Zobrazeno 1 - 10
of 2 683
pro vyhledávání: '"Xu, Jianhua"'
In recent years, current mainstream feature masking distillation methods mainly function by reconstructing selectively masked regions of a student network from the feature maps of a teacher network. In these methods, attention mechanisms can help to
Externí odkaz:
http://arxiv.org/abs/2407.13147
Autor:
Song, Wei, Li, Yadong, Xu, Jianhua, Wu, Guowei, Ming, Lingfeng, Yi, Kexin, Luo, Weihua, Li, Houyi, Du, Yi, Guo, Fangda, Yu, Kaicheng
As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human intelligence. However, existing benc
Externí odkaz:
http://arxiv.org/abs/2406.05343
Traditional LiDAR-based object detection research primarily focuses on closed-set scenarios, which falls short in complex real-world applications. Directly transferring existing 2D open-vocabulary models with some known LiDAR classes for open-vocabul
Externí odkaz:
http://arxiv.org/abs/2312.08876
Autor:
Yu, Linfeng, Xu, Jianhua, Shen, Chen, Zhang, Hongbin, Zheng, Xiong, Wang, Huiming, Qin, Zhenzhen, Qin, Guangzhao
The asymmetric properties of Janus two-dimensional materials commonly depend on chemical effects, such as different atoms, elements, material types, etc. Herein, based on carbon gene recombination strategy, we identify an intrinsic non-chemical Janus
Externí odkaz:
http://arxiv.org/abs/2309.05319
Recent mainstream masked distillation methods function by reconstructing selectively masked areas of a student network from the feature map of its teacher counterpart. In these methods, the masked regions need to be properly selected, such that recon
Externí odkaz:
http://arxiv.org/abs/2309.02719
Deep neural networks have garnered widespread attention due to their simplicity and flexibility in the fields of engineering and scientific calculation. In this study, we probe into solving a class of elliptic partial differential equations(PDEs) wit
Externí odkaz:
http://arxiv.org/abs/2306.13385
In face detection, low-resolution faces, such as numerous small faces of a human group in a crowded scene, are common in dense face prediction tasks. They usually contain limited visual clues and make small faces less distinguishable from the other s
Externí odkaz:
http://arxiv.org/abs/2306.02277
Sketch-based image retrieval, which aims to use sketches as queries to retrieve images containing the same query instance, receives increasing attention in recent years. Although dramatic progress has been made in sketch retrieval, few efforts are de
Externí odkaz:
http://arxiv.org/abs/2304.02214
In recent years, deep convolutional neural networks (CNN) have significantly advanced face detection. In particular, lightweight CNNbased architectures have achieved great success due to their lowcomplexity structure facilitating real-time detection
Externí odkaz:
http://arxiv.org/abs/2302.11816
As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation framework
Externí odkaz:
http://arxiv.org/abs/2301.13538