18 citations · 45 across the 5 of their papers we have counts for
5 papers · 1 filter
Box-Level Class-Balanced Sampling for Active Object Detection
Jingyi Liao, Xun Xu, Chuan-Sheng Foo +1
Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-lev…
Exploring Spatial Diversity for Region-based Active Learning
Lile Cai, Xun Xu, Lining Zhang +1
State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation c…
Exploring Active Learning for Semiconductor Defect Segmentation
Lile Cai, Ramanpreet Singh Pahwa, Xun Xu +4
The development of X-Ray microscopy (XRM) technology has enabled non-destructive inspection of semiconductor structures for defect identification. Deep learning is widely used as t…
Revisiting Pretraining for Semi-Supervised Learning in the Low-Label Regime
Xun Xu, Jingyi Liao, Lile Cai +5
Semi-supervised learning (SSL) addresses the lack of labeled data by exploiting large unlabeled data through pseudolabeling. However, in the extremely low-label regime, pseudo labe…
Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach
Xian Shi, Xun Xu, Ke Chen +3
Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets. Howe…