Learning from Complementary Labels via Partial-Output Consistency Regularization
Authors: Deng-Bao Wang, Lei Feng, Min-Ling Zhang
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct a series of experiments showing that the proposed method achieves highly competitive performance in CLL. |
| Researcher Affiliation | Academia | Deng-Bao Wang,1,2 Lei Feng,3 Min-Ling Zhang1,2 1School of Computer Science and Engineering, Southeast University, Nanjing 210096, China 2Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China 3College of Computer Science, Chongqing University, Chongqing, 400044, China |
| Pseudocode | No | No explicit pseudocode or algorithm blocks were found. |
| Open Source Code | No | The paper does not contain any explicit statements or links indicating that the source code for the methodology is openly available. |
| Open Datasets | Yes | Datasets To verify the superiority of our method, we conduct experiments on three commonly used image datasets: SVHN, CIFAR-10 and CIFAR-100. |
| Dataset Splits | No | SVHN contains 73,257 training samples and 26,032 test samples. Both of CIFAR-10 and CIFAR-100 contain 50,000 training samples and 10,000 test samples. |
| Hardware Specification | Yes | Our implementation is based on Py Torch [Paszke et al., 2019] and experiments were carried out with NVIDIA Tesla V100 GPU. |
| Software Dependencies | No | Our implementation is based on Py Torch [Paszke et al., 2019] and experiments were carried out with NVIDIA Tesla V100 GPU. (Does not specify version numbers for PyTorch or other software dependencies). |
| Experiment Setup | Yes | We train the commonly used Le Net-5, Pre Act-Res Net18 and Wide-Res Net-34-10 with 200 epochs, and use SGD as the opimizer with a momentum of 0.9, a weight decay of 1e-4, and a batch size 64 in our experiments. We set the initial learning rate as 0.1 across all datasets and divide it by a factor of 10 after 100 epochs and 150 epochs respectively. The hyperparameters used in Eq.(13) are set as T = 100 and λ = 1. The number m of augmented instances used for consistency training is set to 2 |