PyTorchKR Papers

“Object Detection”

총 13,453편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2405.14497공식 코드 · Papers with Code

Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment

In this work, we tackle the problem of domain generalization for object detection, specifically focusing on the scenario where only a single source domain is available. We propose an effective approach that involves two key steps: diversifying the source domain and aligning detections based on class prediction confidence and localization. Firstly, we demonstrate that by carefully selecting a set of augmentations, a base detector can outperform existing methods for single domain generalization by a good margin. This highlights the importance of domain diversification in improving the performance of object detectors. Secondly, we introduce a method to align detections from multiple views, considering both classification and localization outputs. This alignment procedure leads to better generalized and well-calibrated object detector models, which are crucial for accurate decision-making in safety-critical applications. Our approach is detector-agnostic and can be seamlessly applied to both single-stage and two-stage detectors. To validate the effectiveness of our proposed methods, we conduct extensive experiments and ablations on challenging domain-shift scenarios. The results consistently demonstrate the superiority of our approach compared to existing methods. Our code and models are available at: https://github.com/msohaildanish/DivAlign

arXiv:1907.13576

Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks

Object detection and recognition has been an ongoing research topic for a long time in the field of computer vision. Even in robotics, detecting the state of an object by a robot still remains a challenging task. Also, collecting data for each possible state is also not feasible. In this literature, we use a deep convolutional neural network with SVM as a classifier to help with recognizing the state of a cooking object. We also study how a generative adversarial network can be used for synthetic data augmentation and improving the classification accuracy. The main motivation behind this work is to estimate how well a robot could recognize the current state of an object

arXiv:2210.10221

Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets

We propose a non-iterative method to optimize pseudo-labeling thresholds for learning object detection from a collection of low-cost datasets, each of which is annotated for only a subset of all the object classes. A popular approach to this problem is first to train teacher models and then to use their confident predictions as pseudo ground-truth labels when training a student model. To obtain the best result, however, thresholds for prediction confidence must be adjusted. This process typically involves iterative search and repeated training of student models and is time-consuming. Therefore, we develop a method to optimize the thresholds without iterative optimization by maximizing the $F_\beta$-score on a validation dataset, which measures the quality of pseudo labels and can be measured without training a student model. We experimentally demonstrate that our proposed method achieves an mAP comparable to that of grid search on the COCO and VOC datasets.

arXiv:1803.08707

Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction

There are mainly two types of state-of-the-art object detectors. On one hand, we have two-stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or Mask R-CNN, that (i) use a Region Proposal Network to generate regions of interests in the first stage and (ii) send the region proposals down the pipeline for object classification and bounding-box regression. Such models reach the highest accuracy rates, but are typically slower. On the other hand, we have single-stage detectors, such as YOLO (You Only Look Once) and SSD (Singe Shot MultiBox Detector), that treat object detection as a simple regression problem by taking an input image and learning the class probabilities and bounding box coordinates. Such models reach lower accuracy rates, but are much faster than two-stage object detectors. In this paper, we propose to use an image difficulty predictor to achieve an optimal trade-off between accuracy and speed in object detection. The image difficulty predictor is applied on the test images to split them into easy versus hard images. Once separated, the easy images are sent to the faster single-stage detector, while the hard images are sent to the more accurate two-stage detector. Our experiments on PASCAL VOC 2007 show that using image difficulty compares favorably to a random split of the images. Our method is flexible, in that it allows to choose a desired threshold for splitting the images into easy versus hard.

arXiv:2104.13876공식 코드 · Papers with Code

PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling

Recent one-stage object detectors follow a per-pixel prediction approach that predicts both the object category scores and boundary positions from every single grid location. However, the most suitable positions for inferring different targets, i.e., the object category and boundaries, are generally different. Predicting all these targets from the same grid location thus may lead to sub-optimal results. In this paper, we analyze the suitable inference positions for object category and boundaries, and propose a prediction-target-decoupled detector named PDNet to establish a more flexible detection paradigm. Our PDNet with the prediction decoupling mechanism encodes different targets separately in different locations. A learnable prediction collection module is devised with two sets of dynamic points, i.e., dynamic boundary points and semantic points, to collect and aggregate the predictions from the favorable regions for localization and classification. We adopt a two-step strategy to learn these dynamic point positions, where the prior positions are estimated for different targets first, and the network further predicts residual offsets to the positions with better perceptions of the object properties. Extensive experiments on the MS COCO benchmark demonstrate the effectiveness and efficiency of our method. With a single ResNeXt-64x4d-101-DCN as the backbone, our detector achieves 50.1 AP with single-scale testing, which outperforms the state-of-the-art methods by an appreciable margin under the same experimental settings.Moreover, our detector is highly efficient as a one-stage framework. Our code is public at https://github.com/yangli18/PDNet.

arXiv:2407.05607공식 코드 · Papers with Code

Weakly Supervised Test-Time Domain Adaptation for Object Detection

Prior to deployment, an object detector is trained on a dataset compiled from a previous data collection campaign. However, the environment in which the object detector is deployed will invariably evolve, particularly in outdoor settings where changes in lighting, weather and seasons will significantly affect the appearance of the scene and target objects. It is almost impossible for all potential scenarios that the object detector may come across to be present in a finite training dataset. This necessitates continuous updates to the object detector to maintain satisfactory performance. Test-time domain adaptation techniques enable machine learning models to self-adapt based on the distributions of the testing data. However, existing methods mainly focus on fully automated adaptation, which makes sense for applications such as self-driving cars. Despite the prevalence of fully automated approaches, in some applications such as surveillance, there is usually a human operator overseeing the system's operation. We propose to involve the operator in test-time domain adaptation to raise the performance of object detection beyond what is achievable by fully automated adaptation. To reduce manual effort, the proposed method only requires the operator to provide weak labels, which are then used to guide the adaptation process. Furthermore, the proposed method can be performed in a streaming setting, where each online sample is observed only once. We show that the proposed method outperforms existing works, demonstrating a great benefit of human-in-the-loop test-time domain adaptation. Our code is publicly available at https://github.com/dzungdoan6/WSTTA

arXiv:1603.05955

Transferring Learned Microcalcification Group Detection from 2D Mammography to 3D Digital Breast Tomosynthesis Using a Hierarchical Model and Scope-based Normalization Features

A novel hierarchical model is introduced to solve a general problem of detecting groups of similar objects. Under this model, detection of groups is performed in hierarchically organized layers while each layer represents a scope for target objects. The processing of these layers involves sequential extraction of appearance features for an individual object, consistency measurement features for nearby objects, and finally the distribution features for all objects within the group. Using the concept of scope-based normalization, the extracted features not only enhance local contrast of an individual object, but also provide consistent characterization for all related objects. As an example, a microcalcification group detection system for 2D mammography was developed, and then the learned model was transferred to 3D digital breast tomosynthesis without any retraining or fine-tuning. The detection system demonstrated state-of-the-art performance and detected 96% of cancerous lesions at the rate of 1.2 false positives per volume as measured on an independent tomosynthesis test set.

arXiv:2411.19220

Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection

Identifying defects and anomalies in industrial products is a critical quality control task. Traditional manual inspection methods are slow, subjective, and error-prone. In this work, we propose a novel zero-shot training-free approach for automated industrial image anomaly detection using a multimodal machine learning pipeline, consisting of three foundation models. Our method first uses a large language model, i.e., GPT-3. generate text prompts describing the expected appearances of normal and abnormal products. We then use a grounding object detection model, called Grounding DINO, to locate the product in the image. Finally, we compare the cropped product image patches to the generated prompts using a zero-shot image-text matching model, called CLIP, to identify any anomalies. Our experiments on two datasets of industrial product images, namely MVTec-AD and VisA, demonstrate the effectiveness of this method, achieving high accuracy in detecting various types of defects and anomalies without the need for model training. Our proposed model enables efficient, scalable, and objective quality control in industrial manufacturing settings.

arXiv:1708.07522

SPARCNN: SPAtially Related Convolutional Neural Networks

The ability to accurately detect and classify objects at varying pixel sizes in cluttered scenes is crucial to many Navy applications. However, detection performance of existing state-of the-art approaches such as convolutional neural networks (CNNs) degrade and suffer when applied to such cluttered and multi-object detection tasks. We conjecture that spatial relationships between objects in an image could be exploited to significantly improve detection accuracy, an approach that had not yet been considered by any existing techniques (to the best of our knowledge) at the time the research was conducted. We introduce a detection and classification technique called Spatially Related Detection with Convolutional Neural Networks (SPARCNN) that learns and exploits a probabilistic representation of inter-object spatial configurations within images from training sets for more effective region proposals to use with state-of-the-art CNNs. Our empirical evaluation of SPARCNN on the VOC 2007 dataset shows that it increases classification accuracy by 8% when compared to a region proposal technique that does not exploit spatial relations. More importantly, we obtained a higher performance boost of 18.8% when task difficulty in the test set is increased by including highly obscured objects and increased image clutter.

arXiv:1907.01176

Multi-Cue Vehicle Detection for Semantic Video Compression In Georegistered Aerial Videos

Detection of moving objects such as vehicles in videos acquired from an airborne camera is very useful for video analytics applications. Using fast low power algorithms for onboard moving object detection would also provide region of interest-based semantic information for scene content aware image compression. This would enable more efficient and flexible communication link utilization in lowbandwidth airborne cloud computing networks. Despite recent advances in both UAV or drone platforms and imaging sensor technologies, vehicle detection from aerial video remains challenging due to small object sizes, platform motion and camera jitter, obscurations, scene complexity and degraded imaging conditions. This paper proposes an efficient moving vehicle detection pipeline which synergistically fuses both appearance and motion-based detections in a complementary manner using deep learning combined with flux tensor spatio-temporal filtering. Our proposed multi-cue pipeline is able to detect moving vehicles with high precision and recall, while filtering out false positives such as parked vehicles, through intelligent fusion. Experimental results show that incorporating contextual information of moving vehicles enables high semantic compression ratios of over 100:1 with high image fidelity, for better utilization of limited bandwidth air-to-ground network links.

arXiv:1906.06058공식 코드 · Papers with Code

Multi Scale Curriculum CNN for Context-Aware Breast MRI Malignancy Classification

Classification of malignancy for breast cancer and other cancer types is usually tackled as an object detection problem: Individual lesions are first localized and then classified with respect to malignancy. However, the drawback of this approach is that abstract features incorporating several lesions and areas that are not labelled as a lesion but contain global medically relevant information are thus disregarded: especially for dynamic contrast-enhanced breast MRI, criteria such as background parenchymal enhancement and location within the breast are important for diagnosis and cannot be captured by object detection approaches properly. In this work, we propose a 3D CNN and a multi scale curriculum learning strategy to classify malignancy globally based on an MRI of the whole breast. Thus, the global context of the whole breast rather than individual lesions is taken into account. Our proposed approach does not rely on lesion segmentations, which renders the annotation of training data much more effective than in current object detection approaches. Achieving an AUROC of 0.89, we compare the performance of our approach to Mask R-CNN and Retina U-Net as well as a radiologist. Our performance is on par with approaches that, in contrast to our method, rely on pixelwise segmentations of lesions.

arXiv:2005.11475공식 코드 · Papers with Code

Attention-guided Context Feature Pyramid Network for Object Detection

For object detection, how to address the contradictory requirement between feature map resolution and receptive field on high-resolution inputs still remains an open question. In this paper, to tackle this issue, we build a novel architecture, called Attention-guided Context Feature Pyramid Network (AC-FPN), that exploits discriminative information from various large receptive fields via integrating attention-guided multi-path features. The model contains two modules. The first one is Context Extraction Module (CEM) that explores large contextual information from multiple receptive fields. As redundant contextual relations may mislead localization and recognition, we also design the second module named Attention-guided Module (AM), which can adaptively capture the salient dependencies over objects by using the attention mechanism. AM consists of two sub-modules, i.e., Context Attention Module (CxAM) and Content Attention Module (CnAM), which focus on capturing discriminative semantics and locating precise positions, respectively. Most importantly, our AC-FPN can be readily plugged into existing FPN-based models. Extensive experiments on object detection and instance segmentation show that existing models with our proposed CEM and AM significantly surpass their counterparts without them, and our model successfully obtains state-of-the-art results. We have released the source code at https://github.com/Caojunxu/AC-FPN.

arXiv:2101.02190

A Robust Illumination-Invariant Camera System for Agricultural Applications

Object detection and semantic segmentation are two of the most widely adopted deep learning algorithms in agricultural applications. One of the major sources of variability in image quality acquired in the outdoors for such tasks is changing lighting condition that can alter the appearance of the objects or the contents of the entire image. While transfer learning and data augmentation to some extent reduce the need for large amount of data to train deep neural networks, the large variety of cultivars and the lack of shared datasets in agriculture makes wide-scale field deployments difficult. In this paper, we present a high throughput robust active lighting-based camera system that generates consistent images in all lighting conditions. We detail experiments that show the consistency in images quality leading to relatively fewer images to train deep neural networks for the task of object detection. We further present results from field experiment under extreme lighting conditions where images without active lighting significantly lack to provide consistent results. The experimental results show that on average, deep nets for object detection trained on consistent data required nearly four times less data to achieve similar level of accuracy. This proposed work could potentially provide pragmatic solutions to computer vision needs in agriculture.

arXiv:2203.05662공식 코드 · Papers with Code

Point Density-Aware Voxels for LiDAR 3D Object Detection

LiDAR has become one of the primary 3D object detection sensors in autonomous driving. However, LiDAR's diverging point pattern with increasing distance results in a non-uniform sampled point cloud ill-suited to discretized volumetric feature extraction. Current methods either rely on voxelized point clouds or use inefficient farthest point sampling to mitigate detrimental effects caused by density variation but largely ignore point density as a feature and its predictable relationship with distance from the LiDAR sensor. Our proposed solution, Point Density-Aware Voxel network (PDV), is an end-to-end two stage LiDAR 3D object detection architecture that is designed to account for these point density variations. PDV efficiently localizes voxel features from the 3D sparse convolution backbone through voxel point centroids. The spatially localized voxel features are then aggregated through a density-aware RoI grid pooling module using kernel density estimation (KDE) and self-attention with point density positional encoding. Finally, we exploit LiDAR's point density to distance relationship to refine our final bounding box confidences. PDV outperforms all state-of-the-art methods on the Waymo Open Dataset and achieves competitive results on the KITTI dataset. We provide a code release for PDV which is available at https://github.com/TRAILab/PDV.

arXiv:2608.21937v1cs.CV

C$^2$Path: 비전-언어 점진적 객체 검출을 위한 클래스 조건부 경로 분리

C$^2$Path: Class-Conditional Pathway Decoupling for Vision-Language Incremental Object Detection

점진적 객체 검출(Incremental Object Detection, IOD)은 검출기가 이전에 습득한 지식을 보존하면서 새로운 범주를 지속적으로 학습할 수 있도록 하는 것을 목표로 한다. 그러나 기존 방법들은 두 가지 형태의 \textbf{클래스 지식 결합(class knowledge coupling)}, 즉 공유 매개변수 업데이트로 인한 클래스 경계 침식과 혼합된 특징 인코딩에서 비롯되는 클래스 표현 얽힘 문제를 겪는다. 우리는 효과적인 점진적 학습을 위해서는 격리된 매개변수 업데이트와 클래스별로 분리된 주입을 가능하게 하는 클래스 특화 연산 경로가 필요하다고 주장한다. 이를 위해 토큰 수준의 클래스 단서를 활용하여 서로 다른 범주에 대해 전용의 업데이트 가능한 연산 경로를 구축하는, 비전-언어 점진적 객체 검출을 위한 클래스 조건부 경로 분리 프레임워크인 \textbf{C$^2$Path}를 제안한다. 구체적으로 C$^2$Path는 범주 전문가 라이브러리(category expert library)와 클래스 조건부 분리 모듈(class-conditional decoupling module)을 도입한다. 전문가 라이브러리는 범주별 지식을 포착하는 학습 가능한 저랭크 연산 노드로 구성되며, 분리 모듈은 클래스 인식 라우팅 신호를 생성하여 이 전문가들로부터 \textit{ClassLoRA} 어댑터를 동적으로 구성함으로써 범주 간 격리된 업데이트와 분리된 주입을 위한 클래스 특화 연산 경로를 형성한다. 여러 점진적 학습 설정에서 COCO 2017을 이용한 폭넓은 실험을 통해 C$^2$Path가 최신 방법들을 일관되게 능가함을 보이며, 이는 비전-언어 검출기에서 범주를 지속적으로 확장하기 위한 효과적이고 확장 가능한 해법을 제공한다.

arXiv:2302.10624

Self-improving object detection via disagreement reconciliation

Object detectors often experience a drop in performance when new environmental conditions are insufficiently represented in the training data. This paper studies how to automatically fine-tune a pre-existing object detector while exploring and acquiring images in a new environment without relying on human intervention, i.e., in a self-supervised fashion. In our setting, an agent initially explores the environment using a pre-trained off-the-shelf detector to locate objects and associate pseudo-labels. By assuming that pseudo-labels for the same object must be consistent across different views, we devise a novel mechanism for producing refined predictions from the consensus among observations. Our approach improves the off-the-shelf object detector by 2.66% in terms of mAP and outperforms the current state of the art without relying on ground-truth annotations.

arXiv:1911.06849

Curriculum Self-Paced Learning for Cross-Domain Object Detection

Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e.g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN. On top of combining Cycle-GAN transformations and self-paced learning in a smart and efficient way, in this paper, we propose a novel self-paced algorithm that learns from easy to hard. Our method is simple and effective, without any overhead during inference. It uses only pseudo-labels for samples taken from the target domain, i.e. the domain adaptation is unsupervised. We conduct experiments on four cross-domain benchmarks, showing better results than the state of the art. We also perform an ablation study demonstrating the utility of each component in our framework. Additionally, we study the applicability of our framework to other object detectors. Furthermore, we compare our difficulty measure with other measures from the related literature, proving that it yields superior results and that it correlates well with the performance metric.

arXiv:2212.11172공식 코드 · Papers with Code

A recurrent CNN for online object detection on raw radar frames

Automotive radar sensors provide valuable information for advanced driving assistance systems (ADAS). Radars can reliably estimate the distance to an object and the relative velocity, regardless of weather and light conditions. However, radar sensors suffer from low resolution and huge intra-class variations in the shape of objects. Exploiting the time information (e.g., multiple frames) has been shown to help to capture better the dynamics of objects and, therefore, the variation in the shape of objects. Most temporal radar object detectors use 3D convolutions to learn spatial and temporal information. However, these methods are often non-causal and unsuitable for real-time applications. This work presents RECORD, a new recurrent CNN architecture for online radar object detection. We propose an end-to-end trainable architecture mixing convolutions and ConvLSTMs to learn spatio-temporal dependencies between successive frames. Our model is causal and requires only the past information encoded in the memory of the ConvLSTMs to detect objects. Our experiments show such a method's relevance for detecting objects in different radar representations (range-Doppler, range-angle) and outperform state-of-the-art models on the ROD2021 and CARRADA datasets while being less computationally expensive.

arXiv:2606.11546v1cs.CV

VL-DINO: 오픈 어휘 객체 검출을 위한 CLIP 비전-언어 지식 활용

VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio

CLIP과 같은 비전-언어 모델은 오픈 어휘 객체 검출(object detection)을 위해 풍부한 의미적 사전(semantic priors)을 제공할 수 있습니다. 그러나 텍스트와 시각 지식을 검출 아키텍처에 공동으로 통합하는 것은 여전히 어려운 과제입니다. 본 논문에서는 CLIP의 비전-언어 지식을 더 효과적인 활용(exploitation)을 통해 DINO를 강화한 오픈 어휘 검출기인 VL-DINO를 제안합니다. 구체적으로, 쿼리 기반 양성 샘플 구성(QPSC) 모듈을 먼저 개발하여 추가적인 고품질 양성 샘플을 구성합니다. 이는 기본 DINO 프레임워크가 이기종 데이터 소스 간의 혼합 학습(training)을 더 잘 수용하도록 하면서 더 많은 비전-언어 정렬(alignment) 신호를 제공하여, 학습 과정에서 더 풍부한 텍스트 지식을 통합할 수 있게 합니다. 이어 비전 시맨틱 인코더(VSE) 모듈을 도입하여 CLIP 시각 지식을 백본에서 추출된 특징으로 증류(distill)하고, 후속 인코더 정제를 위한 융합 특징을 생성합니다. 융합 특징을 기반으로 객체 영역 시맨틱 정렬(ORSA) 모듈은 객체 중심 영역 특징을 추출하고 이를 해당 텍스트 임베딩과 정렬하여 텍스트 단서를 추가로 통합합니다. 제로샷(zero-shot) 설정에서 VL-DINO-T와 VL-DINO-L은 각각 LVIS 벤치마크에서 36.3과 38.1 AP를 달성하여 기존의 고급 방법들을 일관되게 능가합니다. 광범위한 실험을 통해 제안된 설계의 효과와 경쟁력 있는 성능을 입증합니다.

arXiv:2406.19407

YOLO11 to Its Genesis: A Decadal and Comprehensive Review of The You Only Look Once (YOLO) Series

Given the rapid emergence and applications of Large Language This review systematically examines the progression of the You Only Look Once (YOLO) object detection algorithms from YOLOv1 to the recently unveiled YOLO11 (or YOLOv11). Employing a reverse chronological analysis, this study examines the advancements introduced by YOLO algorithms, beginning with YOLOv11 and progressing through YOLOv10, YOLOv9, YOLOv8, and subsequent versions to explore each version's contributions to enhancing speed, detection accuracy, and computational efficiency in real-time object detection. By detailing the incremental technological advancements in subsequent YOLO versions, this review chronicles the evolution of YOLO, and discusses the challenges and limitations in each earlier versions. The evolution signifies a path towards integrating YOLO with multimodal, context-aware, and Artificial General Intelligence (AGI) systems for the next YOLO decade, promising significant implications for future developments in AI-driven applications. YOLOV11 to YOLOv1