Zobrazeno 1 - 10
of 2 952
pro vyhledávání: '"Zhang, JingWei"'
Saliency maps are widely used in the computer vision community for interpreting neural network classifiers. However, due to the randomness of training samples and optimization algorithms, the resulting saliency maps suffer from a significant level of
Externí odkaz:
http://arxiv.org/abs/2412.14509
Autor:
Zhang, Jingwei, Nguyen, Anh Tien, Han, Xi, Trinh, Vincent Quoc-Huy, Qin, Hong, Samaras, Dimitris, Hosseini, Mahdi S.
Efficiently modeling large 2D contexts is essential for various fields including Giga-Pixel Whole Slide Imaging (WSI) and remote sensing. Transformer-based models offer high parallelism but face challenges due to their quadratic complexity for handli
Externí odkaz:
http://arxiv.org/abs/2412.00678
Autor:
Zhang, Jingwei, Lampe, Thomas, Abdolmaleki, Abbas, Springenberg, Jost Tobias, Riedmiller, Martin
We propose an agent architecture that automates parts of the common reinforcement learning experiment workflow, to enable automated mastery of control domains for embodied agents. To do so, it leverages a VLM to perform some of the capabilities norma
Externí odkaz:
http://arxiv.org/abs/2409.03402
Online linear programming (OLP) has gained significant attention from both researchers and practitioners due to its extensive applications, such as online auction, network revenue management, order fulfillment and advertising. Existing OLP algorithms
Externí odkaz:
http://arxiv.org/abs/2408.00465
Autor:
Ospanov, Azim, Zhang, Jingwei, Jalali, Mohammad, Cao, Xuenan, Bogdanov, Andrej, Farnia, Farzan
While standard evaluation scores for generative models are mostly reference-based, a reference-dependent assessment of generative models could be generally difficult due to the unavailability of applicable reference datasets. Recently, the reference-
Externí odkaz:
http://arxiv.org/abs/2407.02961
Few-shot gradient methods have been extensively utilized in existing model pruning methods, where the model weights are regarded as static values and the effects of potential weight perturbations are not considered. However, the widely used large lan
Externí odkaz:
http://arxiv.org/abs/2406.07017
Autor:
Miao, Qiaomu, Graikos, Alexandros, Zhang, Jingwei, Mondal, Sounak, Hoai, Minh, Samaras, Dimitris
Training gaze following models requires a large number of images with gaze target coordinates annotated by human annotators, which is a laborious and inherently ambiguous process. We propose the first semi-supervised method for gaze following by intr
Externí odkaz:
http://arxiv.org/abs/2406.02774
Autor:
Sun, Jiahao, Qing, Chunmei, Xu, Xiang, Kong, Lingdong, Liu, Youquan, Li, Li, Zhu, Chenming, Zhang, Jingwei, Xiao, Zeqi, Chen, Runnan, Wang, Tai, Zhang, Wenwei, Chen, Kai
In the rapidly evolving field of autonomous driving, precise segmentation of LiDAR data is crucial for understanding complex 3D environments. Traditional approaches often rely on disparate, standalone codebases, hindering unified advancements and fai
Externí odkaz:
http://arxiv.org/abs/2405.14870
Autor:
Zhang, Jingwei, Farnia, Farzan
Transportation of samples across different domains is a central task in several machine learning problems. A sensible requirement for domain transfer tasks in computer vision and language domains is the sparsity of the transportation map, i.e., the t
Externí odkaz:
http://arxiv.org/abs/2405.07489
An interpretable comparison of generative models requires the identification of sample types produced more frequently by each of the involved models. While several quantitative scores have been proposed in the literature to rank different generative
Externí odkaz:
http://arxiv.org/abs/2405.02700