PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2607.29533v1cs.CV

OSAGEN: 산업용 이상 생성을 위한 객체 인식 마스크 사전 정보 및 다단계 분리 확산 모델

OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation

산업용 이상 탐지(anomaly detection) 및 위치 추정(localization)은 실제 이상 데이터와 픽셀 단위 주석의 부족으로 인해 한계를 겪고 있으며, 합성된 이미지-마스크 쌍은 이러한 병목 현상을 완화할 수 있습니다. 그러나 기존의 퓨샷(few-shot) 마스크 유도 생성 방식은 마스크의 기하학적 형태에 지나치게 얽매이거나, 미약한 이상을 생성하거나, 현재 객체 인스턴스와 맞지 않는 조건 마스크를 사용할 수 있습니다. 본 논문에서는 객체 인식 마스크 사전 정보(prior)와 다단계 분리 확산(diffusion) 모델을 결합한 OSAGEN을 제안합니다. 이 모델의 3단계 적응 과정은 정상 외형, 대략적인 조건 하에서의 결함 외형, 그리고 세분화된 마스크 캘리브레이션을 순차적으로 학습하여 결함 구현도와 국소적 제어력을 향상시킵니다. QBG는 매칭된 정상 이미지의 객체 구조를 마스크 확산 과정에 주입하여 객체 인식 사전 정보를 생성하며, ISC는 샘플링 중 이상 확산을 제한하고 정상 콘텐츠를 보존합니다. 또한 경량 구체화 단계를 통해 구현된 결함과 정렬된 픽셀 단위 라벨을 복원합니다. 통합된 다운스트림 위치 추정 프로토콜 하에서 OSAGEN은 MVTec AD 및 VisA 데이터셋에서 각각 88.1/82.2 및 68.5/66.1의 AP-P/F1-P 점수를 달성했습니다. 코드는 논문 채택 시 공개될 예정입니다.

arXiv:2211.16066공식 코드 · Papers with Code

Analysis of Training Object Detection Models with Synthetic Data

Recently, the use of synthetic training data has been on the rise as it offers correctly labelled datasets at a lower cost. The downside of this technique is that the so-called domain gap between the real target images and synthetic training data leads to a decrease in performance. In this paper, we attempt to provide a holistic overview of how to use synthetic data for object detection. We analyse aspects of generating the data as well as techniques used to train the models. We do so by devising a number of experiments, training models on the Dataset of Industrial Metal Objects (DIMO). This dataset contains both real and synthetic images. The synthetic part has different subsets that are either exact synthetic copies of the real data or are copies with certain aspects randomised. This allows us to analyse what types of variation are good for synthetic training data and which aspects should be modelled to closely match the target data. Furthermore, we investigate what types of training techniques are beneficial towards generalisation to real data, and how to use them. Additionally, we analyse how real images can be leveraged when training on synthetic images. All these experiments are validated on real data and benchmarked to models trained on real data. The results offer a number of interesting takeaways that can serve as basic guidelines for using synthetic data for object detection. Code to reproduce results is available at https://github.com/EDM-Research/DIMO_ObjectDetection.

arXiv:2302.06052공식 코드 · Papers with Code

CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction

Multi-scale features are essential for dense prediction tasks, such as object detection, instance segmentation, and semantic segmentation. The prevailing methods usually utilize a classification backbone to extract multi-scale features and then fuse these features using a lightweight module (e.g., the fusion module in FPN and BiFPN, two typical object detection methods). However, as these methods allocate most computational resources to the classification backbone, the multi-scale feature fusion in these methods is delayed, which may lead to inadequate feature fusion. While some methods perform feature fusion from early stages, they either fail to fully leverage high-level features to guide low-level feature learning or have complex structures, resulting in sub-optimal performance. We propose a streamlined cascade encoder-decoder network, dubbed CEDNet, tailored for dense \mbox{prediction} tasks. All stages in CEDNet share the same encoder-decoder structure and perform multi-scale feature fusion within the decoder. A hallmark of CEDNet is its ability to incorporate high-level features from early stages to guide low-level feature learning in subsequent stages, thereby enhancing the effectiveness of multi-scale feature fusion. We explored three well-known encoder-decoder structures: Hourglass, UNet, and FPN. When integrated into CEDNet, they performed much better than traditional methods that use a pre-designed classification backbone combined with a lightweight fusion module. Extensive experiments on object detection, instance segmentation, and semantic segmentation demonstrated the effectiveness of our method. The code is available at https://github.com/zhanggang001/CEDNet.

arXiv:2411.15602

Enhancing Object Detection Accuracy in Autonomous Vehicles Using Synthetic Data

The rapid progress in machine learning models has significantly boosted the potential for real-world applications such as autonomous vehicles, disease diagnoses, and recognition of emergencies. The performance of many machine learning models depends on the nature and size of the training data sets. These models often face challenges due to the scarcity, noise, and imbalance in real-world data, limiting their performance. Nonetheless, high-quality, diverse, relevant and representative training data is essential to build accurate and reliable machine learning models that adapt well to real-world scenarios. It is hypothesised that well-designed synthetic data can improve the performance of a machine learning algorithm. This work aims to create a synthetic dataset and evaluate its effectiveness to improve the prediction accuracy of object detection systems. This work considers autonomous vehicle scenarios as an illustrative example to show the efficacy of synthetic data. The effectiveness of these synthetic datasets in improving the performance of state-of-the-art object detection models is explored. The findings demonstrate that incorporating synthetic data improves model performance across all performance matrices. Two deep learning systems, System-1 (trained on real-world data) and System-2 (trained on a combination of real and synthetic data), are evaluated using the state-of-the-art YOLO model across multiple metrics, including accuracy, precision, recall, and mean average precision. Experimental results revealed that System-2 outperformed System-1, showing a 3% improvement in accuracy, along with superior performance in all other metrics.

arXiv:1805.02152

Quantization Mimic: Towards Very Tiny CNN for Object Detection

In this paper, we propose a simple and general framework for training very tiny CNNs for object detection. Due to limited representation ability, it is challenging to train very tiny networks for complicated tasks like detection. To the best of our knowledge, our method, called Quantization Mimic, is the first one focusing on very tiny networks. We utilize two types of acceleration methods: mimic and quantization. Mimic improves the performance of a student network by transfering knowledge from a teacher network. Quantization converts a full-precision network to a quantized one without large degradation of performance. If the teacher network is quantized, the search scope of the student network will be smaller. Using this feature of the quantization, we propose Quantization Mimic. It first quantizes the large network, then mimic a quantized small network. The quantization operation can help student network to better match the feature maps from teacher network. To evaluate our approach, we carry out experiments on various popular CNNs including VGG and Resnet, as well as different detection frameworks including Faster R-CNN and R-FCN. Experiments on Pascal VOC and WIDER FACE verify that our Quantization Mimic algorithm can be applied on various settings and outperforms state-of-the-art model acceleration methods given limited computing resouces.

arXiv:2104.12041공식 코드 · Papers with Code

Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy

A practical long-term tracker typically contains three key properties, i.e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism. However, most state-of-the-art long-term trackers (e.g., Pseudo and re-detecting based ones) do not take all three key properties into account and therefore may either be time-consuming or drift to distractors. To address the issues, we propose a two-task tracking frame work (named DMTrack), which utilizes two core components (i.e., one-shot detection and re-identification (re-id) association) to achieve distractor-aware fast tracking via Dynamic convolutions (d-convs) and Multiple object tracking (MOT) philosophy. To achieve precise and fast global detection, we construct a lightweight one-shot detector using a novel dynamic convolutions generation method, which provides a unified and more flexible way for fusing target information into the search field. To distinguish the target from distractors, we resort to the philosophy of MOT to reason distractors explicitly by maintaining all potential similarities' tracklets. Benefited from the strength of high recall detection and explicit object association, our tracker achieves state-of-the-art performance on the LaSOT, OxUvA, TLP, VOT2018LT and VOT2019LT benchmarks and runs in real-time (3x faster than comparisons).

arXiv:2307.11077공식 코드 · Papers with Code

AlignDet: Aligning Pre-training and Fine-tuning in Object Detection

The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and fine-tuning procedure in existing practices, which implicitly limit the detector's performance, generalization ability, and convergence speed. To this end, we propose AlignDet, a unified pre-training framework that can be adapted to various existing detectors to alleviate the discrepancies. AlignDet decouples the pre-training process into two stages, i.e., image-domain and box-domain pre-training. The image-domain pre-training optimizes the detection backbone to capture holistic visual abstraction, and box-domain pre-training learns instance-level semantics and task-aware concepts to initialize the parts out of the backbone. By incorporating the self-supervised pre-trained backbones, we can pre-train all modules for various detectors in an unsupervised paradigm. As depicted in Figure 1, extensive experiments demonstrate that AlignDet can achieve significant improvements across diverse protocols, such as detection algorithm, model backbone, data setting, and training schedule. For example, AlignDet improves FCOS by 5.3 mAP, RetinaNet by 2.1 mAP, Faster R-CNN by 3.3 mAP, and DETR by 2.3 mAP under fewer epochs.

arXiv:2401.12129공식 코드 · Papers with Code

Out-of-Distribution Detection & Applications With Ablated Learned Temperature Energy

As deep neural networks become adopted in high-stakes domains, it is crucial to identify when inference inputs are Out-of-Distribution (OOD) so that users can be alerted of likely drops in performance and calibration despite high confidence -- ultimately to know when networks' decisions (and their uncertainty in those decisions) should be trusted. In this paper we introduce Ablated Learned Temperature Energy (or "AbeT" for short), an OOD detection method which lowers the False Positive Rate at 95\% True Positive Rate (FPR@95) by $43.43\%$ in classification compared to state of the art without training networks in multiple stages or requiring hyperparameters or test-time backward passes. We additionally provide empirical insights as to why our model learns to distinguish between In-Distribution (ID) and OOD samples while only being explicitly trained on ID samples via exposure to misclassified ID examples at training time. Lastly, we show the efficacy of our method in identifying predicted bounding boxes and pixels corresponding to OOD objects in object detection and semantic segmentation, respectively -- with an AUROC increase of $5.15\%$ in object detection and both a decrease in FPR@95 of $41.48\%$ and an increase in AUPRC of $34.20\%$ in semantic segmentation compared to previous state of the art.

arXiv:1412.0065

3D Hand Pose Detection in Egocentric RGB-D Images

We focus on the task of everyday hand pose estimation from egocentric viewpoints. For this task, we show that depth sensors are particularly informative for extracting near-field interactions of the camera wearer with his/her environment. Despite the recent advances in full-body pose estimation using Kinect-like sensors, reliable monocular hand pose estimation in RGB-D images is still an unsolved problem. The problem is considerably exacerbated when analyzing hands performing daily activities from a first-person viewpoint, due to severe occlusions arising from object manipulations and a limited field-of-view. Our system addresses these difficulties by exploiting strong priors over viewpoint and pose in a discriminative tracking-by-detection framework. Our priors are operationalized through a photorealistic synthetic model of egocentric scenes, which is used to generate training data for learning depth-based pose classifiers. We evaluate our approach on an annotated dataset of real egocentric object manipulation scenes and compare to both commercial and academic approaches. Our method provides state-of-the-art performance for both hand detection and pose estimation in egocentric RGB-D images.

arXiv:2305.07598공식 코드 · Papers with Code

Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer

Detection Transformers (DETR) have recently set new benchmarks in object detection. However, their performance in detecting rotated objects lags behind established oriented object detectors. Our analysis identifies a key observation: the boundary discontinuity and square-like problem in bipartite matching poses an issue with assigning appropriate ground truths to predictions, leading to duplicate low-confidence predictions. To address this, we introduce a Hausdorff distance-based cost for bipartite matching, which more accurately quantifies the discrepancy between predictions and ground truths. Additionally, we find that a static denoising approach impedes the training of rotated DETR, especially as the quality of the detector's predictions begins to exceed that of the noised ground truths. To overcome this, we propose an adaptive query denoising method that employs bipartite matching to selectively eliminate noised queries that detract from model improvement. When compared to models adopting a ResNet-50 backbone, our proposed model yields remarkable improvements, achieving $\textbf{+4.18}$ AP$_{50}$, $\textbf{+4.59}$ AP$_{50}$, and $\textbf{+4.99}$ AP$_{50}$ on DOTA-v2.0, DOTA-v1.5, and DIOR-R, respectively.

arXiv:2609.14560v2cs.CV

LAF-YOLOv10을 이용한 드론 항공 영상의 소형 객체 탐지

Small Object Detection in Drone Aerial Imagery with LAF-YOLOv10

범용 객체 탐지기는 대상이 몇 픽셀에 불과하고 탑재 연산 자원이 제한된 UAV 영상에서 정확도가 떨어진다. 기존 연구는 독립적으로 검증된 구조적 기법들을 하나의 탐지기로 결합하며, 개별적으로 보고된 이득이 결합 후에도 유지된다고 가정한다. 본 연구는 이 가정을 직접 시험한다. LAF-YOLOv10은 YOLOv10n에 네 가지 기법, 즉 Partial Convolution C2f(PC-C2f) 백본 블록, Attention-Guided Feature Pyramid Network(AG-FPN), 대형 객체용 P5 헤드를 대체하는 P2 탐지 헤드, Wise-IoU v3 회귀를 통합하여 이들의 결합 효과가 각각의 기여와 일치하는지 묻는다. LAF-YOLOv10을 VisDrone-DET2019에서 세 번(시드 42, 123, 256) 학습하고 수정하지 않은 YOLOv10n과 비교하며, TIDE 오류 분해, 범주별 분석, 구성 요소별 절제, 어텐션/손실 비교, UAVDT로의 제로샷 전이, 보류/test-dev 평가를 사용하여 결합이 성공 또는 실패하는 지점을 규명한다. 여기서는 조합 가능성이 성립하지 않는다. LAF-YOLOv10은 2.14M 파라미터에서 24.0±0.4% mAP@0.5를 달성하여 YOLOv10n(31.8%)보다 7.8포인트 낮으며, 이 격차는 UAVDT에서도 나타나고(-10.0포인트) 보류 및 test-dev 평가(23.5%, 22.5%)로 확인된다. 배경 오탐, 위치 오차, 중복 탐지는 AG-FPN과 Wise-IoU가 유도하도록 설계된 방향으로 변화한다. 절제 실험은 격차의 구체적 원인을 추적한다. P2/-P5 헤드 교체는 단독으로 2.5포인트의 손실을 초래하며, PC-C2f로 약화된 백본에 적용하면 2.5포인트의 상호작용 페널티가 추가된다. PC-C2f 자체의 2.0포인트 손실은 사전 학습 가중치의 부분 이식(백본 텐서 150개 중 73개 전이)과 부합한다. 실패는 네 구성 요소 각각이 아니라 특정 상호작용에 기인한다. 조합 가능성은 가정할 것이 아니라 직접 검증해야 한다. 코드/체크포인트: https://github.com/Mudassiruddin7/Small-Object-Detection-in-UAV-Imagery.

arXiv:2210.15085

Robot to Human Object Handover using Vision and Joint Torque Sensor Modalities

We present a robot-to-human object handover algorithm and implement it on a 7-DOF arm equipped with a 3-finger mechanical hand. The system performs a fully autonomous and robust object handover to a human receiver in real-time. Our algorithm relies on two complementary sensor modalities: joint torque sensors on the arm and an eye-in-hand RGB-D camera for sensor feedback. Our approach is entirely implicit, i.e., there is no explicit communication between the robot and the human receiver. Information obtained via the aforementioned sensor modalities is used as inputs to their related deep neural networks. While the torque sensor network detects the human receiver's "intention" such as: pull, hold, or bump, the vision sensor network detects if the receiver's fingers have wrapped around the object. Networks' outputs are then fused, based on which a decision is made to either release the object or not. Despite substantive challenges in sensor feedback synchronization, object, and human hand detection, our system achieves robust robot-to-human handover with 98\% accuracy in our preliminary real experiments using human receivers.

arXiv:1811.11507공식 코드 · Papers with Code

One-Shot Instance Segmentation

We tackle the problem of one-shot instance segmentation: Given an example image of a novel, previously unknown object category, find and segment all objects of this category within a complex scene. To address this challenging new task, we propose Siamese Mask R-CNN. It extends Mask R-CNN by a Siamese backbone encoding both reference image and scene, allowing it to target detection and segmentation towards the reference category. We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection network towards the reference category appears to be more difficult. Our work provides a first strong baseline for one-shot instance segmentation and will hopefully inspire further research into more powerful and flexible scene analysis algorithms. Code is available at: https://github.com/bethgelab/siamese-mask-rcnn

arXiv:2003.01288

Trained Model Fusion for Object Detection using Gating Network

The major approaches of transfer learning in computer vision have tried to adapt the source domain to the target domain one-to-one. However, this scenario is difficult to apply to real applications such as video surveillance systems. As those systems have many cameras installed at each location regarded as source domains, it is difficult to identify the proper source domain. In this paper, we introduce a new transfer learning scenario that has various source domains and one target domain, assuming video surveillance system integration. Also, we propose a novel method for automatically producing a high accuracy model by fusing models trained at various source domains. In particular, we show how to apply a gating network to fuse source domains for object detection tasks, which is a new approach. We demonstrate the effectiveness of our method through experiments on traffic surveillance datasets.

arXiv:2008.09672

Towards Autonomous Driving: a Multi-Modal 360$^{\circ}$ Perception Proposal

In this paper, a multi-modal 360$^{\circ}$ framework for 3D object detection and tracking for autonomous vehicles is presented. The process is divided into four main stages. First, images are fed into a CNN network to obtain instance segmentation of the surrounding road participants. Second, LiDAR-to-image association is performed for the estimated mask proposals. Then, the isolated points of every object are processed by a PointNet ensemble to compute their corresponding 3D bounding boxes and poses. Lastly, a tracking stage based on Unscented Kalman Filter is used to track the agents along time. The solution, based on a novel sensor fusion configuration, provides accurate and reliable road environment detection. A wide variety of tests of the system, deployed in an autonomous vehicle, have successfully assessed the suitability of the proposed perception stack in a real autonomous driving application.

arXiv:2107.13757

Bridging Gap between Image Pixels and Semantics via Supervision: A Survey

The fact that there exists a gap between low-level features and semantic meanings of images, called the semantic gap, is known for decades. Resolution of the semantic gap is a long standing problem. The semantic gap problem is reviewed and a survey on recent efforts in bridging the gap is made in this work. Most importantly, we claim that the semantic gap is primarily bridged through supervised learning today. Experiences are drawn from two application domains to illustrate this point: 1) object detection and 2) metric learning for content-based image retrieval (CBIR). To begin with, this paper offers a historical retrospective on supervision, makes a gradual transition to the modern data-driven methodology and introduces commonly used datasets. Then, it summarizes various supervision methods to bridge the semantic gap in the context of object detection and metric learning.

arXiv:2306.03537

Real-Time Onboard Object Detection for Augmented Reality: Enhancing Head-Mounted Display with YOLOv8

This paper introduces a software architecture for real-time object detection using machine learning (ML) in an augmented reality (AR) environment. Our approach uses the recent state-of-the-art YOLOv8 network that runs onboard on the Microsoft HoloLens 2 head-mounted display (HMD). The primary motivation behind this research is to enable the application of advanced ML models for enhanced perception and situational awareness with a wearable, hands-free AR platform. We show the image processing pipeline for the YOLOv8 model and the techniques used to make it real-time on the resource-limited edge computing platform of the headset. The experimental results demonstrate that our solution achieves real-time processing without needing offloading tasks to the cloud or any other external servers while retaining satisfactory accuracy regarding the usual mAP metric and measured qualitative performance

arXiv:2402.04673

Streamlined Hybrid Annotation Framework using Scalable Codestream for Bandwidth-Restricted UAV Object Detection

Emergency response missions depend on the fast relay of visual information, a task to which unmanned aerial vehicles are well adapted. However, the effective use of unmanned aerial vehicles is often compromised by bandwidth limitations that impede fast data transmission, thereby delaying the quick decision-making necessary in emergency situations. To address these challenges, this paper presents a streamlined hybrid annotation framework that utilizes the JPEG 2000 compression algorithm to facilitate object detection under limited bandwidth. The proposed framework employs a fine-tuned deep learning network for initial image annotation at lower resolutions and uses JPEG 2000's scalable codestream to selectively enhance the image resolution in critical areas that require human expert annotation. We show that our proposed hybrid framework reduces the response time by a factor of 34 in emergency situations compared to a baseline approach.

arXiv:2502.03072

RoboGrasp: A Universal Grasping Policy for Robust Robotic Control

Imitation learning and world models have shown significant promise in advancing generalizable robotic learning, with robotic grasping remaining a critical challenge for achieving precise manipulation. Existing methods often rely heavily on robot arm state data and RGB images, leading to overfitting to specific object shapes or positions. To address these limitations, we propose RoboGrasp, a universal grasping policy framework that integrates pretrained grasp detection models with robotic learning. By leveraging robust visual guidance from object detection and segmentation tasks, RoboGrasp significantly enhances grasp precision, stability, and generalizability, achieving up to 34% higher success rates in few-shot learning and grasping box prompt tasks. Built on diffusion-based methods, RoboGrasp is adaptable to various robotic learning paradigms, enabling precise and reliable manipulation across diverse and complex scenarios. This framework represents a scalable and versatile solution for tackling real-world challenges in robotic grasping.

arXiv:1711.05471

Exploring the Bounds of the Utility of Context for Object Detection

The recurring context in which objects appear holds valuable information that can be employed to predict their existence. This intuitive observation indeed led many researchers to endow appearance-based detectors with explicit reasoning about context. The underlying thesis suggests that stronger contextual relations would facilitate greater improvements in detection capacity. In practice, however, the observed improvement in many cases is modest at best, and often only marginal. In this work we seek to improve our understanding of this phenomenon, in part by pursuing an opposite approach. Instead of attempting to improve detection scores by employing context, we treat the utility of context as an optimization problem: to what extent can detection scores be improved by considering context or any other kind of additional information? With this approach we explore the bounds on improvement by using contextual relations between objects and provide a tool for identifying the most helpful ones. We show that simple co-occurrence relations can often provide large gains, while in other cases a significant improvement is simply impossible or impractical with either co-occurrence or more precise spatial relations. To better understand these results we then analyze the ability of context to handle different types of false detections, revealing that tested contextual information cannot ameliorate localization errors, severely limiting its gains. These and additional insights further our understanding on where and why utilization of context for object detection succeeds and fails.