152 citations · 194 across the 6 of their papers we have counts for
4 papers · 1 filter
Polarized Self-Attention: Towards High-quality Pixel-wise Regression
Huajun Liu, Fuqiang Liu, Xinyi Fan +1
Pixel-wise regression is probably the most common problem in fine-grained computer vision tasks, such as estimating keypoint heatmaps and segmentation masks. These regression probl…
Object Recognition Based on Amounts of Unlabeled Data
Fuqiang Liu, Fukun Bi, Liang Chen
This paper proposes a novel semi-supervised method on object recognition. First, based on Boost Picking, a universal algorithm, Boost Picking Teaching (BPT), is proposed to train a…
Feature-Area Optimization: A Novel SAR Image Registration Method
Fuqiang Liu, Fukun Bi, Liang Chen +2
This letter proposes a synthetic aperture radar (SAR) image registration method named Feature-Area Optimization (FAO). First, the traditional area-based optimization model is recon…
Boost Picking: A Universal Method on Converting Supervised Classification to Semi-supervised Classification
Fuqiang Liu, Fukun Bi, Yiding Yang +1
This paper proposes a universal method, Boost Picking, to train supervised classification models mainly by un-labeled data. Boost Picking only adopts two weak classifiers to estima…