Search Results for author:
Found 6 papers, 1 papers with code
Automatic Rank Selection for High-Speed Convolutional Neural Network
In this paper, we define rank selection as a combinatorial optimization problem and propose a methodology to minimize network complexity while maintaining the desired accuracy.
Combinatorial Optimization
Vocal Bursts Intensity Prediction
Efficient Neural Network Compression
The better accuracy and complexity compromise, as well as the extremely fast speed of our method makes it suitable for neural network compression.
Fine-Tuning DARTS for Image Classification
Our method offers a good trade-off between the number of parameters and classification accuracy.
Ranked #1 on
Image Classification
on Fashion-MNIST
Plug-and-Play Anomaly Detection with Expectation Maximization Filtering
With a single epoch of training, our method improves the AUC by 8. 03% compared to the convolutional LSTM-based approach.
Increased-Range Unsupervised Monocular Depth Estimation
Small-baseline stereo pairs provide small depth range but handle occlusions well.
Monocular Depth Estimation
Unsupervised Monocular Depth Estimation
Uniform Subdivision of Omnidirectional Camera Space for Efficient Spherical Stereo Matching
However, stereo matching performance on these image formats has been lower than the conventional stereo due to severe image distortion near pole regions.
