書誌事項
- タイトル別名
-
- Model Compression for ResNet via Layer Erasure and Re-training
説明
<p>Residual Networks with convolutional layers are widely used in the field of machine learning. Since they effectively extract features from input data by stacking multiple layers, they can achieve high accuracy in many applications. However, the stacking of many layers raises their computation costs. To address this problem, we propose Network Implosion, it erases multiple layers from Residual Networks without degrading accuracy. Our key idea is to introduce a priority term that identifies the importance of a layer; we can select unimportant layers according to the priority and erase them after the training. In addition, we retrain the networks to avoid critical drops in accuracy after layer erasure. Our experiments show that Network Implosion can, for classification on CIFAR10/100 and ImageNet, reduce the number of layers by 24.00% ～ 42.86% without any drop in accuracy.</p>
収録刊行物
-
- 人工知能学会論文誌
-
人工知能学会論文誌 35 (3), C-JA3_1-10, 2020-05-01
一般社団法人 人工知能学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390566775132701440
-
- NII論文ID
- 130007839983
-
- ISSN
- 13468030
- 13460714
-
- 本文言語コード
- ja
-
- データソース種別
-
- JaLC
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可
