Robust Regularization with Adversarial Labelling of Perturbed Samples
Authors: Xiaohui Guo, Richong Zhang, Yaowei Zheng, Yongyi Mao
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on the SVHN, CIFAR-10, CIFAR-100 and Tiny-Image Net datasets show that the ALPS has a state-of-the-art regularization performance while also serving as an effective adversarial training scheme. |
| Researcher Affiliation | Academia | 1Hangzhou Innovation Institute, Beihang University, Hangzhou, China 2BDBC and SKLSDE, School of Computer Science and Engineering, Beihang University, Beijing, China 3School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada |
| Pseudocode | Yes | Algorithm 1 ALPS Regularized Training |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository. |
| Open Datasets | Yes | Four publicly available benchmark datasets are used. The SVHN dataset has 10 classes for the digit numbers, and 73257 training digits, 26032 test digits. The CIFAR-10 and CIFAR100 dataset have the same image set but different label strategy. CIFAR-10 has 10 classes containing 6000 images each, and CIFAR-100 has 100 classes containing 600 images each. The two datasets are split with 5:1 for training and testing per class. The Tiny-Image Net dataset has 200 classes. Each class has 500 training images, 50 validation images, and 50 test images. |
| Dataset Splits | Yes | The two datasets are split with 5:1 for training and testing per class. The Tiny-Image Net dataset has 200 classes. Each class has 500 training images, 50 validation images, and 50 test images. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions software components like "SGD with momentum optimizer" but does not specify version numbers for any libraries or frameworks used (e.g., PyTorch, TensorFlow, specific Python version). |
| Experiment Setup | Yes | In training processes, we adopt the geometrical transformation augmentation methods, random crops and horizontal flips. Normalization is performed on both training and test set with the mean and standard derivation computed on training set. We follow the training procedure of [Zhang et al., 2018], where SGD with momentum optimizer is used with a stepwise learning rate decay. Weight decay factor is set to 10 4. For Dropout, we randomly deactivate 50% of the neurons in the penultimate layer at each iteration. The label smoothing ratio is set to 0.1. The Beta hyper-parameter of Mix Up α is set to 1. For ALPS, the mode of asymmetric Beta distribution is chosen in the range (0.75, 1), and the L1 ball constraint ϵ in adversarial labelling is restricted to (0, 0.5) empirically. |