Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Tao, Mingyuan"'
Autor:
Liu, Kai, Fu, Zhihang, Chen, Chao, Jin, Sheng, Chen, Ze, Tao, Mingyuan, Jiang, Rongxin, Ye, Jieping
The key to OOD detection has two aspects: generalized feature representation and precise category description. Recently, vision-language models such as CLIP provide significant advances in both two issues, but constructing precise category descriptio
Externí odkaz:
http://arxiv.org/abs/2407.16725
Knowledge hallucination have raised widespread concerns for the security and reliability of deployed LLMs. Previous efforts in detecting hallucinations have been employed at logit-level uncertainty estimation or language-level self-consistency evalua
Externí odkaz:
http://arxiv.org/abs/2402.03744
Publikováno v:
NeurIPS 2023
For a machine learning model deployed in real world scenarios, the ability of detecting out-of-distribution (OOD) samples is indispensable and challenging. Most existing OOD detection methods focused on exploring advanced training skills or training-
Externí odkaz:
http://arxiv.org/abs/2402.10062
Change Detection (CD) has been attracting extensive interests with the availability of bi-temporal datasets. However, due to the huge cost of multi-temporal images acquisition and labeling, existing change detection datasets are small in quantity, sh
Externí odkaz:
http://arxiv.org/abs/2312.17428
With the increasing interest and rapid development of methods for Ultra-High Resolution (UHR) segmentation, a large-scale benchmark covering a wide range of scenes with full fine-grained dense annotations is urgently needed to facilitate the field. T
Externí odkaz:
http://arxiv.org/abs/2305.10899
Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student. However, low-level texture knowledge is also of vital importance for characterizing the local struct
Externí odkaz:
http://arxiv.org/abs/2305.03944
Existing long-tailed classification (LT) methods only focus on tackling the class-wise imbalance that head classes have more samples than tail classes, but overlook the attribute-wise imbalance. In fact, even if the class is balanced, samples within
Externí odkaz:
http://arxiv.org/abs/2207.09504
Autor:
Chen, Ze, Fu, Zhihang, Huang, Jianqiang, Tao, Mingyuan, Jiang, Rongxin, Tian, Xiang, Chen, Yaowu, Hua, Xian-sheng
Publikováno v:
Image and Vision Computing, Volume 116, 2021, 104314, ISSN 0262-8856
Weakly supervised object detection (WSOD), which is an effective way to train an object detection model using only image-level annotations, has attracted considerable attention from researchers. However, most of the existing methods, which are based
Externí odkaz:
http://arxiv.org/abs/2204.06899
Autor:
Chen, Ze, Fu, Zhihang, Huang, Jianqiang, Tao, Mingyuan, Li, Shengyu, Jiang, Rongxin, Tian, Xiang, Chen, Yaowu, Hua, Xian-sheng
Publikováno v:
Neurocomputing, Volume 469, 2022, Pages 310-320, ISSN 0925-2312
The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem, recent stu
Externí odkaz:
http://arxiv.org/abs/2204.00183
Autor:
Chen, Xiaoshuang, Zhao, Yiru, Qin, Yu, Jiang, Fei, Tao, Mingyuan, Hua, Xiansheng, Lu, Hongtao
Crowd counting aims to learn the crowd density distributions and estimate the number of objects (e.g. persons) in images. The perspective effect, which significantly influences the distribution of data points, plays an important role in crowd countin
Externí odkaz:
http://arxiv.org/abs/2111.00406