can affect performance and inference time. In doing so, we propose a series of models at different scales, which we name `YOLO-Z', and which display an improvement of up to 6.9% in mAP when detecting smaller objects at 50% IOU, at the cost of just a 3ms increase in inference time compared to the original YOLOv5. Our objective is to inform future research on the potential of adjusting a popular detector such as YOLOv5 to address specific tasks and provide insights on how specific changes can impact small object detection. Such findings, applied to the broader context of autonomous vehicles, could increase the amount of contextual information available to such systems.

arXiv:2204.08394공식 코드 · Papers with Code

CenterNet++ for Object Detection

There are two mainstreams for object detection: top-down and bottom-up. The state-of-the-art approaches mostly belong to the first category. In this paper, we demonstrate that the bottom-up approaches are as competitive as the top-down and enjoy higher recall. Our approach, named CenterNet, detects each object as a triplet keypoints (top-left and bottom-right corners and the center keypoint). We firstly group the corners by some designed cues and further confirm the objects by the center keypoints. The corner keypoints equip the approach with the ability to detect objects of various scales and shapes and the center keypoint avoids the confusion brought by a large number of false-positive proposals. Our approach is a kind of anchor-free detector because it does not need to define explicit anchor boxes. We adapt our approach to the backbones with different structures, i.e., the 'hourglass' like networks and the the 'pyramid' like networks, which detect objects on a single-resolution feature map and multi-resolution feature maps, respectively. On the MS-COCO dataset, CenterNet with Res2Net-101 and Swin-Transformer achieves APs of 53.7% and 57.1%, respectively, outperforming all existing bottom-up detectors and achieving state-of-the-art. We also design a real-time CenterNet, which achieves a good trade-off between accuracy and speed with an AP of 43.6% at 30.5 FPS. https://github.com/Duankaiwen/PyCenterNet.

arXiv:2309.12969공식 코드 · Papers with Code

Detect Everything with Few Examples

Few-shot object detection aims at detecting novel categories given only a few example images. It is a basic skill for a robot to perform tasks in open environments. Recent methods focus on finetuning strategies, with complicated procedures that prohibit a wider application. In this paper, we introduce DE-ViT, a few-shot object detector without the need for finetuning. DE-ViT's novel architecture is based on a new region-propagation mechanism for localization. The propagated region masks are transformed into bounding boxes through a learnable spatial integral layer. Instead of training prototype classifiers, we propose to use prototypes to project ViT features into a subspace that is robust to overfitting on base classes. We evaluate DE-ViT on few-shot, and one-shot object detection benchmarks with Pascal VOC, COCO, and LVIS. DE-ViT establishes new state-of-the-art results on all benchmarks. Notably, for COCO, DE-ViT surpasses the few-shot SoTA by 15 mAP on 10-shot and 7.2 mAP on 30-shot and one-shot SoTA by 2.8 AP50. For LVIS, DE-ViT outperforms few-shot SoTA by 17 box APr. Further, we evaluate DE-ViT with a real robot by building a pick-and-place system for sorting novel objects based on example images. The videos of our robot demonstrations, the source code and the models of DE-ViT can be found at https://mlzxy.github.io/devit.

arXiv:2502.14168

Deep learning based infrared small object segmentation: Challenges and future directions

Infrared sensing is a core method for supporting unmanned systems, such as autonomous vehicles and drones. Recently, infrared sensors have been widely deployed on mobile and stationary platforms for detection and classification of objects from long distances and in wide field of views. Given its success in the vision image analysis domain, deep learning has also been applied for object recognition in infrared images. However, techniques that have proven successful in visible light perception face new challenges in the infrared domain. These challenges include extremely low signal-to-noise ratios in infrared images, very small and blurred objects of interest, and limited availability of labeled/unlabeled training data due to the specialized nature of infrared sensors. Numerous methods have been proposed in the literature for the detection and classification of small objects in infrared images achieving varied levels of success. There is a need for a survey paper that critically analyzes existing techniques in this domain, identifies unsolved challenges and provides future research directions. This paper fills the gap and offers a concise and insightful review of deep learning-based methods. It also identifies the challenges faced by existing infrared object segmentation methods and provides a structured review of existing infrared perception methods from the perspective of these challenges and highlights the motivations behind the various approaches. Finally, this review suggests promising future directions based on recent advancements within this domain.

arXiv:2207.02039공식 코드 · Papers with Code

PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient

Knowledge distillation(KD) is a widely-used technique to train compact models in object detection. However, there is still a lack of study on how to distill between heterogeneous detectors. In this paper, we empirically find that better FPN features from a heterogeneous teacher detector can help the student although their detection heads and label assignments are different. However, directly aligning the feature maps to distill detectors suffers from two problems. First, the difference in feature magnitude between the teacher and the student could enforce overly strict constraints on the student. Second, the FPN stages and channels with large feature magnitude from the teacher model could dominate the gradient of distillation loss, which will overwhelm the effects of other features in KD and introduce much noise. To address the above issues, we propose to imitate features with Pearson Correlation Coefficient to focus on the relational information from the teacher and relax constraints on the magnitude of the features. Our method consistently outperforms the existing detection KD methods and works for both homogeneous and heterogeneous student-teacher pairs. Furthermore, it converges faster. With a powerful MaskRCNN-Swin detector as the teacher, ResNet-50 based RetinaNet and FCOS achieve 41.5% and 43.9% mAP on COCO2017, which are 4.1\% and 4.8\% higher than the baseline, respectively.