Improvement of learning for CNN with ReLU activation by sparse regularization H Ide, T Kurita 2017 international joint conference on neural networks (IJCNN), 2684-2691, 2017 | 378 | 2017 |
Robust pruning for efficient CNNs H Ide, T Kobayashi, K Watanabe, T Kurita Pattern Recognition Letters 135, 90-98, 2020 | 18 | 2020 |
Texture segmentation using Siamese network and hierarchical region merging R Yamada, H Ide, N Yudistira, T Kurita 2018 24th International Conference on Pattern Recognition (ICPR), 2735-2740, 2018 | 6 | 2018 |
Convolutional neural network with discriminant criterion for input of each neuron in output layer H Ide, T Kurita Neural Information Processing: 25th International Conference, ICONIP 2018 …, 2018 | 3 | 2018 |
Low level visual feature extraction by learning of multiple tasks for convolutional neural networks H Ide, T Kurita 2016 International joint conference on neural networks (IJCNN), 3620-3627, 2016 | 2 | 2016 |
Decomposition of Invariant and Variant Features by Using Convolutional Autoencoder H Ide, H Fujishige, J Miyao, T Kurita International Workshop on Frontiers of Computer Vision, 97-111, 2022 | | 2022 |
Simple ConvNet Based on Bag of MLP-Based Local Descriptors T Kobayashi, H Ide, K Watanabe Neural Information Processing: 26th International Conference, ICONIP 2019 …, 2019 | | 2019 |
CNN における ReLU 活性化関数に対するスパース正則化の適用と分析 井手秀徳, 栗田多喜夫 電子情報通信学会論文誌 D 101 (8), 1110-1119, 2018 | | 2018 |
Analysis of sparse regularization for ReLU activation function in CNN H Ide, T Kurita IEICE Technical Report; IEICE Tech. Rep. 116 (528), 123-128, 2017 | | 2017 |
Analysis of Sparse Regularization for ReLU Activation Function in CNN 井手秀徳, 栗田多喜夫 電子情報通信学会技術研究報告= IEICE technical report: 信学技報 116 (527 …, 2017 | | 2017 |