时间：2020年10月22日 下午3：00

地点：理科楼B311

标题：《A Cascaded R-CNN with Multiscale Attention and Imbalanced Samples for Traffic Sign Detection》

汇报人：谢志鹏

摘要：

In recent years, the deep learning is applied to the field of traffic sign detection methods which achieves excellent performance. However, there are two main challenges in traffic sign detection to be solve urgently. For one thing, some traffic signs of small size are more difficult to detect than those of large size so that the small traffic signs are undetected. For another, some false signs are always detected because of interferences caused by the illumination variation, bad weather and some signs similar to the true traffic signs. Therefore, to solve the undetection and false detection, we first propose a cascaded R-CNN to obtain the multiscale features in pyramids. Each layer of the cascaded network except the first layer fuses the output bounding box of the previous one layer for joint training. This method contributes to the traffic sign detection. Then, we propose a multiscale attention method to obtain the weighted multiscale features by dot-product and softmax, which is summed to fine the features to highlight the traffic sign features and improve the accuracy of the traffic sign detection. Finally, we increase the number of difficult negative samples for dataset balance and data augmentation in the training to relieve the interference by complex environment and similar false traffic signs. The data augment method expands the German traffic sign training dataset by simulation of complex environment changes. We conduct numerous experiments to verify the effectiveness of our proposed algorithm. The accuracy and recall rate of our method are 98.7% and 90.5% in GTSDB, 99.7% and 83.62% in CCTSDB and 98.9% and 85.6% in Lisa dataset respectively.

录取期刊：IEEE ACCESS

标题：《An Improved Differential Fault Analysis on Block Cipher KLEIN-64》

汇报人：孔曼

摘要：

KLEIN-64 is a lightweight block cipher designed for resource-constrained environment, and it has advantages in software performance and hardware implementation. Recent investigation shows that KLEIN-64 is vulnerable to differential fault attack (DFA). In this paper, an improved DFA is performed to KLEIN-64. It is found that the differential propagation path and the distribution of the S-box can be fully utilized to distinguish the correct and wrong keys when a half-byte fault is injected in the 10th round. By analyzing the difference matrix before the last round of S-box, the location of fault injection can be limited to a small range. Thus, this improved analysis can greatly improve the attack efficiency. For the best case, the scale of brute-force attack is only 16. While for the worst case, the scale of brute-force attack is far less than 232 with another half byte fault injection, and the probability for this case is 1/64. Furthermore, the measures for KLEIN-64 in resisting the improved DFA is proposed.

录取期刊：Computers, Materials & Continua

标题：《Depth occlusion perception feature analysis for person re-identification》

汇报人：伍洁

摘要：Person re-identification (ReID) has achieved significant improvement under the setting of matching two holistic person images. However, persons are easily occluded by the various objects and other persons in real-world scenarios, making Person ReID a challenging task. In this paper, we propose a novel method named Pose-Driven Visibility Model (PDVM) to effectively solve the degradation of recognition perfor- mance caused by occlusion. Firstly, we extract non-occluded human body features through pose estima- tion, pay attention to the salient features of non-human parts through self-attention mechanism, and obtains the final feature representation after the combination. Secondly, we more accurately locate per- son body parts by utilizing the detected human keypoints in different occlusion situations, effectively reducing the impact of unalignment and realizing better matching for persons. We implement extensive experiments on Occluded-DukeMTMC and Partial-REID. Our proposed method achieves state of the art performances which reaches 53.0% Rank-1 accuracy on Occluded-DukeMTMC dataset and ablation analy- sis also verify the effectiveness of our method.

录取期刊：Pattern Recognition Letters