Cross-dataset Training for Class Increasing Object Detection
15
Citation
31
Reference
10
Related Paper
Citation Trend
Abstract:
We present a conceptually simple, flexible and general framework for cross-dataset training in object detection. Given two or more already labeled datasets that target for different object classes, cross-dataset training aims to detect the union of the different classes, so that we do not have to label all the classes for all the datasets. By cross-dataset training, existing datasets can be utilized to detect the merged object classes with a single model. Further more, in industrial applications, the object classes usually increase on demand. So when adding new classes, it is quite time-consuming if we label the new classes on all the existing datasets. While using cross-dataset training, we only need to label the new classes on the new dataset. We experiment on PASCAL VOC, COCO, WIDER FACE and WIDER Pedestrian with both solo and cross-dataset settings. Results show that our cross-dataset pipeline can achieve similar impressive performance simultaneously on these datasets compared with training independently.Keywords:
Pascal (unit)
Training set
Pedestrian detection is an important application of object detection. SSD is one of the target detection algorithms based on deep learning with better performance. The weak detection ability of SSD for small objects, and there will still be false detections and missed detections in the detection situation of the complex environment. In order to improve the detection accuracy of SSD for pedestrians, we propose an improved SSD object detection algorithm based on DenseNet and multi-scale feature fusion. Based on the SSD algorithm, we design the DenseNet-66 module to enhance the feature extraction and utilization capabilities of the model. In the target detection part, a fusion mechanism of multi-scale feature layers is introduced, and an attention feature fusion module is added to further improve the detection performance of the model for small target pedestrians. After training on PASCAL VOC, INRIA, ETH, TUD, CoCo datasets, the experimental results show that our improved SSD model has 300 × 300 input to achieve PASCAL VOC 2007, VOC 2012, INRIA, ETH, TUD, CoCo datasets Up 89.50% mAP, 84.76% mAP, 78.49% mAP, 69.50% mAP, 78.58% mAP and 57.35% mAP. Compared with SSD, the improved SSD detection accuracy increases by 3.75%, 1.77%, 3.06%, 3.66%, 1.90% and 1.87%, respectively.
Pascal (unit)
Pedestrian detection
Feature (linguistics)
Object-class detection
Cite
Citations (4)
Pascal (unit)
Cite
Citations (11)
We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet provides quantized weak directions pointing a target object and the ensemble of iterative predictions from AttentionNet converges to an accurate object boundary box. Since AttentionNet is a unified network for object detection, it detects objects without any separated models from the object proposal to the post bounding-box regression. We evaluate AttentionNet by a human detection task and achieve the state-of-the-art performance of 65% (AP) on PASCAL VOC 2007/2012 with an 8-layered architecture only.
Pascal (unit)
Minimum bounding box
Bounding overwatch
Cite
Citations (171)
Research on object detection algorithms with higher accuracy and faster detection speed is currently the main concern. In order to improve detection performance, an improved object detection algorithm using YOLOv3-tiny based on pyramid pooling is proposed. First, an improved pyramid pooling module using adaptive average pooling is designed to efficiently extract global feature information, and then combine the module with YOLOv3-tiny to explore the impact of different combinations on the detection results. The experiment used PASCAL VOC2007 trainval and all PASCAL VOC2012 for training and validation, and used PASCAL VOC2007 test for testing. Experimental results show that the proposed network improves mAP by 1.8% compared to YOLOv3-tiny while the detection speed is almost the same, which better achieves the balance of detection speed and accuracy.
Pascal (unit)
Pooling
Pyramid (geometry)
Cite
Citations (1)
Object detection is a fundamental problem in image understanding. One popular solution is the R-CNN framework [15] and its fast versions [14, 27]. They decompose the object detection problem into two cascaded easier tasks: 1) generating object proposals from images, 2) classifying proposals into various object categories. Despite that we are handling with two relatively easier tasks, they are not solved perfectly and there's still room for improvement. In this paper, we push the "divide and conquer" solution even further by dividing each task into two sub-tasks. We call the proposed method "CRAFT" (Cascade Regionproposal-network And FasT-rcnn), which tackles each task with a carefully designed network cascade. We show that the cascade structure helps in both tasks: in proposal generation, it provides more compact and better localized object proposals, in object classification, it reduces false positives (mainly between ambiguous categories) by capturing both inter-and intra-category variances. CRAFT achieves consistent and considerable improvement over the state-of the-art on object detection benchmarks like PASCAL VOC 07/12 and ILSVRC.
Pascal (unit)
Craft
Cite
Citations (105)
We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet provides quantized weak directions pointing a target object and the ensemble of iterative predictions from AttentionNet converges to an accurate object boundary box. Since AttentionNet is a unified network for object detection, it detects objects without any separated models from the object proposal to the post bounding-box regression. We evaluate AttentionNet by a human detection task and achieve the state-of-the-art performance of 65% (AP) on PASCAL VOC 2007/2012 with an 8-layered architecture only.
Pascal (unit)
Minimum bounding box
Bounding overwatch
Cite
Citations (0)
The growth of detection datasets and the multiple directions of object detection research provide both an unprecedented need and a great opportunity for a thorough evaluation of the current state of the field of categorical object detection. In this paper we strive to answer two key questions. First, where are we currently as a field: what have we done right, what still needs to be improved? Second, where should we be going in designing the next generation of object detectors? Inspired by the recent work of Hoiem et al. on the standard PASCAL VOC detection dataset, we perform a large-scale study on the Image Net Large Scale Visual Recognition Challenge (ILSVRC) data. First, we quantitatively demonstrate that this dataset provides many of the same detection challenges as the PASCAL VOC. Due to its scale of 1000 object categories, ILSVRC also provides an excellent test bed for understanding the performance of detectors as a function of several key properties of the object classes. We conduct a series of analyses looking at how different detection methods perform on a number of image-level and object-class-level properties such as texture, color, deformation, and clutter. We learn important lessons of the current object detection methods and propose a number of insights for designing the next generation object detectors.
Pascal (unit)
Object-class detection
Categorical variable
Cite
Citations (88)
Numerous studies in the field of object detection have been conducted over the past few decades. Several effective methods have been developed. Among various object detection algorithms, Faster RCNN offers excellent results in both detection speed and accuracy. It is a combination of Fast RCNN and RPN layers. This paper conducts a comparative study of object detection using Faster RCNN. The study shows that use of smaller convolutional network called Region Proposal Network improves performance of the system. It shows that object detection using Faster RCNN can give high accuracy and faster performance as compared to other methods and algorithms. It takes only 0.2 seconds to predict a single image. Also, it gives 70% Mean Accuracy Precision (mAP) on the PASCAL VOC 2007 and PASCAL VOC 2012 datasets.
Pascal (unit)
Cite
Citations (4)
Object detection performance, as measured on the PASCAL VOC dataset, has achieved a prominent result since systems based on the deep convolution neural network (CNN) was proposed. However, inaccurate localization remains a major factor causing error for detection. Building upon high-capacity CNN architectures, we address the problem by 1)combining a high-recall algorithm proposing candidate regions for an object bounding box with an algorithm reducing localization bias, and 2)utilizing box alignment which penalizing deviation via taking object boundaries into account, to instruct the procedure of proposing input of CNN. Experiments demonstrate that the proposed methods improve the detection performance over the baseline and many other methods on the PASCAL VOC 2007 dataset.
Pascal (unit)
Minimum bounding box
Bounding overwatch
Convolution (computer science)
Cite
Citations (0)
In recent years, object detection has made great progress with the continuous development of deep neural network. At present, there are many different fully supervised object detection algorithms in the field of computer vision, which are basically saturated, while object detection in a weakly supervised manner is more challenging than strongly supervised object detection. Since nowadays mature object detection algorithms rely heavily on strongly labeled datasets, but strong labeled datasets are very expensive and require huge datasets to support in order to train a better object detection model, weakly supervised object detection has received more and more attention. In this paper, a new module can be embedded in the framework of weakly supervised object detection, three modules are introduced into the weakly supervised object detection framework, which is used to generate high-quality proposals and screen these proposals, and finally selecting more accurate proposal boxes that are beneficial for subsequent training, and demonstrate their effectiveness on the PASCAL VOC2007 and PASCAL VOC2012 datasets, in which this paper achieves a significant improvement over the existing classic weakly supervised object detection algorithms with significant improvements.
Pascal (unit)
Object-class detection
Cite
Citations (0)