首页/论文/2006.07825

arXiv 2006.078252020-06-14cs.CV

Working with scale: 2nd place solution to Product Detection in Densely Packed Scenes [Technical Report]

Artem Kozlov

英文摘要：

This report describes a 2nd place solution of the detection challenge which is held within CVPR 2020 Retail-Vision workshop. Instead of going further considering previous results this work mainly aims to verify previously observed takeaways by re-experimenting. The reliability and reproducibility of the results are reached by incorporating a popular object detection toolbox - MMDetection. In this report, I firstly represent the results received for Faster-RCNN and RetinaNet models, which were taken for comparison in the original work. Then I describe the experiment results with more advanced models. The final section reviews two simple tricks for Faster-RCNN model that were used for my final submission: changing default anchor scale parameter and train-time image tiling. The source code is available at https://github.com/tyomj/product_detection.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Precise Detection in Densely Packed Scenes

Bar-Ilan University（巴伊兰大学）；Trax Retail（Trax零售公司）；Tel Aviv University（特拉维夫大学）；The Open University of Israel（以色列开放大学）

Man-made scenes can be densely packed, containing numerous objects, often identical, positioned in close proximity. We show that precise object detection in such scenes remains a challenging frontier even for state-of-the-art object detectors. We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings. Our contributions include: (1) A layer for estimating the Jaccard index as a detection quality score; (2) a novel EM merging unit, which uses our quality scores to resolve detection overlap ambiguities; finally, (3) an extensive, annotated…

2019-04-30cs.CV

Dynamic Refinement Network for Oriented and Densely Packed Object Detection

Institute of Automation, CAS（中国科学院自动化研究所）；School of Artificial Intelligence, UCAS（中国科学院大学人工智能学院）；Youtu Lab, Tencent（腾讯优图实验室）；CASIA-LLVision Joint Lab（中国科学院自动化研究所-联汇视界联合实验室）；Y-Tech, Kuaishou Technology（快手科技Y-Tech）

Object detection has achieved remarkable progress in the past decade. However, the detection of oriented and densely packed objects remains challenging because of following inherent reasons: (1) receptive fields of neurons are all axis-aligned and of the same shape, whereas objects are usually of diverse shapes and align along various directions; (2) detection models are typically trained with generic knowledge and may not generalize well to handle specific objects at test time; (3) the limited dataset hinders the development on this task. To resolve the first two issues, we present a dynamic …

2020-06-10cs.CV

使用Faster R-CNN和YOLO网络的协同训练半监督框架用于密集零售图像中的目标检测

A Co-Training Semi-Supervised Framework Using Faster R-CNN and YOLO Networks for Object Detection in Densely Packed Retail Images

Khazar University（哈扎尔大学）；Politecnico di Milano（米兰理工大学）；Duy Tan University（维新大学）

本研究提出一种半监督协同训练框架，结合Faster R-CNN与YOLO交换伪标签，并集成XGBoost等分类器与元启发式优化，有效提升了密集零售图像目标检测的精度与效率。

2025-09-11cs.AIcs.CV

Semi-supervised Learning for Dense Object Detection in Retail Scenes

ParallelDots, Inc.（ParallelDots公司）

Retail scenes usually contain densely packed high number of objects in each image. Standard object detection techniques use fully supervised training methodology. This is highly costly as annotating a large dense retail object detection dataset involves an order of magnitude more effort compared to standard datasets. Hence, we propose semi-supervised learning to effectively use the large amount of unlabeled data available in the retail domain. We adapt a popular self supervised method called noisy student initially proposed for object classification to the task of dense object detection. We sh…

2021-07-05cs.CV

A Solution to Product detection in Densely Packed Scenes

This work is a solution to densely packed scenes dataset SKU-110k. Our work is modified from Cascade R-CNN. To solve the problem, we proposed a random crop strategy to ensure both the sampling rate and input scale is relatively sufficient as a contrast to the regular random crop. And we adopted some of trick and optimized the hyper-parameters. To grasp the essential feature of the densely packed scenes, we analysis the stages of a detector and investigate the bottleneck which limits the performance. As a result, our method obtains 58.7 mAP on test set of SKU-110k.

2021-08-10cs.CV

RT-DETR++用于无人机目标检测

RT-DETR++ for UAV Object Detection

School of Computer Science & Technology, Huazhong University of Science and Technology（计算机科学与技术学院，华中科技大学）

本文提出RT-DETR++，通过引入通道门控注意力上下采样机制和CSP-PAC并行空洞卷积，增强RT-DETR编码器，在不增加计算复杂度的前提下，提升无人机图像中小目标与密集目标的检测性能。

2025-09-11cs.CV

更多相关论文收起更多论文

Benchmark for Generic Product Detection: A Low Data Baseline for Dense Object Detection

ParallelDots, Inc.（ParallelDots公司）

Object detection in densely packed scenes is a new area where standard object detectors fail to train well. Dense object detectors like RetinaNet trained on large and dense datasets show great performance. We train a standard object detector on a small, normally packed dataset with data augmentation techniques. This dataset is 265 times smaller than the standard dataset, in terms of number of annotations. This low data baseline achieves satisfactory results (mAP=0.56) at standard IoU of 0.5. We also create a varied benchmark for generic SKU product detection by providing full annotations for m…

2020-01-08cs.CV

基于单点监督的遥感目标检测学习

Learning Remote Sensing Object Detection with Single Point Supervision

College of Electronic Science and Technology, National University of Defense Technology（国防科技大学电子科学与技术学院）

针对遥感图像场景复杂、目标密集多尺度导致点监督检测效果不佳的问题，提出含PLUG点标签升级器和稀疏特征引导语义预测模块的单点监督遥感检测方法，在DOTA数据集上性能优于现有方法，缩小与框级监督的差距。

2023-12-14cs.CV

Investigating the Challenges of Class Imbalance and Scale Variation in Object Detection in Aerial Images

MBZUAI（穆罕默德·本·扎耶德人工智能大学）

While object detection is a common problem in computer vision, it is even more challenging when dealing with aerial satellite images. The variety in object scales and orientations can make them difficult to identify. In addition, there can be large amounts of densely packed small objects such as cars. In this project, we propose a few changes to the Faster-RCNN architecture. First, we experiment with different backbones to extract better features. We also modify the data augmentations and generated anchor sizes for region proposals in order to better handle small objects. Finally, we investiga…

2022-02-05cs.CV

Scene-level Pose Estimation for Multiple Instances of Densely Packed Objects

Rutgers University（罗格斯大学）

This paper introduces key machine learning operations that allow the realization of robust, joint 6D pose estimation of multiple instances of objects either densely packed or in unstructured piles from RGB-D data. The first objective is to learn semantic and instance-boundary detectors without manual labeling. An adversarial training framework in conjunction with physics-based simulation is used to achieve detectors that behave similarly in synthetic and real data. Given the stochastic output of such detectors, candidates for object poses are sampled. The second objective is to automatically l…

2019-10-11cs.CVcs.RO

BugNIST——一个用于域迁移下目标检测的大型体数据集

BugNIST -- a Large Volumetric Dataset for Object Detection under Domain Shift

Technical University of Denmark（丹麦技术大学）

针对三维图像中密集目标标注昂贵及训练—检测域迁移问题，本文构建 BugNIST 显微 CT 数据集并提供基线检测分析。

2024-07-07cs.AIcs.CV

一种用于微流控实验中重叠红血球 sickling 动力学量化的人工智能工具

An AI-enabled tool for quantifying overlapping red blood cell sickling dynamics in microfluidic assays

School of Engineering, Brown University（工程学院，布朗大学）；Division of Applied Mathematics, Brown University（应用数学系，布朗大学）

本文提出一种基于AI的工具，用于微流控实验中量化红血球在不同密度下的形态变化，通过深度学习和分割算法提高细胞重叠的检测精度，从而提升实验效率和药物评估能力。

2026-02-04cs.CV

增强、精炼与融合：迈向鲁棒的多尺度与密集船舶检测

Enhancing, Refining, and Fusing: Towards Robust Multi-Scale and Dense Ship Detection

School of Integrated Circuits and Electronics, Beijing Institute of Technology（北京理工大学集成电路与电子学院）

针对SAR图像中复杂背景、密集目标和尺度变化问题，提出CASS-Det框架，通过CEM、NAM和CC-FPN增强中心、精炼边界并融合多尺度特征，在三个数据集上达到最先进检测性能。

2025-01-10cs.CV