PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1609.06260

GAdaBoost: Accelerating Adaboost Feature Selection with Genetic Algorithms

Boosted cascade of simple features, by Viola and Jones, is one of the most famous object detection frameworks. However, it suffers from a lengthy training process. This is due to the vast features space and the exhaustive search nature of Adaboost. In this paper we propose GAdaboost: a Genetic Algorithm to accelerate the training procedure through natural feature selection. Specifically, we propose to limit Adaboost search within a subset of the huge feature space, while evolving this subset following a Genetic Algorithm. Experiments demonstrate that our proposed GAdaboost is up to 3.7 times faster than Adaboost. We also demonstrate that the price of this speedup is a mere decrease (3%, 4%) in detection accuracy when tested on FDDB benchmark face detection set, and Caltech Web Faces respectively.

arXiv:2611.08393v1cs.CV

도로 이상 탐지를 위한 적응형 저조도 향상: 다중 아키텍처 벤치마크 및 엣지 배포 연구

Adaptive Low-Light Enhancement for Road Anomaly Detection: A Multi-Architecture Benchmark and Edge Deployment Study

자율주행차의 도로 이상 탐지 시스템은 어둠, 비, 하르마탄 먼지 연무를 포함한 열화된 시각 조건에서도 안정적으로 작동해야 한다. 본 논문은 물리적 근거에 기반한 조명 및 날씨 열화 조건에서 네 가지 객체 탐지 아키텍처인 YOLOv8n, YOLOv12n, RT-DETR, Faster R-CNN을 벤치마크하고, SCI 저조도 향상 네트워크를 일률적으로 적용하는 것이 황혼 수준의 조명에서는 오히려 해롭다는 것(mAP@50 -16.1%~-30.7%)을 보인다. 우리는 프레임별 Rec. 601 휘도에 따라 무향상, 중간 수준의 SCI, 잡음 제거와 강한 SCI 중에서 선택하는 경량의 학습이 필요 없는 휘도 적응형 라우터를 제안하며, 이는 저조도 이득을 유지하면서 황혼 시 성능 저하의 대부분을 회복한다. 또한 전체 파이프라인을 NVIDIA Jetson Nano 엣지 하드웨어에서 검증한다.

arXiv:1801.02722공식 코드 · Papers with Code

End-to-end detection-segmentation network with ROI convolution

We propose an end-to-end neural network that improves the segmentation accuracy of fully convolutional networks by incorporating a localization unit. This network performs object localization first, which is then used as a cue to guide the training of the segmentation network. We test the proposed method on a segmentation task of small objects on a clinical dataset of ultrasound images. We show that by jointly learning for detection and segmentation, the proposed network is able to improve the segmentation accuracy compared to only learning for segmentation. Code is publicly available at https://github.com/vincentzhang/roi-fcn.

arXiv:2110.13064

2nd Place Solution for SODA10M Challenge 2021 -- Continual Detection Track

In this technical report, we present our approaches for the continual object detection track of the SODA10M challenge. We adapt ResNet50-FPN as the baseline and try several improvements for the final submission model. We find that task-specific replay scheme, learning rate scheduling, model calibration, and using original image scale helps to improve performance for both large and small objects in images. Our team `hypertune28' secured the second position among 52 participants in the challenge. This work will be presented at the ICCV 2021 Workshop on Self-supervised Learning for Next-Generation Industry-level Autonomous Driving (SSLAD).

arXiv:2401.17129공식 코드 · Papers with Code

Enhanced Sound Event Localization and Detection in Real 360-degree audio-visual soundscapes

This technical report details our work towards building an enhanced audio-visual sound event localization and detection (SELD) network. We build on top of the audio-only SELDnet23 model and adapt it to be audio-visual by merging both audio and video information prior to the gated recurrent unit (GRU) of the audio-only network. Our model leverages YOLO and DETIC object detectors. We also build a framework that implements audio-visual data augmentation and audio-visual synthetic data generation. We deliver an audio-visual SELDnet system that outperforms the existing audio-visual SELD baseline.

arXiv:2409.20122

Training a Computer Vision Model for Commercial Bakeries with Primarily Synthetic Images

In the food industry, reprocessing returned product is a vital step to increase resource efficiency. [SBB23] presented an AI application that automates the tracking of returned bread buns. We extend their work by creating an expanded dataset comprising 2432 images and a wider range of baked goods. To increase model robustness, we use generative models pix2pix and CycleGAN to create synthetic images. We train state-of-the-art object detection model YOLOv9 and YOLOv8 on our detection task. Our overall best-performing model achieved an average precision [email omitted] of 90.3% on our test set.

arXiv:2007.02595

Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection

In real applications, object detectors based on deep networks still face challenges of the large domain gap between the labeled training data and unlabeled testing data. To reduce the gap, recent techniques are proposed by aligning the image/instance-level features between source and unlabeled target domains. However, these methods suffer from the suboptimal problem mainly because of ignoring the category information of object instances. To tackle this issue, we develop a fine-grained domain alignment approach with a well-designed domain classifier bank that achieves the instance-level alignment respecting to their categories. Specifically, we first employ the mean teacher paradigm to generate pseudo labels for unlabeled samples. Then we implement the class-level domain classifiers and group them together, called domain classifier bank, in which each domain classifier is responsible for aligning features of a specific class. We assemble the bare object detector with the proposed fine-grained domain alignment mechanism as the adaptive detector, and optimize it with a developed crossed adaptive weighting mechanism. Extensive experiments on three popular transferring benchmarks demonstrate the effectiveness of our method and achieve the new remarkable state-of-the-arts.

arXiv:2101.12398

The Orientation Estimation of Elongated Underground Objects via Multi-Polarization Aggregation and Selection Neural Network

The horizontal orientation angle and vertical inclination angle of an elongated subsurface object are key parameters for object identification and imaging in ground penetrating radar (GPR) applications. Conventional methods can only extract the horizontal orientation angle or estimate both angles in narrow ranges due to limited polarimetric information and detection capability. To address these issues, this letter, for the first time, explores the possibility of leveraging neural networks with multi-polarimetric GPR data to estimate both angles of an elongated subsurface object in the entire spatial range. Based on the polarization-sensitive characteristic of an elongated object, we propose a multi-polarization aggregation and selection neural network (MASNet), which takes the multi-polarimetric radargrams as inputs, integrates their characteristics in the feature space, and selects discriminative features of reflected signal patterns for accurate orientation estimation. Numerical results show that our proposed MASNet achieves high estimation accuracy with an angle estimation error of less than 5{\deg}. The promising results obtained by the proposed method encourages one to think of new solutions for GPR-related tasks by integrating multi-polarization information with deep learning techniques.

arXiv:2305.07304공식 코드 · Papers with Code

CLIP-Count: Towards Text-Guided Zero-Shot Object Counting

Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object counting, however, remains a formidable challenge. In this study, we first investigate transferring vision-language models (VLMs) for class-agnostic object counting. Specifically, we propose CLIP-Count, the first end-to-end pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner. To align the text embedding with dense visual features, we introduce a patch-text contrastive loss that guides the model to learn informative patch-level visual representations for dense prediction. Moreover, we design a hierarchical patch-text interaction module to propagate semantic information across different resolution levels of visual features. Benefiting from the full exploitation of the rich image-text alignment knowledge of pretrained VLMs, our method effectively generates high-quality density maps for objects-of-interest. Extensive experiments on FSC-147, CARPK, and ShanghaiTech crowd counting datasets demonstrate state-of-the-art accuracy and generalizability of the proposed method. Code is available: https://github.com/songrise/CLIP-Count.

arXiv:1411.6850

Similarity- based approach for outlier detection

This paper presents a new approach for detecting outliers by introducing the notion of object's proximity. The main idea is that normal point has similar characteristics with several neighbors. So the point in not an outlier if it has a high degree of proximity and its neighbors are several. The performance of this approach is illustrated through real datasets

arXiv:2110.12130

RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection

Feature pyramid networks (FPN) are widely exploited for multi-scale feature fusion in existing advanced object detection frameworks. Numerous previous works have developed various structures for bidirectional feature fusion, all of which are shown to improve the detection performance effectively. We observe that these complicated network structures require feature pyramids to be stacked in a fixed order, which introduces longer pipelines and reduces the inference speed. Moreover, semantics from non-adjacent levels are diluted in the feature pyramid since only features at adjacent pyramid levels are merged by the local fusion operation in a sequence manner. To address these issues, we propose a novel architecture named RCNet, which consists of Reverse Feature Pyramid (RevFP) and Cross-scale Shift Network (CSN). RevFP utilizes local bidirectional feature fusion to simplify the bidirectional pyramid inference pipeline. CSN directly propagates representations to both adjacent and non-adjacent levels to enable multi-scale features more correlative. Extensive experiments on the MS COCO dataset demonstrate RCNet can consistently bring significant improvements over both one-stage and two-stage detectors with subtle extra computational overhead. In particular, RetinaNet is boosted to 40.2 AP, which is 3.7 points higher than baseline, by replacing FPN with our proposed model. On COCO test-dev, RCNet can achieve very competitive performance with a single-model single-scale 50.5 AP. Codes will be made available.

arXiv:2607.05176v2cs.CV

FSDC-DETR: 소형 객체 검출을 위한 주파수-공간 도메인 협력 DETR

FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection

소형 객체 검출(SOD)에서 주파수 에일리어싱과 고주파 성분 손실 문제를 해결하기 위해, DBFSAF·SFS-FF·FSD-Down 세 모듈로 구성된 주파수-공간 도메인 협력 프레임워크 FSDC-DETR을 제안한다. VisDrone-DET2019와 AITODv2 벤치마크에서 소형 객체 AP를 각각 6.8, 6.9 향상시키며 최고 성능을 달성했다.

arXiv:2410.04088공식 코드 · Papers with Code

Cross Resolution Encoding-Decoding For Detection Transformers

Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decoding (CRED) mechanism that allows DETR to achieve the accuracy of high-resolution detection while having the speed of low-resolution detection. CRED is based on two modules; Cross Resolution Attention Module (CRAM) and One Step Multiscale Attention (OSMA). CRAM is designed to transfer the knowledge of low-resolution encoder output to a high-resolution feature. While OSMA is designed to fuse multiscale features in a single step and produce a feature map of a desired resolution enriched with multiscale information. When used in prominent DETR methods, CRED delivers accuracy similar to the high-resolution DETR counterpart in roughly 50% fewer FLOPs. Specifically, state-of-the-art DN-DETR, when used with CRED (calling CRED-DETR), becomes 76% faster, with ~50% reduced FLOPs than its high-resolution counterpart with 202 G FLOPs on MS-COCO benchmark. We plan to release pretrained CRED-DETRs for use by the community. Code: https://github.com/ashishkumar822/CRED-DETR

arXiv:2012.01724공식 코드 · Papers with Code

Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection

This paper proposes the Parallel Residual Bi-Fusion Feature Pyramid Network (PRB-FPN) for fast and accurate single-shot object detection. Feature Pyramid (FP) is widely used in recent visual detection, however the top-down pathway of FP cannot preserve accurate localization due to pooling shifting. The advantage of FP is weakened as deeper backbones with more layers are used. In addition, it cannot keep up accurate detection of both small and large objects at the same time. To address these issues, we propose a new parallel FP structure with bi-directional (top-down and bottom-up) fusion and associated improvements to retain high-quality features for accurate localization. We provide the following design improvements: (1) A parallel bifusion FP structure with a bottom-up fusion module (BFM) to detect both small and large objects at once with high accuracy. (2) A concatenation and re-organization (CORE) module provides a bottom-up pathway for feature fusion, which leads to the bi-directional fusion FP that can recover lost information from lower-layer feature maps. (3) The CORE feature is further purified to retain richer contextual information. Such CORE purification in both top-down and bottom-up pathways can be finished in only a few iterations. (4) The adding of a residual design to CORE leads to a new Re-CORE module that enables easy training and integration with a wide range of deeper or lighter backbones. The proposed network achieves state-of-the-art performance on the UAVDT17 and MS COCO datasets. Code is available at https://github.com/pingyang1117/PRBNet_PyTorch.

arXiv:2407.02968

Unified Anomaly Detection methods on Edge Device using Knowledge Distillation and Quantization

With the rapid advances in deep learning and smart manufacturing in Industry 4.0, there is an imperative for high-throughput, high-performance, and fully integrated visual inspection systems. Most anomaly detection approaches using defect detection datasets, such as MVTec AD, employ one-class models that require fitting separate models for each class. On the contrary, unified models eliminate the need for fitting separate models for each class and significantly reduce cost and memory requirements. Thus, in this work, we experiment with considering a unified multi-class setup. Our experimental study shows that multi-class models perform at par with one-class models for the standard MVTec AD dataset. Hence, this indicates that there may not be a need to learn separate object/class-wise models when the object classes are significantly different from each other, as is the case of the dataset considered. Furthermore, we have deployed three different unified lightweight architectures on the CPU and an edge device (NVIDIA Jetson Xavier NX). We analyze the quantized multi-class anomaly detection models in terms of latency and memory requirements for deployment on the edge device while comparing quantization-aware training (QAT) and post-training quantization (PTQ) for performance at different precision widths. In addition, we explored two different methods of calibration required in post-training scenarios and show that one of them performs notably better, highlighting its importance for unsupervised tasks. Due to quantization, the performance drop in PTQ is further compensated by QAT, which yields at par performance with the original 32-bit Floating point in two of the models considered.

arXiv:2407.17197공식 코드 · Papers with Code

ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only

3D object detection plays a crucial role in various applications such as autonomous vehicles, robotics and augmented reality. However, training 3D detectors requires a costly precise annotation, which is a hindrance to scaling annotation to large datasets. To address this challenge, we propose a weakly supervised 3D annotator that relies solely on 2D bounding box annotations from images, along with size priors. One major problem is that supervising a 3D detection model using only 2D boxes is not reliable due to ambiguities between different 3D poses and their identical 2D projection. We introduce a simple yet effective and generic solution: we build 3D proxy objects with annotations by construction and add them to the training dataset. Our method requires only size priors to adapt to new classes. To better align 2D supervision with 3D detection, our method ensures depth invariance with a novel expression of the 2D losses. Finally, to detect more challenging instances, our annotator follows an offline pseudo-labelling scheme which gradually improves its 3D pseudo-labels. Extensive experiments on the KITTI dataset demonstrate that our method not only performs on-par or above previous works on the Car category, but also achieves performance close to fully supervised methods on more challenging classes. We further demonstrate the effectiveness and robustness of our method by being the first to experiment on the more challenging nuScenes dataset. We additionally propose a setting where weak labels are obtained from a 2D detector pre-trained on MS-COCO instead of human annotations. The code is available at https://github.com/CEA-LIST/ALPI

arXiv:1706.04062

Deep Learning-Based Food Calorie Estimation Method in Dietary Assessment

Obesity treatment requires obese patients to record all food intakes per day. Computer vision has been introduced to estimate calories from food images. In order to increase accuracy of detection and reduce the error of volume estimation in food calorie estimation, we present our calorie estimation method in this paper. To estimate calorie of food, a top view and side view is needed. Faster R-CNN is used to detect the food and calibration object. GrabCut algorithm is used to get each food's contour. Then the volume is estimated with the food and corresponding object. Finally we estimate each food's calorie. And the experiment results show our estimation method is effective.

arXiv:2304.06052

Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling

Deploying deep learning models in real-world certified systems requires the ability to provide confidence estimates that accurately reflect their uncertainty. In this paper, we demonstrate the use of the conformal prediction framework to construct reliable and trustworthy predictors for detecting railway signals. Our approach is based on a novel dataset that includes images taken from the perspective of a train operator and state-of-the-art object detectors. We test several conformal approaches and introduce a new method based on conformal risk control. Our findings demonstrate the potential of the conformal prediction framework to evaluate model performance and provide practical guidance for achieving formally guaranteed uncertainty bounds.

arXiv:2310.03333

Real-time Multi-modal Object Detection and Tracking on Edge for Regulatory Compliance Monitoring

Regulatory compliance auditing across diverse industrial domains requires heightened quality assurance and traceability. Present manual and intermittent approaches to such auditing yield significant challenges, potentially leading to oversights in the monitoring process. To address these issues, we introduce a real-time, multi-modal sensing system employing 3D time-of-flight and RGB cameras, coupled with unsupervised learning techniques on edge AI devices. This enables continuous object tracking thereby enhancing efficiency in record-keeping and minimizing manual interventions. While we validate the system in a knife sanitization context within agrifood facilities, emphasizing its prowess against occlusion and low-light issues with RGB cameras, its potential spans various industrial monitoring settings.

arXiv:2007.12449

Learning Crisp Edge Detector Using Logical Refinement Network

Edge detection is a fundamental problem in different computer vision tasks. Recently, edge detection algorithms achieve satisfying improvement built upon deep learning. Although most of them report favorable evaluation scores, they often fail to accurately localize edges and give thick and blurry boundaries. In addition, most of them focus on 2D images and the challenging 3D edge detection is still under-explored. In this work, we propose a novel logical refinement network for crisp edge detection, which is motivated by the logical relationship between segmentation and edge maps and can be applied to both 2D and 3D images. The network consists of a joint object and edge detection network and a crisp edge refinement network, which predicts more accurate, clearer and thinner high quality binary edge maps without any post-processing. Extensive experiments are conducted on the 2D nuclei images from Kaggle 2018 Data Science Bowl and a private 3D microscopy images of a monkey brain, which show outstanding performance compared with state-of-the-art methods.