Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Ye, Rongguang"'
Autor:
Kou, Wei-Bin, Lin, Qingfeng, Tang, Ming, Ye, Rongguang, Wang, Shuai, Zhu, Guangxu, Wu, Yik-Chung
Street Scene Semantic Understanding (denoted as TriSU) is a complex task for autonomous driving (AD). However, inference model trained from data in a particular geographical region faces poor generalization when applied in other regions due to inter-
Externí odkaz:
http://arxiv.org/abs/2409.19560
Autor:
Kou, Wei-Bin, Zhu, Guangxu, Ye, Rongguang, Wang, Shuai, Lin, Qingfeng, Tang, Ming, Wu, Yik-Chung
Various adverse weather conditions pose a significant challenge to autonomous driving (AD) perception. A common strategy is to minimize the disparity between images captured in clear and adverse weather conditions. However, this technique typically r
Externí odkaz:
http://arxiv.org/abs/2409.14737
Publikováno v:
IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2024)
Pareto set learning (PSL) is an emerging approach for acquiring the complete Pareto set of a multi-objective optimization problem. Existing methods primarily rely on the mapping of preference vectors in the objective space to Pareto optimal solutions
Externí odkaz:
http://arxiv.org/abs/2408.05778
Autor:
Kou, Wei-Bin, Lin, Qingfeng, Tang, Ming, Xu, Sheng, Ye, Rongguang, Leng, Yang, Wang, Shuai, Li, Guofa, Chen, Zhenyu, Zhu, Guangxu, Wu, Yik-Chung
Deep learning-based Autonomous Driving (AD) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL) could improve the generalization of an AD model (known as FedAD syste
Externí odkaz:
http://arxiv.org/abs/2405.04146
Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model for any special group (e.g., male or female) of sensitive features. However, there is a trade-off between model performance and fairness, i.e., impr
Externí odkaz:
http://arxiv.org/abs/2404.08973
Recently, Pareto Set Learning (PSL) has been proposed for learning the entire Pareto set using a neural network. PSL employs preference vectors to scalarize multiple objectives, facilitating the learning of mappings from preference vectors to specifi
Externí odkaz:
http://arxiv.org/abs/2404.08414
Pareto front learning is a technique that introduces preference vectors in a neural network to approximate the Pareto front. Previous Pareto front learning methods have demonstrated high performance in approximating simple Pareto fronts. These method
Externí odkaz:
http://arxiv.org/abs/2404.08397
Pareto Set Learning (PSL) is an emerging research area in multi-objective optimization, focusing on training neural networks to learn the mapping from preference vectors to Pareto optimal solutions. However, existing PSL methods are limited to addres
Externí odkaz:
http://arxiv.org/abs/2404.01224
Autor:
Zheng, Zhaohui, Ye, Rongguang, Hou, Qibin, Ren, Dongwei, Wang, Ping, Zuo, Wangmeng, Cheng, Ming-Ming
Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the prediction logits due to its inefficiency in distilling the localization information. In this paper, we investigate whether l
Externí odkaz:
http://arxiv.org/abs/2204.05957
Autor:
Zheng, Zhaohui, Ye, Rongguang, Wang, Ping, Ren, Dongwei, Zuo, Wangmeng, Hou, Qibin, Cheng, Ming-Ming
Knowledge distillation (KD) has witnessed its powerful capability in learning compact models in object detection. Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of mimicking class
Externí odkaz:
http://arxiv.org/abs/2102.12252