PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2311.15273

An Intelligent-Detection Network for Handwritten Mathematical Expression Recognition

The use of artificial intelligence technology in education is growing rapidly, with increasing attention being paid to handwritten mathematical expression recognition (HMER) by researchers. However, many existing methods for HMER may fail to accurately read formulas with complex structures, as the attention results can be inaccurate due to illegible handwriting or large variations in writing styles. Our proposed Intelligent-Detection Network (IDN) for HMER differs from traditional encoder-decoder methods by utilizing object detection techniques. Specifically, we have developed an enhanced YOLOv7 network that can accurately detect both digital and symbolic objects. The detection results are then integrated into the bidirectional gated recurrent unit (BiGRU) and the baseline symbol relationship tree (BSRT) to determine the relationships between symbols and numbers. The experiments demonstrate that the proposed method outperforms those encoder-decoder networks in recognizing complex handwritten mathematical expressions. This is due to the precise detection of symbols and numbers. Our research has the potential to make valuable contributions to the field of HMER. This could be applied in various practical scenarios, such as assignment grading in schools and information entry of paper documents.

arXiv:1910.08259

Eye in the Sky: Drone-Based Object Tracking and 3D Localization

Drones, or general UAVs, equipped with a single camera have been widely deployed to a broad range of applications, such as aerial photography, fast goods delivery and most importantly, surveillance. Despite the great progress achieved in computer vision algorithms, these algorithms are not usually optimized for dealing with images or video sequences acquired by drones, due to various challenges such as occlusion, fast camera motion and pose variation. In this paper, a drone-based multi-object tracking and 3D localization scheme is proposed based on the deep learning based object detection. We first combine a multi-object tracking method called TrackletNet Tracker (TNT) which utilizes temporal and appearance information to track detected objects located on the ground for UAV applications. Then, we are also able to localize the tracked ground objects based on the group plane estimated from the Multi-View Stereo technique. The system deployed on the drone can not only detect and track the objects in a scene, but can also localize their 3D coordinates in meters with respect to the drone camera. The experiments have proved our tracker can reliably handle most of the detected objects captured by drones and achieve favorable 3D localization performance when compared with the state-of-the-art methods.

arXiv:2511.06080v4cs.CV

AIDEN: 시각장애인을 위한 AI 어시스턴트 설계 및 파일럿 연구

AIDEN: Design and Pilot Study of an AI Assistant for the Visually Impaired

이 논문은 AIDEN을 소개한다. AIDEN은 객체 식별, 텍스트 읽기, 낯선 환경에서의 내비게이션에 어려움을 겪는 시각장애인의 자율성과 일상적인 삶의 질을 향상시키기 위해 설계된 인공지능 기반 어시스턴트이다. 스크린 리더나 오디오 기반 어시스턴트와 같은 기존 솔루션은 정보 접근을 용이하게 하지만, 청각적 과부하를 자주 유발하고 개방된 환경에서 프라이버시 우려를 야기한다. AIDEN은 실시간 객체 검출을 위한 YOLO(You Only Look Once)와 장면 설명 및 광학 문자 인식(OCR)을 위한 대형 언어-비전 어시스턴트(LLaVA)를 통합한 하이브리드 아키텍처로 이러한 한계를 해결한다. 시스템의 핵심적인 새로운 기능은 가이거 계수기 은유에 기반한 연속적인 햅틱 안내 메커니즘으로, 청각 채널을 점유하지 않고 객체 중심화를 지원하며, 개인 데이터가 저장되지 않도록 보장함으로써 프라이버시를 보호한다. 시각장애인 참가자를 대상으로 한 실증적 평가에서는 기술 수용 모델(TAM)을 사용하여 인지된 사용 편의성과 수용도를 평가하였다. 결과는 특히 직관성과 인지된 자율성 측면에서 높은 사용자 만족도를 나타낸다. 또한 '객체 찾기' 기능은 효과적인 실시간 성능을 달성하였다. 이러한 결과는 멀티모달 햅틱-시각 피드백이 전통적인 오디오 중심 방법에 비해 일상적인 사용성과 독립성을 향상시킬 수 있다는 유망한 증거를 제공하며, 더 대규모의 임상 검증을 촉진한다.

arXiv:2003.12040

Pseudo-Labeling for Small Lesion Detection on Diabetic Retinopathy Images

Diabetic retinopathy (DR) is a primary cause of blindness in working-age people worldwide. About 3 to 4 million people with diabetes become blind because of DR every year. Diagnosis of DR through color fundus images is a common approach to mitigate such problem. However, DR diagnosis is a difficult and time consuming task, which requires experienced clinicians to identify the presence and significance of many small features on high resolution images. Convolutional Neural Network (CNN) has proved to be a promising approach for automatic biomedical image analysis recently. In this work, we investigate lesion detection on DR fundus images with CNN-based object detection methods. Lesion detection on fundus images faces two unique challenges. The first one is that our dataset is not fully labeled, i.e., only a subset of all lesion instances are marked. Not only will these unlabeled lesion instances not contribute to the training of the model, but also they will be mistakenly counted as false negatives, leading the model move to the opposite direction. The second challenge is that the lesion instances are usually very small, making them difficult to be found by normal object detectors. To address the first challenge, we introduce an iterative training algorithm for the semi-supervised method of pseudo-labeling, in which a considerable number of unlabeled lesion instances can be discovered to boost the performance of the lesion detector. For the small size targets problem, we extend both the input size and the depth of feature pyramid network (FPN) to produce a large CNN feature map, which can preserve the detail of small lesions and thus enhance the effectiveness of the lesion detector. The experimental results show that our proposed methods significantly outperform the baselines.

arXiv:2310.01393공식 코드 · Papers with Code

DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection

Open-vocabulary object detection (OVOD) aims to detect the objects beyond the set of classes observed during training. This work introduces a straightforward and efficient strategy that utilizes pre-trained vision-language models (VLM), like CLIP, to identify potential novel classes through zero-shot classification. Previous methods use a class-agnostic region proposal network to detect object proposals and consider the proposals that do not match the ground truth as background. Unlike these methods, our method will select a subset of proposals that will be considered as background during the training. Then, we treat them as novel classes during training. We refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training. Compared to previous pseudo methods, our approach does not require re-training and offline labeling processing, which is more efficient and effective in one-shot training. Empirical evaluations on three datasets, including LVIS, V3Det, and COCO, demonstrate significant improvements over the baseline performance without incurring additional parameters or computational costs during inference. In addition, we also apply our method to various baselines. In particular, compared with the previous method, F-VLM, our method achieves a 1.7% improvement on the LVIS dataset. Combined with the recent method CLIPSelf, our method also achieves 46.7 novel class AP on COCO without introducing extra data for pertaining. We also achieve over 6.5% improvement over the F-VLM baseline in the recent challenging V3Det dataset. We release our code and models at https://github.com/xushilin1/dst-det.

arXiv:2406.14878공식 코드 · Papers with Code

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

LiDAR-based 3D object detection is crucial for various applications but often experiences performance degradation in real-world deployments due to domain shifts. While most studies focus on cross-dataset shifts, such as changes in environments and object geometries, practical corruptions from sensor variations and weather conditions remain underexplored. In this work, we propose a novel online test-time adaptation framework for 3D detectors that effectively tackles these shifts, including a challenging cross-corruption scenario where cross-dataset shifts and corruptions co-occur. By leveraging long-term knowledge from previous test batches, our approach mitigates catastrophic forgetting and adapts effectively to diverse shifts. Specifically, we propose a Model Synergy (MOS) strategy that dynamically selects historical checkpoints with diverse knowledge and assembles them to best accommodate the current test batch. This assembly is directed by our proposed Synergy Weights (SW), which perform a weighted averaging of the selected checkpoints, minimizing redundancy in the composite model. The SWs are computed by evaluating the similarity of predicted bounding boxes on the test data and the independence of features between checkpoint pairs in the model bank. To maintain an efficient and informative model bank, we discard checkpoints with the lowest average SW scores, replacing them with newly updated models. Our method was rigorously tested against existing test-time adaptation strategies across three datasets and eight types of corruptions, demonstrating superior adaptability to dynamic scenes and conditions. Notably, it achieved a 67.3% improvement in a challenging cross-corruption scenario, offering a more comprehensive benchmark for adaptation. Source code: https://github.com/zhuoxiao-chen/MOS.

arXiv:1904.06883

DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors

Traditional neural objection detection methods use multi-scale features that allow multiple detectors to perform detecting tasks independently and in parallel. At the same time, with the handling of the prior box, the algorithm's ability to deal with scale invariance is enhanced. However, too many prior boxes and independent detectors will increase the computational redundancy of the detection algorithm. In this study, we introduce Dubox, a new one-stage approach that detects the objects without prior box. Working with multi-scale features, the designed dual scale residual unit makes dual scale detectors no longer run independently. The second scale detector learns the residual of the first. Dubox has enhanced the capacity of heuristic-guided that can further enable the first scale detector to maximize the detection of small targets and the second to detect objects that cannot be identified by the first one. Besides, for each scale detector, with the new classification-regression progressive strapped loss makes our process not based on prior boxes. Integrating these strategies, our detection algorithm has achieved excellent performance in terms of speed and accuracy. Extensive experiments on the VOC, COCO object detection benchmark have confirmed the effectiveness of this algorithm.

arXiv:2205.01414공식 코드 · Papers with Code

Multimodal Detection of Unknown Objects on Roads for Autonomous Driving

Tremendous progress in deep learning over the last years has led towards a future with autonomous vehicles on our roads. Nevertheless, the performance of their perception systems is strongly dependent on the quality of the utilized training data. As these usually only cover a fraction of all object classes an autonomous driving system will face, such systems struggle with handling the unexpected. In order to safely operate on public roads, the identification of objects from unknown classes remains a crucial task. In this paper, we propose a novel pipeline to detect unknown objects. Instead of focusing on a single sensor modality, we make use of lidar and camera data by combining state-of-the art detection models in a sequential manner. We evaluate our approach on the Waymo Open Perception Dataset and point out current research gaps in anomaly detection.

arXiv:2311.07981

Benchmarking Individual Tree Mapping with Sub-meter Imagery

There is a rising interest in mapping trees using satellite or aerial imagery, but there is no standardized evaluation protocol for comparing and enhancing methods. In dense canopy areas, the high variability of tree sizes and their spatial proximity makes it arduous to define the quality of the predictions. Concurrently, object-centric approaches such as bounding box detection usuallyperform poorly on small and dense objects. It thus remains unclear what is the ideal framework for individual tree mapping, in regards to detection and segmentation approaches, convolutional neural networks and transformers. In this paper, we introduce an evaluation framework suited for individual tree mapping in any physical environment, with annotation costs and applicative goals in mind. We review and compare different approaches and deep architectures, and introduce a new method that we experimentally prove to be a good compromise between segmentation and detection.

arXiv:1411.1091

Do Convnets Learn Correspondence?

Convolutional neural nets (convnets) trained from massive labeled datasets have substantially improved the state-of-the-art in image classification and object detection. However, visual understanding requires establishing correspondence on a finer level than object category. Given their large pooling regions and training from whole-image labels, it is not clear that convnets derive their success from an accurate correspondence model which could be used for precise localization. In this paper, we study the effectiveness of convnet activation features for tasks requiring correspondence. We present evidence that convnet features localize at a much finer scale than their receptive field sizes, that they can be used to perform intraclass alignment as well as conventional hand-engineered features, and that they outperform conventional features in keypoint prediction on objects from PASCAL VOC 2011.

arXiv:2207.02541공식 코드 · Papers with Code

Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection

To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseudo-boxes with the dense prediction as a united and straightforward form of pseudo-label. Compared to the pseudo-boxes, our Dense Pseudo-Label (DPL) does not involve any post-processing method, thus retaining richer information. We also introduce a region selection technique to highlight the key information while suppressing the noise carried by dense labels. We name our proposed SS-OD algorithm that leverages the DPL as Dense Teacher. On COCO and VOC, Dense Teacher shows superior performance under various settings compared with the pseudo-box-based methods.

arXiv:2109.15177

You Cannot Easily Catch Me: A Low-Detectable Adversarial Patch for Object Detectors

Blind spots or outright deceit can bedevil and deceive machine learning models. Unidentified objects such as digital "stickers," also known as adversarial patches, can fool facial recognition systems, surveillance systems and self-driving cars. Fortunately, most existing adversarial patches can be outwitted, disabled and rejected by a simple classification network called an adversarial patch detector, which distinguishes adversarial patches from original images. An object detector classifies and predicts the types of objects within an image, such as by distinguishing a motorcyclist from the motorcycle, while also localizing each object's placement within the image by "drawing" so-called bounding boxes around each object, once again separating the motorcyclist from the motorcycle. To train detectors even better, however, we need to keep subjecting them to confusing or deceitful adversarial patches as we probe for the models' blind spots. For such probes, we came up with a novel approach, a Low-Detectable Adversarial Patch, which attacks an object detector with small and texture-consistent adversarial patches, making these adversaries less likely to be recognized. Concretely, we use several geometric primitives to model the shapes and positions of the patches. To enhance our attack performance, we also assign different weights to the bounding boxes in terms of loss function. Our experiments on the common detection dataset COCO as well as the driving-video dataset D2-City show that LDAP is an effective attack method, and can resist the adversarial patch detector.

arXiv:2207.08379

Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and Investigation

Deep reinforcement learning (DRL) has attracted much attention in automated game testing. Early attempts rely on game internal information for game space exploration, thus requiring deep integration with games, which is inconvenient for practical applications. In this work, we propose using only screenshots/pixels as input for automated game testing and build a general game testing agent, Inspector, that can be easily applied to different games without deep integration with games. In addition to covering all game space for testing, our agent tries to take human-like behaviors to interact with key objects in a game, since some bugs usually happen in player-object interactions. Inspector is based on purely pixel inputs and comprises three key modules: game space explorer, key object detector, and human-like object investigator. Game space explorer aims to explore the whole game space by using a curiosity-based reward function with pixel inputs. Key object detector aims to detect key objects in a game, based on a small number of labeled screenshots. Human-like object investigator aims to mimic human behaviors for investigating key objects via imitation learning. We conduct experiments on two popular video games: Shooter Game and Action RPG Game. Experiment results demonstrate the effectiveness of Inspector in exploring game space, detecting key objects, and investigating objects. Moreover, Inspector successfully discovers two potential bugs in those two games. The demo video of Inspector is available at https://github.com/Inspector-GameTesting/Inspector-GameTesting.

arXiv:2003.00186

HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection

We present Hybrid Voxel Network (HVNet), a novel one-stage unified network for point cloud based 3D object detection for autonomous driving. Recent studies show that 2D voxelization with per voxel PointNet style feature extractor leads to accurate and efficient detector for large 3D scenes. Since the size of the feature map determines the computation and memory cost, the size of the voxel becomes a parameter that is hard to balance. A smaller voxel size gives a better performance, especially for small objects, but a longer inference time. A larger voxel can cover the same area with a smaller feature map, but fails to capture intricate features and accurate location for smaller objects. We present a Hybrid Voxel network that solves this problem by fusing voxel feature encoder (VFE) of different scales at point-wise level and project into multiple pseudo-image feature maps. We further propose an attentive voxel feature encoding that outperforms plain VFE and a feature fusion pyramid network to aggregate multi-scale information at feature map level. Experiments on the KITTI benchmark show that a single HVNet achieves the best mAP among all existing methods with a real time inference speed of 31Hz.

arXiv:2009.05102공식 코드 · Papers with Code

Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection

Existing RGB-D salient object detection methods treat depth information as an independent component to complement its RGB part, and widely follow the bi-stream parallel network architecture. To selectively fuse the CNNs features extracted from both RGB and depth as a final result, the state-of-the-art (SOTA) bi-stream networks usually consist of two independent subbranches; i.e., one subbranch is used for RGB saliency and the other aims for depth saliency. However, its depth saliency is persistently inferior to the RGB saliency because the RGB component is intrinsically more informative than the depth component. The bi-stream architecture easily biases its subsequent fusion procedure to the RGB subbranch, leading to a performance bottleneck. In this paper, we propose a novel data-level recombination strategy to fuse RGB with D (depth) before deep feature extraction, where we cyclically convert the original 4-dimensional RGB-D into \textbf{D}GB, R\textbf{D}B and RG\textbf{D}. Then, a newly lightweight designed triple-stream network is applied over these novel formulated data to achieve an optimal channel-wise complementary fusion status between the RGB and D, achieving a new SOTA performance.

arXiv:2011.04825공식 코드 · Papers with Code

Multi-Agent Active Search using Realistic Depth-Aware Noise Model

The active search for objects of interest in an unknown environment has many robotics applications including search and rescue, detecting gas leaks or locating animal poachers. Existing algorithms often prioritize the location accuracy of objects of interest while other practical issues such as the reliability of object detection as a function of distance and lines of sight remain largely ignored. Additionally, in many active search scenarios, communication infrastructure may be unreliable or unestablished, making centralized control of multiple agents impractical. We present an algorithm called Noise-Aware Thompson Sampling (NATS) that addresses these issues for multiple ground-based robots performing active search considering two sources of sensory information from monocular optical imagery and depth maps. By utilizing Thompson Sampling, NATS allows for decentralized coordination among multiple agents. NATS also considers object detection uncertainty from depth as well as environmental occlusions and operates while remaining agnostic of the number of objects of interest. Using simulation results, we show that NATS significantly outperforms existing methods such as information-greedy policies or exhaustive search. We demonstrate the real-world viability of NATS using a pseudo-realistic environment created in the Unreal Engine 4 game development platform with the AirSim plugin.

arXiv:2011.09763공식 코드 · Papers with Code

Attention-Based Transformers for Instance Segmentation of Cells in Microstructures

Detecting and segmenting object instances is a common task in biomedical applications. Examples range from detecting lesions on functional magnetic resonance images, to the detection of tumours in histopathological images and extracting quantitative single-cell information from microscopy imagery, where cell segmentation is a major bottleneck. Attention-based transformers are state-of-the-art in a range of deep learning fields. They have recently been proposed for segmentation tasks where they are beginning to outperforming other methods. We present a novel attention-based cell detection transformer (Cell-DETR) for direct end-to-end instance segmentation. While the segmentation performance is on par with a state-of-the-art instance segmentation method, Cell-DETR is simpler and faster. We showcase the method's contribution in a the typical use case of segmenting yeast in microstructured environments, commonly employed in systems or synthetic biology. For the specific use case, the proposed method surpasses the state-of-the-art tools for semantic segmentation and additionally predicts the individual object instances. The fast and accurate instance segmentation performance increases the experimental information yield for a posteriori data processing and makes online monitoring of experiments and closed-loop optimal experimental design feasible.

arXiv:2309.09668

DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation

We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous works that encode RGB-D information with RGB pretrained backbone, we pretrain the backbone using image-depth pairs from ImageNet-1K, and hence the DFormer is endowed with the capacity to encode RGB-D representations; 2) DFormer comprises a sequence of RGB-D blocks, which are tailored for encoding both RGB and depth information through a novel building block design. DFormer avoids the mismatched encoding of the 3D geometry relationships in depth maps by RGB pretrained backbones, which widely lies in existing methods but has not been resolved. We finetune the pretrained DFormer on two popular RGB-D tasks, i.e., RGB-D semantic segmentation and RGB-D salient object detection, with a lightweight decoder head. Experimental results show that our DFormer achieves new state-of-the-art performance on these two tasks with less than half of the computational cost of the current best methods on two RGB-D semantic segmentation datasets and five RGB-D salient object detection datasets. Our code is available at: https://github.com/VCIP-RGBD/DFormer.

arXiv:2403.15241공식 코드 · Papers with Code

IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection

Bird's eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typically exhibit small sizes, and the associated point cloud context is inherently sparse, which leads to great challenges for reliable 3D perception. In this paper, we propose IS-Fusion, an innovative multimodal fusion framework that jointly captures the Instance- and Scene-level contextual information. IS-Fusion essentially differs from existing approaches that only focus on the BEV scene-level fusion by explicitly incorporating instance-level multimodal information, thus facilitating the instance-centric tasks like 3D object detection. It comprises a Hierarchical Scene Fusion (HSF) module and an Instance-Guided Fusion (IGF) module. HSF applies Point-to-Grid and Grid-to-Region transformers to capture the multimodal scene context at different granularities. IGF mines instance candidates, explores their relationships, and aggregates the local multimodal context for each instance. These instances then serve as guidance to enhance the scene feature and yield an instance-aware BEV representation. On the challenging nuScenes benchmark, IS-Fusion outperforms all the published multimodal works to date. Code is available at: https://github.com/yinjunbo/IS-Fusion.

arXiv:2611.11272v1cs.CV

BiRefNet-V2: 고해상도 이분 영상 분할을 위한 양측 참조의 재고찰

BiRefNet-V2: Rethinking Bilateral Reference for High-Resolution Dichotomous Image Segmentation

이분 영상 분할(dichotomous image segmentation)은 가는 필라멘트, 날카로운 가장자리, 복잡한 질감과 같은 미세 구조를 보존하면서 픽셀 단위로 정확한 전경-배경 분리를 요구한다. BiRefNet은 이미지 패치와 기울기 정보를 결합한 양측 참조로 이 과제를 다루었지만, 내향 참조는 국소 공간 구조를 잃고 의미적 안내가 부족하며, 외향 참조는 단일 채널 기울기 어텐션에 의존한다. 본 논문은 이 패러다임을 통제된 정보 복원으로 재정립한다. 즉, 국소성은 어떤 공간 정보가 남는지를, 의미적 선택성은 어떤 정보가 유입되는지를, 집중된 경계 지도는 정제가 어디에서 이루어지는지를 결정한다. 이를 구현하기 위해 BiRefNet-V2를 제안한다. (1) 공간-깊이 변환, 중첩 패치, 의미 유도 게이트(Semantically Guided Gate)를 통한 국소성 보존 및 의미 유도 세부 정보 주입, (2) 경계 주석 없이 전체 채널 잔차 어텐션을 생성하는, 집중 지도를 갖춘 학습된 경계 스트림, (3) 깊이별 경계 합성곱과 대형 커널 어텐션을 통합한 이중 분기 디코더이다. LayerNorm, GELU, Lion 옵티마이저, DINOv3 백본으로 구성된 현대화된 프레임워크는 학습을 600 에폭에서 50 에폭으로 줄인다. 폭넓은 실험을 통해 DIS5K, 위장 객체 탐지, 고해상도 돌출 객체 탐지의 13개 전체 평가 세트에서 최고 수준의 성능을 입증한다. 코드는 https://github.com/ZhengPeng7/BiRefNet-V2 에서 이용할 수 있다.