Weakly-supervised object detection via mining pseudo ground truth bounding-boxes

Recent outstanding results of supervised object detection in competitions and challenges are often associated with specific metrics and datasets. The evaluation of such methods applied in different contexts have increased the demand for annotated datasets. Annotation tools represent the location and size of objects in distinct formats, leading to a lack of consensus on the representation. Such a scenario often complicates the comparison of object detection methods. This work alleviates this problem along the following lines: (i) It provides an overview of the most relevant evaluation methods used in object detection competitions, highlighting their peculiarities, differences, and advantages; (ii) it examines the most used annotation formats, showing how different implementations may influence the assessment results; and (iii) it provides a novel open-source toolkit supporting different annotation formats and 15 performance metrics, making it easy for researchers to evaluate the performance of their detection algorithms in most known datasets. In addition, this work proposes a new metric, also included in the toolkit, for evaluating object detection in videos that is based on the spatio-temporal overlap between the ground-truth and detected bounding boxes.

Download Full-text

CarFree: Hassle-Free Object Detection Dataset Generation Using Carla Autonomous Driving Simulator

Applied Sciences ◽

10.3390/app12010281 ◽

2021 ◽

Vol 12 (1) ◽

pp. 281

Author(s):

Jaesung Jang ◽

Hyeongyu Lee ◽

Jong-Chan Kim

Keyword(s):

Object Detection ◽

Real World ◽

Driving Simulator ◽

Data Extraction ◽

Ground Truth ◽

Autonomous Driving ◽

Relevant Information ◽

Detection Accuracy ◽

Daunting Task ◽

Bounding Boxes

For safe autonomous driving, deep neural network (DNN)-based perception systems play essential roles, where a vast amount of driving images should be manually collected and labeled with ground truth (GT) for training and validation purposes. After observing the manual GT generation’s high cost and unavoidable human errors, this study presents an open-source automatic GT generation tool, CarFree, based on the Carla autonomous driving simulator. By that, we aim to democratize the daunting task of (in particular) object detection dataset generation, which was only possible by big companies or institutes due to its high cost. CarFree comprises (i) a data extraction client that automatically collects relevant information from the Carla simulator’s server and (ii) a post-processing software that produces precise 2D bounding boxes of vehicles and pedestrians on the gathered driving images. Our evaluation results show that CarFree can generate a considerable amount of realistic driving images along with their GTs in a reasonable time. Moreover, using the synthesized training images with artificially made unusual weather and lighting conditions, which are difficult to obtain in real-world driving scenarios, CarFree significantly improves the object detection accuracy in the real world, particularly in the case of harsh environments. With CarFree, we expect its users to generate a variety of object detection datasets in hassle-free ways.

Download Full-text

Refining and Selecting Pseudo Ground Truth for Weakly-Supervised Object Detection

10.1109/icce-asia53811.2021.9641995 ◽

2021 ◽

Author(s):

Se-Hun Kim ◽

Min-Seok Seo ◽

Chun-Myung Park ◽

Kyujoong Lee ◽

Hyuk-Jae Lee

Keyword(s):

Object Detection ◽

Ground Truth ◽

Weakly Supervised

Download Full-text

Multi-Scale Feature Integrated Attention-Based Rotation Network for Object Detection in VHR Aerial Images

Sensors ◽

10.3390/s20061686 ◽

2020 ◽

Vol 20 (6) ◽

pp. 1686 ◽

Cited By ~ 3

Author(s):

Feng Yang ◽

Wentong Li ◽

Haiwei Hu ◽

Wanyi Li ◽

Peng Wang

Keyword(s):

Object Detection ◽

Large Scale ◽

Ground Truth ◽

Classification Performance ◽

Aerial Images ◽

Detection Methods ◽

Robust Detection ◽

Scale Feature ◽

Multi Scale ◽

Bounding Boxes

Accurate and robust detection of multi-class objects in very high resolution (VHR) aerial images has been playing a significant role in many real-world applications. The traditional detection methods have made remarkable progresses with horizontal bounding boxes (HBBs) due to CNNs. However, HBB detection methods still exhibit limitations including the missed detection and the redundant detection regions, especially for densely-distributed and strip-like objects. Besides, large scale variations and diverse background also bring in many challenges. Aiming to address these problems, an effective region-based object detection framework named Multi-scale Feature Integration Attention Rotation Network (MFIAR-Net) is proposed for aerial images with oriented bounding boxes (OBBs), which promotes the integration of the inherent multi-scale pyramid features to generate a discriminative feature map. Meanwhile, the double-path feature attention network supervised by the mask information of ground truth is introduced to guide the network to focus on object regions and suppress the irrelevant noise. To boost the rotation regression and classification performance, we present a robust Rotation Detection Network, which can generate efficient OBB representation. Extensive experiments and comprehensive evaluations on two publicly available datasets demonstrate the effectiveness of the proposed framework.

Download Full-text

Object Detection Algorithm Based on Improved YOLOv3

Electronics ◽

10.3390/electronics9030537 ◽

2020 ◽

Vol 9 (3) ◽

pp. 537 ◽

Cited By ~ 5

Author(s):

Liquan Zhao ◽

Shuaiyang Li

Keyword(s):

Markov Chains ◽

Object Detection ◽

Large Scale ◽

Ground Truth ◽

Detection Algorithm ◽

Detection Methods ◽

Cluster Method ◽

Cluster Center ◽

Initial Cluster ◽

Bounding Boxes

The ‘You Only Look Once’ v3 (YOLOv3) method is among the most widely used deep learning-based object detection methods. It uses the k-means cluster method to estimate the initial width and height of the predicted bounding boxes. With this method, the estimated width and height are sensitive to the initial cluster centers, and the processing of large-scale datasets is time-consuming. In order to address these problems, a new cluster method for estimating the initial width and height of the predicted bounding boxes has been developed. Firstly, it randomly selects a couple of width and height values as one initial cluster center separate from the width and height of the ground truth boxes. Secondly, it constructs Markov chains based on the selected initial cluster and uses the final points of every Markov chain as the other initial centers. In the construction of Markov chains, the intersection-over-union method is used to compute the distance between the selected initial clusters and each candidate point, instead of the square root method. Finally, this method can be used to continually update the cluster center with each new set of width and height values, which are only a part of the data selected from the datasets. Our simulation results show that the new method has faster convergence speed for initializing the width and height of the predicted bounding boxes and that it can select more representative initial widths and heights of the predicted bounding boxes. Our proposed method achieves better performance than the YOLOv3 method in terms of recall, mean average precision, and F1-score.

Download Full-text

Beyond Weakly Supervised: Pseudo Ground Truths Mining for Missing Bounding-Boxes Object Detection

IEEE Transactions on Circuits and Systems for Video Technology ◽

10.1109/tcsvt.2019.2898559 ◽

2020 ◽

Vol 30 (4) ◽

pp. 983-997 ◽

Cited By ~ 1

Author(s):

Yongqiang Zhang ◽

Mingli Ding ◽

Yancheng Bai ◽

Mengmeng Xu ◽

Bernard Ghanem

Keyword(s):

Object Detection ◽

Weakly Supervised ◽

Bounding Boxes

Download Full-text

Weakly-Supervised Salient Object Detection With Saliency Bounding Boxes

IEEE Transactions on Image Processing ◽

10.1109/tip.2021.3071691 ◽

2021 ◽

Vol 30 ◽

pp. 4423-4435

Author(s):

Yuxuan Liu ◽

Pengjie Wang ◽

Ying Cao ◽

Zijian Liang ◽

Rynson W. H. Lau

Keyword(s):

Object Detection ◽

Salient Object Detection ◽

Salient Object ◽

Weakly Supervised ◽

Bounding Boxes

Download Full-text

YOLO MDE: Object Detection with Monocular Depth Estimation

Electronics ◽

10.3390/electronics11010076 ◽

2021 ◽

Vol 11 (1) ◽

pp. 76

Author(s):

Jongsub Yu ◽

Hyukdoo Choi

Keyword(s):

Risk Assessment ◽

Object Detection ◽

Network Architecture ◽

Ground Truth ◽

Depth Estimation ◽

Autonomous Driving ◽

Depth Prediction ◽

Bounding Box ◽

Monocular Depth ◽

Bounding Boxes

This paper presents an object detector with depth estimation using monocular camera images. Previous detection studies have typically focused on detecting objects with 2D or 3D bounding boxes. A 3D bounding box consists of the center point, its size parameters, and heading information. However, predicting complex output compositions leads a model to have generally low performances, and it is not necessary for risk assessment for autonomous driving. We focused on predicting a single depth per object, which is essential for risk assessment for autonomous driving. Our network architecture is based on YOLO v4, which is a fast and accurate one-stage object detector. We added an additional channel to the output layer for depth estimation. To train depth prediction, we extract the closest depth from the 3D bounding box coordinates of ground truth labels in the dataset. Our model is compared with the latest studies on 3D object detection using the KITTI object detection benchmark. As a result, we show that our model achieves higher detection performance and detection speed than existing models with comparable depth accuracy.

Download Full-text

Low Shot Box Correction for Weakly Supervised Object Detection

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/125 ◽

2019 ◽

Author(s):

Tianxiang Pan ◽

Bin Wang ◽

Guiguang Ding ◽

Jungong Han ◽

Junhai Yong

Keyword(s):

Object Detection ◽

Large Data ◽

Detection Accuracy ◽

Detection Problem ◽

Data Set ◽

Supervised Methods ◽

Weakly Supervised ◽

Bounding Boxes ◽

State Of Art ◽

Discriminative Parts

Weakly supervised object detection (WSOD) has been widely studied but the accuracy of state-of-art methods remains far lower than strongly supervised methods. One major reason for this huge gap is the incomplete box detection problem which arises because most previous WSOD models are structured on classification networks and therefore tend to recognize the most discriminative parts instead of complete bounding boxes. To solve this problem, we define a low-shot weakly supervised object detection task and propose a novel low-shot box correction network to address it. The proposed task enables to train object detectors on a large data set all of which have image-level annotations, but only a small portion or few shots have box annotations. Given the low-shot box annotations, we use a novel box correction network to transfer the incomplete boxes into complete ones. Extensive empirical evidence shows that our proposed method yields state-of-art detection accuracy under various settings on the PASCAL VOC benchmark.

Download Full-text