RefineDet++: Single-Shot Refinement Neural Network for Object Detection

Object detection is a fundamental task in computer vision, which is usually based on convolutional neural networks (CNNs). While it is difficult to be deployed in embedded devices due to the huge storage and computing consumptions, binary neural networks (BNNs) can execute object detection with limited resources. However, the extreme quantification in BNN causes diversity of feature representation loss, which eventually influences the object detection performance. In this paper, we propose a method balancing Information Retention and Deviation Control to achieve effective object detection, named IR-DC Net. On the one hand, we introduce the KL-Divergence to compose multiple entropy for maximizing the available information. On the other hand, we design a lightweight convolutional module to generate scale factors dynamically for minimizing the deviation between binary and real convolution. The experiments on PASCAL VOC, COCO2014, KITTI, and VisDrone datasets show that our method improved the accuracy in comparison with previous binary neural networks.

Existing night vehicle detection methods mainly detect vehicles by detecting headlights or taillights. However, these features are adversely affected by the complex road lighting environment. In this paper, a cascade detection network framework FteGanOd is proposed with a feature translate-enhancement (FTE) module and the object detection (OD) module. First, the FTE module is built based on CycleGAN and multi-scale feature fusion is proposed to enhance the detection of vehicle features at night. The features of night and day are combined by fusing different convolutional layers to produce enhanced feature (EF) maps. Second, the OD module, based on the existing object detection network, is improved by cascading with the FTE module to detect vehicles on the EF maps. The proposed FteGanOd method recognizes vehicles at night with greater accuracy by improving the contrast between vehicles and the background and by suppressing interference from ambient light. The proposed FteGanOd is validated on the Berkeley Deep Drive (BDD) dataset and our private dataset. The experimental results show that our proposed method can effectively enhance vehicle features and improve the accuracy of vehicle detection at night.

Little is known regarding parental preference for a one-stage complete repair versus a two-staged approach with initial palliation, followed by repair, of the congenital cardiac malformation. We interviewed 103 parents of healthy children referred to a clinic for pediatric cardiology. Participants were presented with a hypothetical scenario in which their children had a cardiac lesion requiring surgery. The surgery could be performed either by means of one-stage complete repair, or using a two-stage approach, with palliation first followed by complete repair a year later. The mortality rate for the one-stage repair was set at 5%. Participants were asked to choose between the one- and two-stage approaches, with differing mortality rates for the two-stage approach. The scenarios included options when the two-stage combined mortality rate was lower than the one-stage mortality, and the first stage mortality rate was at 1% and 3%, and when the two-stage combined mortality rate was the same as that for one-stage mortality, these being set at 1% and 3%. When the two-stage combined mortality rate was lower than that of the one-stage repair, participants were more likely to choose the two-stage approach if the first stage mortality rate was 1% as compared to 3% (57% and 44%, respectively, p = 0.04). When the two-stage combined mortality rate was the same as the one-stage approach, participants choosing the two-stage approach when the mortality rate was set at 1%, and when it was raised to 3%, were not significantly different (42% and 34%, respectively, p = 0.24). When the combined two-stage mortality was the same as that set for one-stage repair, participants with no insurance were less likely to choose the two-stage approach than those covered by insurance (p = 0.03). In the chosen scenarios, when the mortality for a two-stage combined approach is the same as that for one-staged repair, more parents choose the one-staged repair. If the two-stage combined mortality is lower than that for one-staged repair, parents are more likely to choose the two-stage repair if the mortality for the first stage is lower. When the mortality rates for the one-stage and two-stage approaches are the same, people without insurance are more likely to choose one-staged repair.

Detecting objects from images is a challenging problem in the domain of computer vision and plays a very crucial role for wide range of real-time applications. The ever-increasing growth of deep learning due to availability of large training data and powerful GPUs helped computer vision community to build commercial products and services which were not possible a decade ago. Deep learning architectures especially convolutional neural networks have achieved state-of-the-art performance on worldwide competitions for visual recognition like ILSVRC, PASCAL VOC. Deep learning techniques alleviate the need of human expertise from designing the handcrafted features and automatically learn the features. This resulted into use of deep architectures in many domains like computer vision (image classification, visual recognition) and natural language processing (language modeling, speech recognition). Object detection is one such promising area immensely needed to be used in automated applications like self-driving cars, robotics, drone image analysis. This paper analytically reviews state-of-the-art deep learning techniques based on convolutional neural networks for object detection.

Spiking Neural Networks (SNNs), as a biologically inspired computational model, have garnered significant attention in object detection and image classification due to their event-driven mechanism and low-power characteristics. However, in object detection tasks, the residual structures in conventional networks introduce nonspiking operations, posing a critical challenge for SNNs. To address this issue, we propose a multi-layer feature cascade fusion SNN (MFCF-SNN) for object detection. During feature extraction, our novel multi-level cascaded feature extraction module replaces residual connections with cascade operations, eliminating nonspiking computations while enhancing gradient propagation to deeper layers. For downsampling, we introduce a pooling-convolution module that combines max-pooling and spiking convolution, effectively preserving feature information and improving gradient flow. These two modules collectively ensure pure spike-based computation while facilitating deep network training, thereby enhancing detection accuracy. Experimental results on the PASCAL VOC 2012 and SSDD datasets demonstrate state-of-the-art performance, validating the effectiveness of our approach in advancing SNN-based object detection.

In this paper, we present a hardware-software implementation of a deep neural network for object detection based on a point cloud obtained by a LiDAR sensor. The Brevitas / PyTorch tools were used for network quantisation and the FINN tool for hardware implementation in the reprogrammable Zynq UltraScale+ MPSoC device. The PointPillars network was used in the research, as it is a reasonable compromise between detection accuracy and calculation complexity. The obtained results show that quite a significant computation precision limitation along with a few network architecture simplifications allows the solution to be implemented on an heterogeneous embedded platform with reasonable detection accuracy.

In the recent generations, object detection (OD) has played an important role ranging from navigation of autonomous vehicles to video data compression. In the area of OD, deep learning (DL) has played a vital role in detecting the objects automatically. Breakthroughs have been achieved in the field of object detection with the simultaneous advancements in the field of DL. In this article, the author proposes a region-based neural network for detecting desired object in which it overcomes the computational complexity acquired by convolutional neural networks and provides a better accuracy. For training larger datasets and reusability, the deep learning principles are also proposed.

The effectiveness of object detection largely depends on the availability of large annotated datasets to train the deep network successfully; however, obtaining a large-scale dataset is expensive and remains a challenge. In this work, we explore two different GAN-based approaches for data augmentation of agricultural images in a camouflaged environment. Camouflage is the property of an object which makes it hard to detect because of its similarity to its environment. We leverage paired and unpaired image-to-image translation to create synthetic images based on custom segmentation masks. We evaluate the quality of synthetic images by applying these to the object detection task as additional training samples. The experiments demonstrate that adversarial-based data augmentation significantly improves the accuracy of region-based convolutional neural network for object detection. Our findings show that when evaluated on the testing dataset, data augmentation achieves detection performance improvement of 3.97%. Given the difficulty of object detection task in camouflaged images, the result suggests that combining adversarial-based data augmentation with the original data can theoretically be synergistic in enhancing deep neural network efficiency to address the open problem of detecting objects in camouflaged environments.KeywordsGenerative adversarial networksData augmentationCamouflaged images

Deep Learning Models or Neural Networks are loosely modeled based on the Human brain. Neural Networks consist of thousands of simple processing units that are densely interconnected, and are a means of performing machine learning. They aim to recognize patterns in data that enable a machine to perform some tasks based on analyzing several examples. One popular field of Deep Learning is Computer Vision that aims to simulate the complex visual system of human beings. An object detection model for instance, might be fed on thousands of images of objects to find visual patterns in the images that consistently correlate with particular labels. However, human visual perception is based on both visual and non-visual modalities of data. This paper aims to propose a Neural Network for Object detection that use various modalities of data, specifically Images and Text, to perform the object detection task

Object detection is a core computer vision task that aims to localize and classify categories for various objects in an image. With the development of convolutional neural networks, deep learning methods have been widely used in the object detection task, achieving promising performance compared to traditional methods. However, designing a well-performing detection network is inefficient. It consumes too much hardware resources and time to trial, and it also heavily relies on expert knowledge. To efficiently design the neural network architecture, there has been a growing interest in automatically designing neural network architecture by Neural Architecture Search (NAS). In this paper, we propose a Memory-Efficient Multi-Agent Neural Architecture Search (MEMA-NAS) framework in end-to-end object detection neural network. Specifically, we introduce the multi-agent learning to search holistic architecture of the detection network. In this way, a lot of GPU memory is saved, allowing us to search each module’s architecture of the detection network simultaneously. To find a better tradeoff between the precision and computational costs, we add the resource constraint in our method. Search experiments on multiple datasets show that MEMA-NAS achieves state-of-the-art results in search efficiency and precision.

The influence of timing on the functional and morphological result after nerve grafting: an experimental study in rabbits.

Deep Convolutional Neural Networks (CNN) are the state-of-the-art performers for the object detection task. It is well known that object detection requires more com- putation and memory than image classification. In this work, we propose LCDet, a fully-convolutional neural net- work for generic object detection that aims to work in em- bedded systems. We design and develop an end-to-end TensorFlow(TF)-based model. The detection works by a single forward pass through the network. Additionally, we employ 8-bit quantization on the learned weights. As a use case, we choose face detection and train the proposed model on images containing a varying number of faces of different sizes. We evaluate the face detection perfor- mance on publicly available dataset FDDB and Widerface. Our experimental results show that the proposed method achieves comparative accuracy comparing with state-of- the-art CNN-based face detection methods while reducing the model size by 3× and memory-BW by 3 - 4× compar- ing with one of the best real-time CNN-based object de- tector YOLO [23]. Our 8-bit fixed-point TF-model pro- vides additional 4× memory reduction while keeping the accuracy nearly as good as the floating point model and achieves 20× performance gain compared to the floating point model. Thus the proposed model is amenable for em- bedded implementations and is generic to be extended to any number of categories of objects.

Application of Deep Learning for Object Detection

In this paper, we will study the basic flow and the principle of state-of-the-art object detection technique (i.e. Faster R-CNN) and improve it further with the inclusion of two strategies into it. Firstly, we propose a multi-layer features merging strategy by using a concatenation layer. Secondly, we introduce a contextual learning scheme for Faster R-CNN. Previously, Faster R-CNN just uses regional features. Contextual features are added with the regional features for the classification and detection task. Our improvement on Faster R-CNN shows promising results. We call our improved Faster R-CNN network as ID-CNN (Intelligent Detection Using Convolutional Neural Network) as its detection accuracy is better. Therefore, we call it as an intelligent detector. We use a deep VGG-16 model as our base model, as Faster R-CNN did. We evaluated our ID-CNN on Pascal VOC public datasets. Experimental results show that ID-CNN can effectively improve the object detection average precision to some extent. On VOC 2007 and 2012, we achieved a mean average precision (mAP) of 74.7% and 71.9%, respectively. ID-CNN is also end-to-end trainable with the same alternating fine-tuning optimization scheme of Faster R-CNN. Finally, we compared ID-CNN with Faster R-CNN on ImageNet object detection dataset and we achieved mAP of 48.1% compared with 46.2% for Faster R-CNN.

The detection of rotated objects is a meaningful and challenging research work. Although the state-of-the-art deep learning models have feature invariance, especially convolutional neural networks (CNNs), their architectures did not specifically design for rotation invariance. They only slightly compensate for this feature through pooling layers. In this study, we propose a novel network, named LPNet, to solve the problem of object rotation. LPNet improves the detection accuracy by combining retina-like log-polar transformation. Furthermore, LPNet is a plug-and-play architecture for object detection and recognition. It consists of two parts, which we name as encoder and decoder. An encoder extracts images which feature in log-polar coordinates while a decoder eliminates image noise in cartesian coordinates. Moreover, according to the movement of center points, LPNet has stable and sliding modes. LPNet takes the single-shot multibox detector (SSD) network as the baseline network and the visual geometry group (VGG16) as the feature extraction backbone network. The experiment results show that, compared with conventional SSD networks, the mean average precision (mAP) of LPNet increased by 3.4% for regular objects and by 17.6% for rotated objects.