Recent progress on one-stage detectors focuses on improving the quality of bounding boxes, while they pay less attention to the classification head. In this work, we focus on investigating the influence of the classif...
详细信息
Recent progress on one-stage detectors focuses on improving the quality of bounding boxes, while they pay less attention to the classification head. In this work, we focus on investigating the influence of the classification head. To understand the behavior of the classifier in one-stage detectors, we resort to the methods of the Explainable deep learning area. We visualize its learned representations via activation maps and analyze its robustness to image scene context. Based on the analysis, we observe that the classifier limits the performance of the detector due to its limited receptive field and the lack of object locations. Then, we design a simple but efficient location-aware multi-dilation module (LAMD) to enhance the weak classifier. We conduct extensive experiments on the COCO benchmark to validate the effectiveness of LAMD. The results suggest that our LAMD can achieve consistent improvements and leads to robust detection across various one-stage detectors with different backbones. (C) 2020 Elsevier Ltd. All rights reserved.
In order to improve the flexibility and intelligence of the grasping robots in the field of logistics, a research on visual robot objects recognition method based on deep learning was carried out. Aiming at this probl...
详细信息
ISBN:
(数字)9781728181455
ISBN:
(纸本)9781728181462
In order to improve the flexibility and intelligence of the grasping robots in the field of logistics, a research on visual robot objects recognition method based on deep learning was carried out. Aiming at this problem, a real-time object recognition and grasp detection scheme is proposed, the rectangle of the items to be operated is defined, the convolutional neural network structure model is established, and the loss function is defined. Finally, experimental verification was performed, including data processing and network model training, and the results analysis showed the effectiveness of this research method.
In this paper, we propose a fast method based on deep neural networks to detect and recognize Korean characters in traffic guide signs. To detect character candidates quickly, we first employ a region proposal network...
详细信息
ISBN:
(纸本)9781538644584
In this paper, we propose a fast method based on deep neural networks to detect and recognize Korean characters in traffic guide signs. To detect character candidates quickly, we first employ a region proposal network (RPN) which is in this paper ResNet-18, being relatively shallow. We also apply the Inception architecture to residual blocks for reducing parameters of the network. After character candidates are detected, we classify them into 709 Korean characters by using a classification network (CLSN). Similar to the RPN, our CLSN consists of residual blocks with the Inception architecture. In experiments, we achieved 97.69 % of accuracy at 5.9fps on both detection and recognition of Korean characters in traffic guide signs.
暂无评论