Zobrazeno 1 - 10
of 1 464
pro vyhledávání: '"Zhang, Ziqi"'
Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN's computation speed b
Externí odkaz:
http://arxiv.org/abs/2411.09945
Autor:
Zhou, Ce, Yan, Qiben, Kent, Daniel, Wang, Guangjing, Ding, Weikang, Zhang, Ziqi, Radha, Hayder
Monocular Depth Estimation (MDE) is a pivotal component of vision-based Autonomous Driving (AD) systems, enabling vehicles to estimate the depth of surrounding objects using a single camera image. This estimation guides essential driving decisions, s
Externí odkaz:
http://arxiv.org/abs/2411.00192
Monocular Depth Estimation (MDE) plays a crucial role in vision-based Autonomous Driving (AD) systems. It utilizes a single-camera image to determine the depth of objects, facilitating driving decisions such as braking a few meters in front of a dete
Externí odkaz:
http://arxiv.org/abs/2409.17376
Autor:
Chen, Yuxin, Ma, Zongyang, Zhang, Ziqi, Qi, Zhongang, Yuan, Chunfeng, Li, Bing, Pu, Junfu, Shan, Ying, Qi, Xiaojuan, Hu, Weiming
Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from cross-encoder to
Externí odkaz:
http://arxiv.org/abs/2407.07479
Autor:
Ma, Zongyang, Zhang, Ziqi, Chen, Yuxin, Qi, Zhongang, Yuan, Chunfeng, Li, Bing, Luo, Yingmin, Li, Xu, Qi, Xiaojuan, Shan, Ying, Hu, Weiming
Understanding the content of events occurring in the video and their inherent temporal logic is crucial for video-text retrieval. However, web-crawled pre-training datasets often lack sufficient event information, and the widely adopted video-level c
Externí odkaz:
http://arxiv.org/abs/2407.07478
Publikováno v:
EMNLP 2024
Chain of thought (CoT) is a reasoning framework that can enhance the performance of Large Language Models (LLMs) on complex inference tasks. In particular, among various studies related to CoT, multi-path inference stands out as a simple yet effectiv
Externí odkaz:
http://arxiv.org/abs/2407.07099
Query-based black-box attacks have emerged as a significant threat to machine learning systems, where adversaries can manipulate the input queries to generate adversarial examples that can cause misclassification of the model. To counter these attack
Externí odkaz:
http://arxiv.org/abs/2405.20641
Typically, traditional Imitation Learning (IL) methods first shape a reward or Q function and then use this shaped function within a reinforcement learning (RL) framework to optimize the empirical policy. However, if the shaped reward/Q function does
Externí odkaz:
http://arxiv.org/abs/2405.20351
As a data-driven paradigm, offline reinforcement learning (RL) has been formulated as sequence modeling that conditions on the hindsight information including returns, goal or future trajectory. Although promising, this supervised paradigm overlooks
Externí odkaz:
http://arxiv.org/abs/2405.08740
Convective heat transfer is crucial for photovoltaic (PV) systems, as the power generation of PV is sensitive to temperature. The configuration of PV arrays have a significant impact on convective heat transfer by influencing turbulent characteristic
Externí odkaz:
http://arxiv.org/abs/2403.06418