Zobrazeno 1 - 10
of 368
pro vyhledávání: '"Vong Chi-Man"'
Conformal prediction, as an emerging uncertainty quantification technique, typically functions as post-hoc processing for the outputs of trained classifiers. To optimize the classifier for maximum predictive efficiency, Conformal Training rectifies t
Externí odkaz:
http://arxiv.org/abs/2410.09408
Hyperspectral image (HSI) classification involves assigning unique labels to each pixel to identify various land cover categories. While deep classifiers have achieved high predictive accuracy in this field, they lack the ability to rigorously quanti
Externí odkaz:
http://arxiv.org/abs/2409.01236
Autor:
Sun, Jian, Dai, Yuqi, Vong, Chi-Man, Xu, Qing, Li, Shengbo Eben, Wang, Jianqiang, He, Lei, Li, Keqiang
Bird's-eye-view (BEV) semantic segmentation is becoming crucial in autonomous driving systems. It realizes ego-vehicle surrounding environment perception by projecting 2D multi-view images into 3D world space. Recently, BEV segmentation has made nota
Externí odkaz:
http://arxiv.org/abs/2407.13137
Autor:
Lai, Qi, Vong, Chi-Man
Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is still a significant performance gap between WSSS
Externí odkaz:
http://arxiv.org/abs/2405.04913
Partial Label Learning (PLL) tackles model learning from the data with inexact labels under the assumption that training and test objects are in the same distribution, i.e., closed-set scenario. Nevertheless, this assumption does not hold in real-wor
Externí odkaz:
http://arxiv.org/abs/2403.06681
In semantic segmentation, accurate prediction masks are crucial for downstream tasks such as medical image analysis and image editing. Due to the lack of annotated data, few-shot semantic segmentation (FSS) performs poorly in predicting masks with pr
Externí odkaz:
http://arxiv.org/abs/2401.09826
Multi-instance multi-label (MIML) learning is widely applicated in numerous domains, such as the image classification where one image contains multiple instances correlated with multiple logic labels simultaneously. The related labels in existing MIM
Externí odkaz:
http://arxiv.org/abs/2304.10705
described by multiple instances (e.g., image patches) and simultaneously associated with multiple labels. Existing MIML methods are useful in many applications but most of which suffer from relatively low accuracy and training efficiency due to sever
Externí odkaz:
http://arxiv.org/abs/2209.02625
Publikováno v:
In Neurocomputing 14 November 2024 606
Publikováno v:
In Neural Networks October 2024 178