Search Results for author:
Found 4 papers, 1 papers with code
A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity
Although unlabeled data is readily available in pool-based AL, AL algorithms are usually evaluated by measuring the increase in supervised learning (SL) performance at consecutive acquisition steps.
UASNet: Uncertainty Adaptive Sampling Network for Deep Stereo Matching
Extensive experiments show that the proposed method achieves the highest ground truth covering ratio compared with other cascade cost volume based stereo matching methods.
Better Optimization can Reduce Sample Complexity: Active Semi-Supervised Learning via Convergence Rate Control
We name this AL scheme convergence rate control (CRC), and our experiments show that a deep neural network trained using a combination of CRC and a recently proposed SSL algorithm can quickly achieve high performance using far less labeled samples than SL.
PopEval: A Character-Level Approach to End-To-End Evaluation Compatible with Word-Level Benchmark Dataset
Compared to the other evaluation methods, the proposed evaluation algorithm was closer to the human's qualitative evaluation than other existing methods.
