首页/论文/2012.03015

arXiv 2012.030152020-12-05cs.CV

CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud

The Chinese University of Hong Kong（香港中文大学）

Wu Zheng, Weiliang Tang, Sijin Chen, Li Jiang, Chi-Wing Fu

备注：: Accepted by the 35th AAAI Conference on Artificial Intelligence (AAAI), 2021

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Existing single-stage detectors for locating objects in point clouds often treat object localization and category classification as separate tasks, so the localization accuracy and classification confidence may not well align. To address this issue, we present a new single-stage detector named the Confident IoU-Aware Single-Stage object Detector (CIA-SSD). First, we design the lightweight Spatial-Semantic Feature Aggregation module to adaptively fuse high-level abstract semantic features and low-level spatial features for accurate predictions of bounding boxes and classification confidence. Also, the predicted confidence is further rectified with our designed IoU-aware confidence rectification module to make the confidence more consistent with the localization accuracy. Based on the rectified confidence, we further formulate the Distance-variant IoU-weighted NMS to obtain smoother regressions and avoid redundant predictions. We experiment CIA-SSD on 3D car detection in the KITTI test set and show that it attains top performance in terms of the official ranking metric (moderate AP 80.28%) and above 32 FPS inference speed, outperforming all prior single-stage detectors. The code is available at https://github.com/Vegeta2020/CIA-SSD.

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

NIV-SSD：来自点云的邻域 IoU 投票单阶段目标检测器

NIV-SSD: Neighbor IoU-Voting Single-Stage Object Detector From Point Cloud

Sun Yat-sen University（中山大学）；Xidian University（西安电子科技大学）

针对点云单阶段检测器定位精度与分类置信度不对齐及难易目标检测不均衡问题，提出 NIV 策略和目标重采样增强，构建 NIV-SSD，实验验证其有效且性能具有竞争力。

2024-01-23cs.CV

基于机器学习技术的帕金森病检测的批判性研究

A Critical Study towards the Detection of Parkinsons Disease using ML Technologies

The Assam Kaziranga University（阿萨姆卡齐兰加大学）；Adamas University（阿达玛斯大学）

本研究提出深度学习方案用于三类茶叶病害分类与受损区域检测，对比了两种目标检测模型的性能，还结合自定义方法用Mask R-CNN实现叶片病损面积计算。

2025-10-28cs.CV

SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud

The Chinese University of Hong Kong（香港中文大学）

We present Self-Ensembling Single-Stage object Detector (SE-SSD) for accurate and efficient 3D object detection in outdoor point clouds. Our key focus is on exploiting both soft and hard targets with our formulated constraints to jointly optimize the model, without introducing extra computation in the inference. Specifically, SE-SSD contains a pair of teacher and student SSDs, in which we design an effective IoU-based matching strategy to filter soft targets from the teacher and formulate a consistency loss to align student predictions with them. Also, to maximize the distilled knowledge for e…

2021-04-20cs.CV

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

Tianjin University（天津大学）

Bounding box regression is the crucial step in object detection. In existing methods, while $\ell_n$-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recently, IoU loss and generalized IoU (GIoU) loss have been proposed to benefit the IoU metric, but still suffer from the problems of slow convergence and inaccurate regression. In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training t…

2019-11-19cs.CV

基于深度学习技术的茶叶病害检测关键研究

A Critical Study on Tea Leaf Disease Detection using Deep Learning Techniques

Kaziranga University（卡齐兰加大学）；Adamas University（阿达玛斯大学）

本研究利用深度学习模型（SSD MobileNet V2、Faster R-CNN ResNet50 V1和Mask R-CNN）检测三种茶叶病害，并评估其性能，其中Faster R-CNN表现最佳，mAP达25%。

2025-10-26cs.AIcs.CV

SCALoss: Side and Corner Aligned Loss for Bounding Box Regression

Zhejiang University（浙江大学）；Fabu Inc.（Fabu公司）

Bounding box regression is an important component in object detection. Recent work achieves promising performance by optimizing the Intersection over Union~(IoU). However, IoU-based loss has the gradient vanish problem in the case of low overlapping bounding boxes, and the model could easily ignore these simple cases. In this paper, we propose Side Overlap~(SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases. Besides, to speed up the convergence, the Corner Distance~(CD) is added into the objective function. Combining th…

2022-04-26cs.CV

更多相关论文收起更多论文

IoUCert: 基于锚点的目标检测器鲁棒性验证

IoUCert: Robustness Verification for Anchor-based Object Detectors

Safe Intelligence（安全智能公司）；Imperial College London（帝国理工学院）

IoUCert通过改进的坐标变换和区间边界传播方法，首次实现了对基于锚点的目标检测模型在多种输入扰动下的鲁棒性验证。

2026-07-21cs.AIcs.CRcs.CV

UESegNet: Context Aware Unconstrained ROI Segmentation Networks for Ear Biometric

National Institute of Technology Jalandhar（贾朗达尔国家理工学院）；Indian Institute of Technology Mandi（曼迪印度理工学院）

Biometric-based personal authentication systems have seen a strong demand mainly due to the increasing concern in various privacy and security applications. Although the use of each biometric trait is problem dependent, the human ear has been found to have enough discriminating characteristics to allow its use as a strong biometric measure. To locate an ear in a 2D side face image is a challenging task, numerous existing approaches have achieved significant performance, but the majority of studies are based on the constrained environment. However, ear biometrics possess a great level of diffic…

2020-10-08cs.AIcs.CV

图像分割中条件独立假设的松弛

On the Relaxation of Conditional Independence Assumption for Image Segmentation

The Chinese University of Hong Kong（香港中文大学）

针对RankSEG依赖条件独立假设忽略标签相关性的问题，提出空间局部依赖性结构及互反矩近似与定点优化，实现O(d log d)复杂度，在低对比度和小目标分割中显著提升性能。

2026-10-14cs.AIcs.CVcs.LG

Yes-Net: An effective Detector Based on Global Information

CHENGDU HANDSIGHT INFO-TECH CO（成都翰视信息技术有限公司）

This paper introduces a new real-time object detection approach named Yes-Net. It realizes the prediction of bounding boxes and class via single neural network like YOLOv2 and SSD, but owns more efficient and outstanding features. It combines local information with global information by adding the RNN architecture as a packed unit in CNN model to form the basic feature extractor. Independent anchor boxes coming from full-dimension k-means is also applied in Yes-Net, it brings better average IOU than grid anchor box. In addition, instead of NMS, Yes-Net uses RNN as a filter to get the final box…

2017-06-30cs.CV

Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation

Tianjin University（天津大学）；Harbin Institute of Technology（哈尔滨工业大学）

Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency. In particular, we consider three geometric factors, i.e., overlap area, normalized central point distance and aspect ratio, which are crucial for measuring bounding box regression in object detection and instan…

2021-07-05cs.CV

Precise Single-stage Detector

Shanghai Jiao Tong University（上海交通大学）；National University of Computer and Emerging Sciences（国立计算机与新兴科学大学）；National University of Sciences and Technology（国立科技大学）；Dublin City University（都柏林城市大学）；University of Michigan（密歇根大学）；Quaid-e-Awam University of Engineering, Science, and Technology（卡伊德阿瓦姆工程科学技术大学）

There are still two problems in SDD causing some inaccurate results: (1) In the process of feature extraction, with the layer-by-layer acquisition of semantic information, local information is gradually lost, resulting into less representative feature maps; (2) During the Non-Maximum Suppression (NMS) algorithm due to inconsistency in classification and regression tasks, the classification confidence and predicted detection position cannot accurately indicate the position of the prediction boxes. Methods: In order to address these aforementioned issues, we propose a new architecture, a modifie…

2022-10-09cs.AIcs.CVcs.LG

FCOS: A simple and strong anchor-free object detector

The University of Adelaide（阿德莱德大学）

In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications. Recently one-stage methods have gained much attention over two-stage approaches due to their simpler design and competitive performance. Here we propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to other dense prediction problems such as semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely…

2020-10-12cs.CV

现代目标检测器在果园图像中稳健苹果检测的比较研究

A Comparative Study of Modern Object Detectors for Robust Apple Detection in Orchard Imagery

Affiliation omitted for double-blind review

本文比较了六个现代目标检测器在苹果检测中的性能，发现YOLO11n在严格定位性能上表现最佳，同时分析了不同检测器在阈值鲁棒性和下游任务需求上的差异。

2026-04-11cs.CV

ScanSSD: Scanning Single Shot Detector for Mathematical Formulas in PDF Document Images

Rochester Institute of Technology（罗切斯特理工学院）

We introduce the Scanning Single Shot Detector (ScanSSD) for locating math formulas offset from text and embedded in textlines. ScanSSD uses only visual features for detection: no formatting or typesetting information such as layout, font, or character labels are employed. Given a 600 dpi document page image, a Single Shot Detector (SSD) locates formulas at multiple scales using sliding windows, after which candidate detections are pooled to obtain page-level results. For our experiments we use the TFD-ICDAR2019v2 dataset, a modification of the GTDB scanned math article collection. ScanSSD det…

2020-03-18cs.CV