PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1908.01975

Contour Loss: Boundary-Aware Learning for Salient Object Segmentation

We present a learning model that makes full use of boundary information for salient object segmentation. Specifically, we come up with a novel loss function, i.e., Contour Loss, which leverages object contours to guide models to perceive salient object boundaries. Such a boundary-aware network can learn boundary-wise distinctions between salient objects and background, hence effectively facilitating the saliency detection. Yet the Contour Loss emphasizes on the local saliency. We further propose the hierarchical global attention module (HGAM), which forces the model hierarchically attend to global contexts, thus captures the global visual saliency. Comprehensive experiments on six benchmark datasets show that our method achieves superior performance over state-of-the-art ones. Moreover, our model has a real-time speed of 26 fps on a TITAN X GPU.

arXiv:2407.06780공식 코드 · Papers with Code

CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection

The depth/thermal information is beneficial for detecting salient object with conventional RGB images. However, in dual-modal salient object detection (SOD) model, the robustness against noisy inputs and modality missing is crucial but rarely studied. To tackle this problem, we introduce \textbf{Co}nditional Dropout and \textbf{LA}nguage-driven(\textbf{CoLA}) framework comprising two core components. 1) Language-driven Quality Assessment (LQA): Leveraging a pretrained vision-language model with a prompt learner, the LQA recalibrates image contributions without requiring additional quality annotations. This approach effectively mitigates the impact of noisy inputs. 2) Conditional Dropout (CD): A learning method to strengthen the model's adaptability in scenarios with missing modalities, while preserving its performance under complete modalities. The CD serves as a plug-in training scheme that treats modality-missing as conditions, strengthening the overall robustness of various dual-modal SOD models. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art dual-modal SOD models, under both modality-complete and modality-missing conditions. We will release source code upon acceptance.

arXiv:2609.24668v1cs.CV

Ev-YOLO: 통합 증거 공식화를 통한 불확실성 인식 객체 검출

Ev-YOLO: Uncertainty-Aware Object Detection via a Unified Evidential Formulation

불확실한 환경에서 동작하는 자율 시스템에 객체 검출기를 배포하려면 신뢰할 수 있는 불확실성 추정이 필수적이다. 증거 심층 학습(Evidential Deep Learning, EDL)은 네트워크 출력을 증거(evidence)로 표현하고 주관 논리(subjective logic)를 통해 예측을 해석함으로써 불확실성 인식 분류를 위한 원칙적인 프레임워크를 제공한다. 그러나 기존 증거 기반 객체 검출기는 일반적으로 동일한 이론적 기반을 공유하지 않는 회귀(regression) 불확실성 모델과 증거적 분류를 결합한다. 본 연구에서는 분류와 바운딩 박스(bounding-box) 회귀를 모두 공통의 증거 프레임워크 안에서 공식화한 YOLOv8의 증거적 버전을 제안한다. 우리 접근법은 YOLOv8의 분포 기반 바운딩 박스 표현을 활용하여 증거 공식화를 분류뿐 아니라 위치 추정(localisation)에도 적용할 수 있게 한다. 그 결과 두 과제 모두 Dempster–Shafer 프레임워크 내에서 해석할 수 있는 믿음(belief), 불확실ity, 확률 추정치를 생성한다. KITTI, MUSES, nuScenes에서의 실험은 결과 검출기가 검출 정확도 측면에서 표준 YOLOv8과 대체로 경쟁력을 유지하면서, 올바른 검출과 잘못된 검출을 효과적으로 구별하는 위치 추정 불확실성을 제공함을 보여준다. 또한 이 불확실성은 도메인 이동(domain shift) 하에서 점점 더 변별력을 갖게 된다.

arXiv:1801.02031

ReMotENet: Efficient Relevant Motion Event Detection for Large-scale Home Surveillance Videos

This paper addresses the problem of detecting relevant motion caused by objects of interest (e.g., person and vehicles) in large scale home surveillance videos. The traditional method usually consists of two separate steps, i.e., detecting moving objects with background subtraction running on the camera, and filtering out nuisance motion events (e.g., trees, cloud, shadow, rain/snow, flag) with deep learning based object detection and tracking running on cloud. The method is extremely slow and therefore not cost effective, and does not fully leverage the spatial-temporal redundancies with a pre-trained off-the-shelf object detector. To dramatically speedup relevant motion event detection and improve its performance, we propose a novel network for relevant motion event detection, ReMotENet, which is a unified, end-to-end data-driven method using spatial-temporal attention-based 3D ConvNets to jointly model the appearance and motion of objects-of-interest in a video. ReMotENet parses an entire video clip in one forward pass of a neural network to achieve significant speedup. Meanwhile, it exploits the properties of home surveillance videos, e.g., relevant motion is sparse both spatially and temporally, and enhances 3D ConvNets with a spatial-temporal attention model and reference-frame subtraction to encourage the network to focus on the relevant moving objects. Experiments demonstrate that our method can achieve comparable or event better performance than the object detection based method but with three to four orders of magnitude speedup (up to 20k times) on GPU devices. Our network is efficient, compact and light-weight. It can detect relevant motion on a 15s surveillance video clip within 4-8 milliseconds on a GPU and a fraction of second (0.17-0.39) on a CPU with a model size of less than 1MB.

arXiv:2104.06476공식 코드 · Papers with Code

Incremental Multi-Target Domain Adaptation for Object Detection with Efficient Domain Transfer

Recent advances in unsupervised domain adaptation have significantly improved the recognition accuracy of CNNs by alleviating the domain shift between (labeled) source and (unlabeled) target data distributions. While the problem of single-target domain adaptation (STDA) for object detection has recently received much attention, multi-target domain adaptation (MTDA) remains largely unexplored, despite its practical relevance in several real-world applications, such as multi-camera video surveillance. Compared to the STDA problem that may involve large domain shifts between complex source and target distributions, MTDA faces additional challenges, most notably the computational requirements and catastrophic forgetting of previously-learned targets, which can depend on the order of target adaptations. STDA for detection can be applied to MTDA by adapting one model per target, or one common model with a mixture of data from target domains. However, these approaches are either costly or inaccurate. The only state-of-art MTDA method specialized for detection learns targets incrementally, one target at a time, and mitigates the loss of knowledge by using a duplicated detection model for knowledge distillation, which is computationally expensive and does not scale well to many domains. In this paper, we introduce an efficient approach for incremental learning that generalizes well to multiple target domains. Our MTDA approach is more suitable for real-world applications since it allows updating the detection model incrementally, without storing data from previous-learned target domains, nor retraining when a new target domain becomes available. Our proposed method, MTDA-DTM, achieved the highest level of detection accuracy compared against state-of-the-art approaches on several MTDA detection benchmarks and Wildtrack, a benchmark for multi-camera pedestrian detection.

arXiv:2001.10692공식 코드 · Papers with Code

ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes

3D object detection has seen quick progress thanks to advances in deep learning on point clouds. A few recent works have even shown state-of-the-art performance with just point clouds input (e.g. VoteNet). However, point cloud data have inherent limitations. They are sparse, lack color information and often suffer from sensor noise. Images, on the other hand, have high resolution and rich texture. Thus they can complement the 3D geometry provided by point clouds. Yet how to effectively use image information to assist point cloud based detection is still an open question. In this work, we build on top of VoteNet and propose a 3D detection architecture called ImVoteNet specialized for RGB-D scenes. ImVoteNet is based on fusing 2D votes in images and 3D votes in point clouds. Compared to prior work on multi-modal detection, we explicitly extract both geometric and semantic features from the 2D images. We leverage camera parameters to lift these features to 3D. To improve the synergy of 2D-3D feature fusion, we also propose a multi-tower training scheme. We validate our model on the challenging SUN RGB-D dataset, advancing state-of-the-art results by 5.7 mAP. We also provide rich ablation studies to analyze the contribution of each design choice.

논문 ID: document/1033571

An Object Fine-Grained Change Detection Method Based on Frequency Decoupling Interaction for High-Resolution Remote Sensing Images

Change detection is a prominent research direction in the field of remote sensing image processing. However, most current change detection methods focus solely on detecting changes without being able to differentiate the types of changes, such as “appear” or “disappear” of objects. Accurate detection of change types is of great significance in guiding decisionmaking processes. To address this issue, this article introduces the object fine-grained change detection (OFCD) task and proposes a method based on frequency decoupling interaction (FDINet). Specifically, in order to enhance the model’s ability to detect change types and improve its robustness to temporal information, a temporal exchange framework is designed. Additionally, to better capture spatial–temporal correlation in bi-temporal features, a wavelet interaction module (WIM) is proposed. This module utilizes wavelet transform for frequency decoupling, separating features into different components based on their frequency magnitudes. Then the module applies different interaction methods according to the characteristics of these frequency components. Finally, to aggregate complementary information from different-scale feature maps and enhance the representational capabilities of the extracted features, a feature aggregation and upsampling module (FAUM) is adopted. A series of experiments show the superiority of FDINet over most stateof-the-art methods, achieving good results on three different datasets.

arXiv:2306.15416

Irregular Change Detection in Sparse Bi-Temporal Point Clouds using Learned Place Recognition Descriptors and Point-to-Voxel Comparison

Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments. This article proposes an innovative approach for change detection in 3D point clouds using deep learned place recognition descriptors and irregular object extraction based on voxel-to-point comparison. The proposed method first aligns the bi-temporal point clouds using a map-merging algorithm in order to establish a common coordinate frame. Then, it utilizes deep learning techniques to extract robust and discriminative features from the 3D point cloud scans, which are used to detect changes between consecutive point cloud frames and therefore find the changed areas. Finally, the altered areas are sampled and compared between the two time instances to extract any obstructions that caused the area to change. The proposed method was successfully evaluated in real-world field experiments, where it was able to detect different types of changes in 3D point clouds, such as object or muck-pile addition and displacement, showcasing the effectiveness of the approach. The results of this study demonstrate important implications for various applications, including safety and security monitoring in construction sites, mapping and exploration and suggests potential future research directions in this field.

arXiv:2306.16718

Metric-aligned Sample Selection and Critical Feature Sampling for Oriented Object Detection

Arbitrary-oriented object detection is a relatively emerging but challenging task. Although remarkable progress has been made, there still remain many unsolved issues due to the large diversity of patterns in orientation, scale, aspect ratio, and visual appearance of objects in aerial images. Most of the existing methods adopt a coarse-grained fixed label assignment strategy and suffer from the inconsistency between the classification score and localization accuracy. First, to align the metric inconsistency between sample selection and regression loss calculation caused by fixed IoU strategy, we introduce affine transformation to evaluate the quality of samples and propose a distance-based label assignment strategy. The proposed metric-aligned selection (MAS) strategy can dynamically select samples according to the shape and rotation characteristic of objects. Second, to further address the inconsistency between classification and localization, we propose a critical feature sampling (CFS) module, which performs localization refinement on the sampling location for classification task to extract critical features accurately. Third, we present a scale-controlled smooth $L_1$ loss (SC-Loss) to adaptively select high quality samples by changing the form of regression loss function based on the statistics of proposals during training. Extensive experiments are conducted on four challenging rotated object detection datasets DOTA, FAIR1M-1.0, HRSC2016, and UCAS-AOD. The results show the state-of-the-art accuracy of the proposed detector.

arXiv:2501.07101

Dual Scale-aware Adaptive Masked Knowledge Distillation for Object Detection

Recent feature masking knowledge distillation methods make use of attention mechanisms to identify either important spatial regions or channel clues for discriminative feature reconstruction. However, most of existing strategies perform global attention-guided feature masking distillation without delving into fine-grained visual clues in feature maps. In particular, uncovering locality-aware clues across different scales are conducive to reconstructing region-aware features, thereby significantly benefiting distillation performance. In this study, we propose a fine-grained adaptive feature masking distillation framework for accurate object detection. Different from previous methods in which global masking is performed on single-scale feature maps, we explore the scale-aware feature masking by performing feature distillation across various scales, such that the object-aware locality is encoded for improved feature reconstruction. In addition, our fine-grained feature distillation strategy is combined with a masking logits distillation scheme in which logits difference between teacher and student networks is utilized to guide the distillation process. Thus, it can help the student model to better learn from the teacher counterpart with improved knowledge transfer. Extensive experiments for detection task demonstrate the superiority of our method. For example, when RetinaNet, RepPoints and Cascade Mask RCNN are used as teacher detectors, the student network achieves mAP scores of 41.5\%, 42.9\%, and 42.6\%, respectively, outperforming state-of-the-art methods such as DMKD and FreeKD.

arXiv:2611.07994v1cs.CV

트랜스포머 기반 소형 객체 탐지를 위해 버려진 고해상도 특징 되살리기

Reviving the Discarded High-Resolution Feature for Transformer-Based Tiny Object Detection

소형 객체 탐지는 소형 인스턴스가 몇 개의 픽셀만 차지하고 그 세밀한 디테일이 특징 다운샘플링 과정에서 쉽게 손실되기 때문에 여전히 어려운 과제이다. 최고 해상도 특징은 소형 객체에 대한 풍부한 국소 디테일을 보존하지만, DETR 계열 검출기는 큰 계산 비용 때문에 이를 버리는 경우가 많으며, 이 특징을 그대로 다시 도입하면 조밀한 배경 잡음도 함께 유입된다. 이 문제를 해결하기 위해 우리는 소형 객체 탐지를 위해 버려진 고해상도 특징을 되살리는 새로운 프레임워크 ReDHF를 제안한다. ReDHF는 세 가지 협력적 구성요소를 가진다. 교차 스케일 변형 융합(CSDF)은 먼저 의미적으로 강화된 최고 해상도 특징을 구성하고 그 세밀한 디테일을 적당한 비용으로 얕은 특징에 주입한다. 이어서 타원 유도 얕은 층 지도(EGSS)는 기하 적응형 보조 지도를 적용하여 강화된 특징이 더 신뢰할 수 있는 분류 및 위치 추정 사전 정보를 학습하도록 유도한다. 전체 스케일 쿼리 상호작용(FSQI)은 디코더 쿼리가 저수준 디테일과 고수준 의미 정보에 모두 접근하게 하여 소형 객체에 대한 더 풍부한 단서를 집약할 수 있게 한다. 폭넓은 실험을 통해 ReDHF가 여러 DETR 변형에 걸쳐 다양한 기준선을 일관되게 개선하고 평가한 벤치마크에서 최고 수준의 성능을 달성함을 보인다. 최상의 ReDHF 변형은 기준선 대비 AI-TOD-v2에서 +1.4 AP, VisDrone에서 +1.6 AP, SODA-D에서 +1.5 AP를 능가하며, 특히 소형 및 작은 객체에서 현저한 향상을 보인다.

arXiv:2607.26703v1cs.CV

Sequence-SOD: 이벤트 카메라를 위한 생체 모사 기반 시퀀스 인지 스파이킹 객체 탐지

Sequence-SOD: Bio-inspired Sequence-aware Spiking ObjectDetection for Event Cameras

이벤트 카메라는 망막에서 영감을 얻은 센싱 원리를 따라 높은 시간 해상도와 넓은 동적 범위를 바탕으로 국소적 조도 변화를 비동기적으로 보고합니다. 스파이킹 신경망(SNN)은 희소 스파이크와 누설 막 전위를 활용해 시간에 따른 정보를 통합하는 뇌 기반 역학을 통해 이러한 희소 이벤트 스트림을 보완합니다. 그러나 기존의 많은 SNN 객체 탐지기는 단일 라벨을 가진 고립된 이벤트 구간을 처리하고 매 예측 후 네트워크 상태를 초기화하므로, 연속적인 이벤트 스트림의 시간적 정보를 충분히 활용하지 못합니다. 본 논문에서는 여러 시점의 라벨을 포함하는 확장된 이벤트 시퀀스를 처리하는 시퀀스 인지 SNN 객체 탐지기인 Sequence-SOD를 제안합니다. 이벤트는 짧은 구간으로 축적되고 시간 단계로 이산화된 후, 시퀀스 내 구간 전반에 걸쳐 막 전위를 보존하면서 SSD 스타일의 Spiking DenseNet에 순차적으로 공급됩니다. 이를 통해 탐지는 독립적으로 초기화되는 입력 윈도우 대신 진화하는 신경 상태에 의해 구동됩니다. Gen1 Automotive Detection Dataset에서 시퀀스 인지 학습(training)은 mAP를 단일 구간 학습 시 23.38에서 증강이 없을 때 25.30으로, 이벤트 데이터 증강(data augmentation)을 적용했을 때 26.88로 향상시킵니다. 이 모델(model)은 이론적으로 40 Hz의 예측 빈도를 달성합니다. 확장된 이벤트 시퀀스에서 SNN 객체 탐지기를 학습 및 평가하면 희소 스파이킹 연산의 에너지 효율성 이점을 유지하면서 시간적 단서를 활용하는 능력을 향상시킬 수 있습니다. 본 결과는 시퀀스 인지 학습이 이벤트 기반 SNN 탐지를 위한 구조적 개선을 상호 보완하는 방향임을 강조합니다.

arXiv:1603.06121

Buried object detection using handheld WEMI with task-driven extended functions of multiple instances

Many effective supervised discriminative dictionary learning methods have been developed in the literature. However, when training these algorithms, precise ground-truth of the training data is required to provide very accurate point-wise labels. Yet, in many applications, accurate labels are not always feasible. This is especially true in the case of buried object detection in which the size of the objects are not consistent. In this paper, a new multiple instance dictionary learning algorithm for detecting buried objects using a handheld WEMI sensor is detailed. The new algorithm, Task Driven Extended Functions of Multiple Instances, can overcome data that does not have very precise point-wise labels and still learn a highly discriminative dictionary. Results are presented and discussed on measured WEMI data.

arXiv:1506.07363

Salient Object Detection via Objectness Measure

Salient object detection has become an important task in many image processing applications. The existing approaches exploit background prior and contrast prior to attain state of the art results. In this paper, instead of using background cues, we estimate the foreground regions in an image using objectness proposals and utilize it to obtain smooth and accurate saliency maps. We propose a novel saliency measure called `foreground connectivity' which determines how tightly a pixel or a region is connected to the estimated foreground. We use the values assigned by this measure as foreground weights and integrate these in an optimization framework to obtain the final saliency maps. We extensively evaluate the proposed approach on two benchmark databases and demonstrate that the results obtained are better than the existing state of the art approaches.

arXiv:2303.16947공식 코드 · Papers with Code

De-coupling and De-positioning Dense Self-supervised Learning

Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects. Although the dense features extracted by employing segmentation maps and bounding boxes allow networks to perform SSL for each object, we show that they suffer from coupling and positional bias, which arise from the receptive field increasing with layer depth and zero-padding. We address this by introducing three data augmentation strategies, and leveraging them in (i) a decoupling module that aims to robustify the network to variations in the object's surroundings, and (ii) a de-positioning module that encourages the network to discard positional object information. We demonstrate the benefits of our method on COCO and on a new challenging benchmark, OpenImage-MINI, for object classification, semantic segmentation, and object detection. Our extensive experiments evidence the better generalization of our method compared to the SOTA dense SSL methods

arXiv:2211.09518

ImLiDAR: Cross-Sensor Dynamic Message Propagation Network for 3D Object Detection

LiDAR and camera, as two different sensors, supply geometric (point clouds) and semantic (RGB images) information of 3D scenes. However, it is still challenging for existing methods to fuse data from the two cross sensors, making them complementary for quality 3D object detection (3OD). We propose ImLiDAR, a new 3OD paradigm to narrow the cross-sensor discrepancies by progressively fusing the multi-scale features of camera Images and LiDAR point clouds. ImLiDAR enables to provide the detection head with cross-sensor yet robustly fused features. To achieve this, two core designs exist in ImLiDAR. First, we propose a cross-sensor dynamic message propagation module to combine the best of the multi-scale image and point features. Second, we raise a direct set prediction problem that allows designing an effective set-based detector to tackle the inconsistency of the classification and localization confidences, and the sensitivity of hand-tuned hyperparameters. Besides, the novel set-based detector can be detachable and easily integrated into various detection networks. Comparisons on both the KITTI and SUN-RGBD datasets show clear visual and numerical improvements of our ImLiDAR over twenty-three state-of-the-art 3OD methods.

arXiv:2310.01904공식 코드 · Papers with Code

Beyond the Benchmark: Detecting Diverse Anomalies in Videos

Video Anomaly Detection (VAD) plays a crucial role in modern surveillance systems, aiming to identify various anomalies in real-world situations. However, current benchmark datasets predominantly emphasize simple, single-frame anomalies such as novel object detection. This narrow focus restricts the advancement of VAD models. In this research, we advocate for an expansion of VAD investigations to encompass intricate anomalies that extend beyond conventional benchmark boundaries. To facilitate this, we introduce two datasets, HMDB-AD and HMDB-Violence, to challenge models with diverse action-based anomalies. These datasets are derived from the HMDB51 action recognition dataset. We further present Multi-Frame Anomaly Detection (MFAD), a novel method built upon the AI-VAD framework. AI-VAD utilizes single-frame features such as pose estimation and deep image encoding, and two-frame features such as object velocity. They then apply a density estimation algorithm to compute anomaly scores. To address complex multi-frame anomalies, we add a deep video encoding features capturing long-range temporal dependencies, and logistic regression to enhance final score calculation. Experimental results confirm our assumptions, highlighting existing models limitations with new anomaly types. MFAD excels in both simple and complex anomaly detection scenarios.

arXiv:2309.03548

Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation

Object detection in low-light scenarios has attracted much attention in the past few years. A mainstream and representative scheme introduces enhancers as the pre-processing for regular detectors. However, because of the disparity in task objectives between the enhancer and detector, this paradigm cannot shine at its best ability. In this work, we try to arouse the potential of enhancer + detector. Different from existing works, we extend the illumination-based enhancers (our newly designed or existing) as a scene decomposition module, whose removed illumination is exploited as the auxiliary in the detector for extracting detection-friendly features. A semantic aggregation module is further established for integrating multi-scale scene-related semantic information in the context space. Actually, our built scheme successfully transforms the "trash" (i.e., the ignored illumination in the detector) into the "treasure" for the detector. Plenty of experiments are conducted to reveal our superiority against other state-of-the-art methods. The code will be public if it is accepted.

arXiv:1806.06321

Comparative survey of visual object classifiers

Classification of Visual Object Classes represents one of the most elaborated areas of interest in Computer Vision. It is always challenging to get one specific detector, descriptor or classifier that provides the expected object classification result. Consequently, it critical to compare the different detection, descriptor and classifier methods available and chose a single or combination of two or three to get an optimal result. In this paper, we have presented a comparative survey of different feature descriptors and classifiers. From feature descriptors, SIFT (Sparse & Dense) and HeuSIFT combination colour descriptors; From classification techniques, Support Vector Classifier, K-Nearest Neighbor, ADABOOST, and fisher are covered in comparative practical implementation survey.

arXiv:1711.09414

MAVOT: Memory-Augmented Video Object Tracking

We introduce a one-shot learning approach for video object tracking. The proposed algorithm requires seeing the object to be tracked only once, and employs an external memory to store and remember the evolving features of the foreground object as well as backgrounds over time during tracking. With the relevant memory retrieved and updated in each tracking, our tracking model is capable of maintaining long-term memory of the object, and thus can naturally deal with hard tracking scenarios including partial and total occlusion, motion changes and large scale and shape variations. In our experiments we use the ImageNet ILSVRC2015 video detection dataset to train and use the VOT-2016 benchmark to test and compare our Memory-Augmented Video Object Tracking (MAVOT) model. From the results, we conclude that given its oneshot property and simplicity in design, MAVOT is an attractive approach in visual tracking because it shows good performance on VOT-2016 benchmark and is among the top 5 performers in accuracy and robustness in occlusion, motion changes and empty target.