SelectScale: Mining More Patterns from Images via Selective and Soft Dropout
Authors: Zhengsu Chen, Jianwei Niu, Xuefeng Liu, Shaojie Tang
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Using Select Scale, we improve the performance of CNNs on CIFAR and Image Net. |
| Researcher Affiliation | Academia | Zhengsu Chen1 , Jianwei Niu1,2,3 , Xuefeng Liu1 and Shaojie Tang4 1Beihang University 2Hangzhou Innovation Institute of Beihang University 3Zhengzhou University 4University of Texas at Dallas {danczs, niujianwei, liu xuefeng}@buaa.edu.com, tangshaojie@gmail.com |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | Yes | CIFAR-10 and CIFAR-100 are colored 32 32 natural image datasets that consist of 50,000 images in the training set and 10,000 images in the testing set. ... ILSVRC2012 is a subset of Image Net [Russakovsky et al., 2015] database. |
| Dataset Splits | Yes | CIFAR-10 and CIFAR-100 are colored 32 32 natural image datasets that consist of 50,000 images in the training set and 10,000 images in the testing set. ... This dataset contains 1.3M images in the training set and 50K images in the validation set. |
| Hardware Specification | No | The paper does not provide specific hardware details such as exact GPU/CPU models or processor types used for running experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers. |
| Experiment Setup | Yes | If not speciļ¬ed, the networks for CIFAR are trained for 200 epochs with 0.1 initial learning rate. The learning rate drops by 0.2 at 60, 120 and 160 epochs following [Zagoruyko and Komodakis, 2016]. The batch size is 128 and the weight decay is 0.0005. ... On Image Net, ... The batch size is 256 and the weight decay is 0.0001. The model is trained for 105 epochs with a 0.1 initial learning rate. The learning rate drops by 0.1 at 30, 60, 90 and 100 epochs. |