Models, code, and papers for "Yi-Min Wang":

TrueLabel + Confusions: A Spectrum of Probabilistic Models in Analyzing Multiple Ratings

Jun 18, 2012
Chao Liu, Yi-Min Wang

This paper revisits the problem of analyzing multiple ratings given by different judges. Different from previous work that focuses on distilling the true labels from noisy crowdsourcing ratings, we emphasize gaining diagnostic insights into our in-house well-trained judges. We generalize the well-known DawidSkene model (Dawid & Skene, 1979) to a spectrum of probabilistic models under the same "TrueLabel + Confusion" paradigm, and show that our proposed hierarchical Bayesian model, called HybridConfusion, consistently outperforms DawidSkene on both synthetic and real-world data sets.

* ICML2012 

  Click for Model/Code and Paper
Architecture-aware Network Pruning for Vision Quality Applications

Aug 05, 2019
Wei-Ting Wang, Han-Lin Li, Wei-Shiang Lin, Cheng-Ming Chiang, Yi-Min Tsai

Convolutional neural network (CNN) delivers impressive achievements in computer vision and machine learning field. However, CNN incurs high computational complexity, especially for vision quality applications because of large image resolution. In this paper, we propose an iterative architecture-aware pruning algorithm with adaptive magnitude threshold while cooperating with quality-metric measurement simultaneously. We show the performance improvement applied on vision quality applications and provide comprehensive analysis with flexible pruning configuration. With the proposed method, the Multiply-Accumulate (MAC) of state-of-the-art low-light imaging (SID) and super-resolution (EDSR) are reduced by 58% and 37% without quality drop, respectively. The memory bandwidth (BW) requirements of convolutional layer can be also reduced by 20% to 40%.

* Accepted to be Published in the 26th IEEE International Conference on Image Processing (ICIP 2019). Updated to contain the IEEE copyright notice 

  Click for Model/Code and Paper