SSD-EMB: An Improved SSD Using Enhanced Feature Map Block for Object Detection

Abstract

The development of deep learning has achieved great success in object detection, but small object detection is still a difficult and challenging task in computer vision. To address the problem, we propose an improved single-shot multibox detector (SSD) using enhanced feature map blocks (SSD-EMB). The enhanced feature map block (EMB) consists of attention stream and feature map concatenation stream. The attention stream allows the proposed model to focus on the object regions rather than background owing to channel averaging and the effectiveness of the normalization. The feature map concatenation stream provides additional semantic information to the model without degrading the detection speed. By combining the output of these two streams, the enhanced feature map, which improves the detection of a small object, is generated. Experimental results show that the proposed model has high accuracy in small object detection. The proposed model not only achieves good detection accuracy, but also has a good detection speed. The SSD-EMB achieved a mean average precision (mAP) of 80.4% on the PASCAL VOC 2007 dataset at 30 frames per second on an RTX 2080Ti graphics processing unit, an mAP of 79.9% on the VOC 2012 dataset, and an mAP of 26.6% on the MS COCO dataset.

An automatic gastric polyp detection technique using deep learning

“…In the baseline study, Zhang et al 9 used various types of extra pooling layers, which caused the features of small polyps to be lost in deeper layers. Therefore, to resolve this issue, we used RMB, 37 which consists of an attention and concatenation cascade to obtain more semantic information. Next, we feed gastric images as input to our model to accomplish this.…”

“…The loss function in SSD was computed by combining two losses: localization loss denoted as L(loc) and confidence loss denoted as L(conf) 43 . SSD multi‐box is a neural network that can detect and locate objects in an image in a single forward pass.…”

“…The loss function in SSD was computed by combining two losses: localization loss denoted as L(loc) and confidence loss denoted as L(conf). 43 SSD multi-box is a neural network that can detect and locate objects in an image in a single forward pass. The final loss function is computed using the following equation where N is the number of positive matches and 'alpha' is the weight for the localization loss.…”

A New Automated Polyp Detection Network MP-FSSD in WCE and Colonoscopy Images Based Fusion Single Shot Multibox Detector and Transfer Learning

“…Pre-existing domain-specific object detection methods based on deep learning usually can be divided into two categories, the first one is two-stage algorithms based on region proposal such as Faster R-CNN [34]. The other is a one-stage algorithm based on regression, such as YOLO [35] and SSD [36]. In two-stage detectors, region proposals are extracted from the input images using the region-selection algorithm.…”

Few-Shot Object Detection: Application to Medieval Musicological Studies

“…Object detection, as a subtask of computer vision, has been the focus of tremendous research interest over the past few years, from traditional computer vision algorithms such as Viola Jones, and the Histogram of Oriented Gradients Detector, which are still commonly used in mobile applications for their speed and accuracy, to new deep-learning-based models [18][19][20] such as Yolo [17], RCNN [16], SSD [21], and others. We can split the deep learning-based object detection models into two subgroups: one-stage detectors and two-stage detectors.…”