PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2409.04817공식 코드 · Papers with Code

SSFam: Scribble Supervised Salient Object Detection Family

Scribble supervised salient object detection (SSSOD) constructs segmentation ability of attractive objects from surroundings under the supervision of sparse scribble labels. For the better segmentation, depth and thermal infrared modalities serve as the supplement to RGB images in the complex scenes. Existing methods specifically design various feature extraction and multi-modal fusion strategies for RGB, RGB-Depth, RGB-Thermal, and Visual-Depth-Thermal image input respectively, leading to similar model flood. As the recently proposed Segment Anything Model (SAM) possesses extraordinary segmentation and prompt interactive capability, we propose an SSSOD family based on SAM, named SSFam, for the combination input with different modalities. Firstly, different modal-aware modulators are designed to attain modal-specific knowledge which cooperates with modal-agnostic information extracted from the frozen SAM encoder for the better feature ensemble. Secondly, a siamese decoder is tailored to bridge the gap between the training with scribble prompt and the testing with no prompt for the stronger decoding ability. Our model demonstrates the remarkable performance among combinations of different modalities and refreshes the highest level of scribble supervised methods and comes close to the ones of fully supervised methods. https://github.com/liuzywen/SSFam

arXiv:2503.10210

TARS: Traffic-Aware Radar Scene Flow Estimation

Scene flow provides crucial motion information for autonomous driving. Recent LiDAR scene flow models utilize the rigid-motion assumption at the instance level, assuming objects are rigid bodies. However, these instance-level methods are not suitable for sparse radar point clouds. In this work, we present a novel $\textbf{T}$raffic-$\textbf{A}$ware $\textbf{R}$adar $\textbf{S}$cene flow estimation method, named $\textbf{TARS}$, which utilizes the motion rigidity at the traffic level. To address the challenges in radar scene flow, we perform object detection and scene flow jointly and boost the latter. We incorporate the feature map from the object detector, trained with detection losses, to make radar scene flow aware of the environment and road users. Therefrom, we construct a Traffic Vector Field (TVF) in the feature space, enabling a holistic traffic-level scene understanding in our scene flow branch. When estimating the scene flow, we consider both point-level motion cues from point neighbors and traffic-level consistency of rigid motion within the space. TARS outperforms the state of the art on a proprietary dataset and the View-of-Delft dataset, improving the benchmarks by 23% and 15%, respectively.

arXiv:2503.12490

GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing

The application of Vision-Language Models (VLMs) in remote sensing (RS) has demonstrated significant potential in traditional tasks such as scene classification, object detection, and image captioning. However, current models, which excel in Referring Expression Comprehension (REC), struggle with tasks involving complex instructions (e.g., exists multiple conditions) or pixel-level operations like segmentation and change detection. In this white paper, we provide a comprehensive hierarchical summary of vision-language tasks in RS, categorized by the varying levels of cognitive capability required. We introduce the Remote Sensing Vision-Language Task Set (RSVLTS), which includes Open-Vocabulary Tasks (OVT), Referring Expression Tasks (RET), and Described Object Tasks (DOT) with increased difficulty, and Visual Question Answering (VQA) aloneside. Moreover, we propose a novel unified data representation using a set-of-points approach for RSVLTS, along with a condition parser and a self-augmentation strategy based on cyclic referring. These features are integrated into the GeoRSMLLM model, and this enhanced model is designed to handle a broad range of tasks of RSVLTS, paving the way for a more generalized solution for vision-language tasks in geoscience and remote sensing.

arXiv:2505.14239

Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation

This paper focus on few-shot object detection~(FSOD) and instance segmentation~(FSIS), which requires a model to quickly adapt to novel classes with a few labeled instances. The existing methods severely suffer from bias classification because of the missing label issue which naturally exists in an instance-level few-shot scenario and is first formally proposed by us. Our analysis suggests that the standard classification head of most FSOD or FSIS models needs to be decoupled to mitigate the bias classification. Therefore, we propose an embarrassingly simple but effective method that decouples the standard classifier into two heads. Then, these two individual heads are capable of independently addressing clear positive samples and noisy negative samples which are caused by the missing label. In this way, the model can effectively learn novel classes while mitigating the effects of noisy negative samples. Without bells and whistles, our model without any additional computation cost and parameters consistently outperforms its baseline and state-of-the-art by a large margin on PASCAL VOC and MS-COCO benchmarks for FSOD and FSIS tasks. The Code is available at https://csgaobb.github.io/Projects/DCFS.

arXiv:2611.24726v1cs.CV

역사 문서의 HTR을 위한 텍스트 줄 분할의 일반화

Generalization of Text Line Segmentation for HTR in Historical Documents

본 논문에서는 역사 문서의 텍스트 줄을 자동으로 분할하기 위한 최신 객체 탐지 모델(Hi-SAM, YOLO, RT-DETR)의 일반화 능력을 조사한다. 박물관과 기록 보관소가 새로운 컬렉션마다 대량의 레이블 표본을 만드는 것은 현실적이지 않으므로 일반화가 필요하다. 또한 대상 데이터셋당 소수의 학습 표본만으로 네트워크를 미세 조정하는 퓨샷 설정도 평가한다. 이를 위해 시각적 레이아웃과 언어가 크게 다른 아홉 개의 데이터셋을 사용한다. 추가로, 객체 탐지의 고전적 평가 지표인 평균 정밀도(mAP)가 텍스트 줄 분할 모델의 품질을 평가하기에 불충분한 이유를 논의한다. 데이터셋에 따라, 우리의 CRNN 모델은 분할된 텍스트 줄에 대해 페이지당 2.48%에서 7.07%의 문자 오류율(CER)을 달성한다. 이는 독해와 간단한 텍스트 검색에 충분한 수준이다. 마지막으로 다양한 사용 사례 설정에서 학습과 추론에 필요한 자원과 시간을 정량화한다. 이는 가용 자원에 따라 모델과 하드웨어를 선택할 때 보다 충분한 정보에 근거한 결정을 내리는 기초가 된다.

arXiv:2311.12430

AR Visualization System for Ship Detection and Recognition Based on AI

Augmented reality technology has been widely used in industrial design interaction, exhibition guide, information retrieval and other fields. The combination of artificial intelligence and augmented reality technology has also become a future development trend. This project is an AR visualization system for ship detection and recognition based on AI, which mainly includes three parts: artificial intelligence module, Unity development module and Hololens2AR module. This project is based on R3Det algorithm to complete the detection and recognition of ships in remote sensing images. The recognition rate of model detection trained on RTX 2080Ti can reach 96%. Then, the 3D model of the ship is obtained by ship categories and information and generated in the virtual scene. At the same time, voice module and UI interaction module are added. Finally, we completed the deployment of the project on Hololens2 through MRTK. The system realizes the fusion of computer vision and augmented reality technology, which maps the results of object detection to the AR field, and makes a brave step toward the future technological trend and intelligent application.

arXiv:2410.22451

Addressing Issues with Working Memory in Video Object Segmentation

Contemporary state-of-the-art video object segmentation (VOS) models compare incoming unannotated images to a history of image-mask relations via affinity or cross-attention to predict object masks. We refer to the internal memory state of the initial image-mask pair and past image-masks as a working memory buffer. While the current state of the art models perform very well on clean video data, their reliance on a working memory of previous frames leaves room for error. Affinity-based algorithms include the inductive bias that there is temporal continuity between consecutive frames. To account for inconsistent camera views of the desired object, working memory models need an algorithmic modification that regulates the memory updates and avoid writing irrelevant frames into working memory. A simple algorithmic change is proposed that can be applied to any existing working memory-based VOS model to improve performance on inconsistent views, such as sudden camera cuts, frame interjections, and extreme context changes. The resulting model performances show significant improvement on video data with these frame interjections over the same model without the algorithmic addition. Our contribution is a simple decision function that determines whether working memory should be updated based on the detection of sudden, extreme changes and the assumption that the object is no longer in frame. By implementing algorithmic changes, such as this, we can increase the real-world applicability of current VOS models.

arXiv:1511.06147

Coreset-Based Adaptive Tracking

We propose a method for learning from streaming visual data using a compact, constant size representation of all the data that was seen until a given moment. Specifically, we construct a 'coreset' representation of streaming data using a parallelized algorithm, which is an approximation of a set with relation to the squared distances between this set and all other points in its ambient space. We learn an adaptive object appearance model from the coreset tree in constant time and logarithmic space and use it for object tracking by detection. Our method obtains excellent results for object tracking on three standard datasets over more than 100 videos. The ability to summarize data efficiently makes our method ideally suited for tracking in long videos in presence of space and time constraints. We demonstrate this ability by outperforming a variety of algorithms on the TLD dataset with 2685 frames on average. This coreset based learning approach can be applied for both real-time learning of small, varied data and fast learning of big data.

arXiv:2105.14370

BAAI-VANJEE Roadside Dataset: Towards the Connected Automated Vehicle Highway technologies in Challenging Environments of China

As the roadside perception plays an increasingly significant role in the Connected Automated Vehicle Highway(CAVH) technologies, there are immediate needs of challenging real-world roadside datasets for bench marking and training various computer vision tasks such as 2D/3D object detection and multi-sensor fusion. In this paper, we firstly introduce a challenging BAAI-VANJEE roadside dataset which consist of LiDAR data and RGB images collected by VANJEE smart base station placed on the roadside about 4.5m high. This dataset contains 2500 frames of LiDAR data, 5000 frames of RGB images, including 20% collected at the same time. It also contains 12 classes of objects, 74K 3D object annotations and 105K 2D object annotations. By providing a real complex urban intersections and highway scenes, we expect the BAAI-VANJEE roadside dataset will actively assist the academic and industrial circles to accelerate the innovation research and achievement transformation in the field of intelligent transportation in big data era.

arXiv:2110.11679

Depth-only Object Tracking

Depth (D) indicates occlusion and is less sensitive to illumination changes, which make depth attractive modality for Visual Object Tracking (VOT). Depth is used in RGBD object tracking where the best trackers are deep RGB trackers with additional heuristic using depth maps. There are two potential reasons for the heuristics: 1) the lack of large RGBD tracking datasets to train deep RGBD trackers and 2) the long-term evaluation protocol of VOT RGBD that benefits from heuristics such as depth-based occlusion detection. In this work, we study how far D-only tracking can go if trained with large amounts of depth data. To compensate the lack of depth data, we generate depth maps for tracking. We train a "Depth-DiMP" from the scratch with the generated data and fine-tune it with the available small RGBD tracking datasets. The depth-only DiMP achieves good accuracy in depth-only tracking and combined with the original RGB DiMP the end-to-end trained RGBD-DiMP outperforms the recent VOT 2020 RGBD winners.

arXiv:2409.13687

A Bottom-Up Approach to Class-Agnostic Image Segmentation

Class-agnostic image segmentation is a crucial component in automating image editing workflows, especially in contexts where object selection traditionally involves interactive tools. Existing methods in the literature often adhere to top-down formulations, following the paradigm of class-based approaches, where object detection precedes per-object segmentation. In this work, we present a novel bottom-up formulation for addressing the class-agnostic segmentation problem. We supervise our network directly on the projective sphere of its feature space, employing losses inspired by metric learning literature as well as losses defined in a novel segmentation-space representation. The segmentation results are obtained through a straightforward mean-shift clustering of the estimated features. Our bottom-up formulation exhibits exceptional generalization capability, even when trained on datasets designed for class-based segmentation. We further showcase the effectiveness of our generic approach by addressing the challenging task of cell and nucleus segmentation. We believe that our bottom-up formulation will offer valuable insights into diverse segmentation challenges in the literature.

arXiv:2312.01117공식 코드 · Papers with Code

Paved2Paradise: Cost-Effective and Scalable LiDAR Simulation by Factoring the Real World

To achieve strong real world performance, neural networks must be trained on large, diverse datasets; however, obtaining and annotating such datasets is costly and time-consuming, particularly for 3D point clouds. In this paper, we describe Paved2Paradise, a simple, cost-effective approach for generating fully labeled, diverse, and realistic lidar datasets from scratch, all while requiring minimal human annotation. Our key insight is that, by deliberately collecting separate "background" and "object" datasets (i.e., "factoring the real world"), we can intelligently combine them to produce a combinatorially large and diverse training set. The Paved2Paradise pipeline thus consists of four steps: (1) collecting copious background data, (2) recording individuals from the desired object class(es) performing different behaviors in an isolated environment (like a parking lot), (3) bootstrapping labels for the object dataset, and (4) generating samples by placing objects at arbitrary locations in backgrounds. To demonstrate the utility of Paved2Paradise, we generated synthetic datasets for two tasks: (1) human detection in orchards (a task for which no public data exists) and (2) pedestrian detection in urban environments. Qualitatively, we find that a model trained exclusively on Paved2Paradise synthetic data is highly effective at detecting humans in orchards, including when individuals are heavily occluded by tree branches. Quantitatively, a model trained on Paved2Paradise data that sources backgrounds from KITTI performs comparably to a model trained on the actual dataset. These results suggest the Paved2Paradise synthetic data pipeline can help accelerate point cloud model development in sectors where acquiring lidar datasets has previously been cost-prohibitive.

arXiv:2312.01060공식 코드 · Papers with Code

Spectrum-driven Mixed-frequency Network for Hyperspectral Salient Object Detection

Hyperspectral salient object detection (HSOD) aims to detect spectrally salient objects in hyperspectral images (HSIs). However, existing methods inadequately utilize spectral information by either converting HSIs into false-color images or converging neural networks with clustering. We propose a novel approach that fully leverages the spectral characteristics by extracting two distinct frequency components from the spectrum: low-frequency Spectral Saliency and high-frequency Spectral Edge. The Spectral Saliency approximates the region of salient objects, while the Spectral Edge captures edge information of salient objects. These two complementary components, crucial for HSOD, are derived by computing from the inter-layer spectral angular distance of the Gaussian pyramid and the intra-neighborhood spectral angular gradients, respectively. To effectively utilize this dual-frequency information, we introduce a novel lightweight Spectrum-driven Mixed-frequency Network (SMN). SMN incorporates two parameter-free plug-and-play operators, namely Spectral Saliency Generator and Spectral Edge Operator, to extract the Spectral Saliency and Spectral Edge components from the input HSI independently. Subsequently, the Mixed-frequency Attention module, comprised of two frequency-dependent heads, intelligently combines the embedded features of edge and saliency information, resulting in a mixed-frequency feature representation. Furthermore, a saliency-edge-aware decoder progressively scales up the mixed-frequency feature while preserving rich detail and saliency information for accurate salient object prediction. Extensive experiments conducted on the HS-SOD benchmark and our custom dataset HSOD-BIT demonstrate that our SMN outperforms state-of-the-art methods regarding HSOD performance. Code and dataset will be available at https://github.com/laprf/SMN.

arXiv:1812.07762

Real-Time, Highly Accurate Robotic Grasp Detection using Fully Convolutional Neural Network with Rotation Ensemble Module

Rotation invariance has been an important topic in computer vision tasks. Ideally, robot grasp detection should be rotation-invariant. However, rotation-invariance in robotic grasp detection has been only recently studied by using rotation anchor box that are often time-consuming and unreliable for multiple objects. In this paper, we propose a rotation ensemble module (REM) for robotic grasp detection using convolutions that rotates network weights. Our proposed REM was able to outperform current state-of-the-art methods by achieving up to 99.2% (image-wise), 98.6% (object-wise) accuracies on the Cornell dataset with real-time computation (50 frames per second). Our proposed method was also able to yield reliable grasps for multiple objects and up to 93.8% success rate for the real-time robotic grasping task with a 4-axis robot arm for small novel objects that was significantly higher than the baseline methods by 11-56%.

arXiv:2105.04322

RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation

Existing online multiple object tracking (MOT) algorithms often consist of two subtasks, detection and re-identification (ReID). In order to enhance the inference speed and reduce the complexity, current methods commonly integrate these double subtasks into a unified framework. Nevertheless, detection and ReID demand diverse features. This issue would result in an optimization contradiction during the training procedure. With the target of alleviating this contradiction, we devise a module named Global Context Disentangling (GCD) that decouples the learned representation into detection-specific and ReID-specific embeddings. As such, this module provides an implicit manner to balance the different requirements of these two subtasks. Moreover, we observe that preceding MOT methods typically leverage local information to associate the detected targets and neglect to consider the global semantic relation. To resolve this restriction, we develop a module, referred to as Guided Transformer Encoder (GTE), by combining the powerful reasoning ability of Transformer encoder and deformable attention. Unlike previous works, GTE avoids analyzing all the pixels and only attends to capture the relation between query nodes and a few self-adaptively selected key samples. Therefore, it is computationally efficient. Extensive experiments have been conducted on the MOT16, MOT17 and MOT20 benchmarks to demonstrate the superiority of the proposed MOT framework, namely RelationTrack. The experimental results indicate that RelationTrack has surpassed preceding methods significantly and established a new state-of-the-art performance, e.g., IDF1 of 70.5% and MOTA of 67.2% on MOT20.

arXiv:2609.01738v1cs.CV

비활성 폭발물 선별을 위한 UAV 열화상 영상: 다중 캠페인 데이터셋 구축, 객체 검출, 그리고 실용적 권고사항

UAV Thermal Imagery for Inert Ordnance Screening: Multi Campaign Dataset Development,Object Detection, and Practical Recommendations

불발탄(UXO)은 전 세계 오염 지역에서 민간인의 접근, 농업 활동, 기반 시설 복구, 환경 정화를 계속해서 제한하고 있다. 본 연구는 비활성 폭발물에 대한 다중 캠페인 UAV 열화상 이미지 데이터셋을 구축하고, 수집한 영상으로부터 레이블이 지정된 이미지 세트를 만들었으며, 객체 검출 모델을 테스트하고, 인도적 지뢰 제거 활동 및 지뢰 제거 응용을 위한 실용적 고려 사항을 도출하였다. 데이터는 테네시에서 여름과 겨울 조건에서 진행된 네 차례의 현장 캠페인 동안 수집되었으며, 비활성 지뢰, 탄약, 기타 폭발물을 짧은 풀, 키 큰 식생, 자갈, 멀칭재, 암석, 퇴비, 다져진 지표면에 배치하였다. 열화상 영상은 33 m와 15 m의 비행 고도에서 수집되었다. 최종 원본 목록에는 양성 이미지 918장과 배경 이미지 4,937장을 포함하여 총 5,855개의 열화상 이미지-레이블 쌍이 있었다. 모든 양성 이미지를 유지하고 배경 이미지를 다운샘플링한 후, 33 m 데이터셋은 학습 이미지 420장과 검증 이미지 106장을, 15 m 데이터셋은 학습 이미지 629장과 검증 이미지 157장을 포함하였다. 자동화된 후보 검출 모델을 개발하기 위해 YOLOV11l과 RT-DETR-R50 알고리즘을 학습하고 평가하였다. 실용적 권고사항으로는 열화상과 RGB 영상을 함께 수집할 것, 다양한 지표면과 배경만 있는 이미지를 포함할 것, 태양 노출 변화 이후의 시간대를 고려할 것, 조사 범위와 대상 픽셀 표현 사이의 균형을 맞출 것, 대표성 있는 현지 데이터로 모델을 보정할 것, 자격을 갖춘 사람의 검토를 유지할 것 등이 있다. 본 연구의 의도된 용도는 후속 기술 조사 또는 EOD(폭발물 처리) 평가를 위한 선별 및 우선순위 지정이며, 단독 제거 작업을 위한 것이 아니다.

arXiv:1707.02069

A spatiotemporal model with visual attention for video classification

High level understanding of sequential visual input is important for safe and stable autonomy, especially in localization and object detection. While traditional object classification and tracking approaches are specifically designed to handle variations in rotation and scale, current state-of-the-art approaches based on deep learning achieve better performance. This paper focuses on developing a spatiotemporal model to handle videos containing moving objects with rotation and scale changes. Built on models that combine Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to classify sequential data, this work investigates the effectiveness of incorporating attention modules in the CNN stage for video classification. The superiority of the proposed spatiotemporal model is demonstrated on the Moving MNIST dataset augmented with rotation and scaling.

arXiv:2301.07666

DDS: Decoupled Dynamic Scene-Graph Generation Network

Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data. Existing methods show poor performance in detecting triplets outside of a predefined set, primarily due to their reliance on dependent feature learning. To address this issue, we propose DDS -- a decoupled dynamic scene-graph generation network -- that consists of two independent branches that can disentangle extracted features. The key innovation of the current paper is the decoupling of the features representing the relationships from those of the objects, which enables the detection of novel object-relationship combinations. The DDS model is evaluated on three datasets and outperforms previous methods by a significant margin, especially in detecting previously unseen triplets.

arXiv:2409.10716

Online Learning via Memory: Retrieval-Augmented Detector Adaptation

This paper presents a novel way of online adapting any off-the-shelf object detection model to a novel domain without retraining the detector model. Inspired by how humans quickly learn knowledge of a new subject (e.g., memorization), we allow the detector to look up similar object concepts from memory during test time. This is achieved through a retrieval augmented classification (RAC) module together with a memory bank that can be flexibly updated with new domain knowledge. We experimented with various off-the-shelf open-set detector and close-set detectors. With only a tiny memory bank (e.g., 10 images per category) and being training-free, our online learning method could significantly outperform baselines in adapting a detector to novel domains.

arXiv:2412.04114

Thermal and RGB Images Work Better Together in Wind Turbine Damage Detection

The inspection of wind turbine blades (WTBs) is crucial for ensuring their structural integrity and operational efficiency. Traditional inspection methods can be dangerous and inefficient, prompting the use of unmanned aerial vehicles (UAVs) that access hard-to-reach areas and capture high-resolution imagery. In this study, we address the challenge of enhancing defect detection on WTBs by integrating thermal and RGB images obtained from UAVs. We propose a multispectral image composition method that combines thermal and RGB imagery through spatial coordinate transformation, key point detection, binary descriptor creation, and weighted image overlay. Using a benchmark dataset of WTB images annotated for defects, we evaluated several state-of-the-art object detection models. Our results show that composite images significantly improve defect detection efficiency. Specifically, the YOLOv8 model's accuracy increased from 91% to 95%, precision from 89% to 94%, recall from 85% to 92%, and F1-score from 87% to 93%. The number of false positives decreased from 6 to 3, and missed defects reduced from 5 to 2. These findings demonstrate that integrating thermal and RGB imagery enhances defect detection on WTBs, contributing to improved maintenance and reliability.