Optimized Gradient Clipping for Noisy Label Learning
Authors: Xichen Ye, Yifan Wu, Weizhong Zhang, Xiaoqiang Li, Yifan Chen, Cheng Jin
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our extensive experiments across various types of label noise, including symmetric, asymmetric, instance-dependent, and real-world noise, demonstrate the effectiveness of our approach. |
| Researcher Affiliation | Academia | 1Shanghai University 2Fudan University 3Hong Kong Baptist University 4Shanghai Key Laboratory of Intelligent Information Processing 5Shanghai Collaborative Innovation Center of Intelligent Visual Computing EMAIL, EMAIL, EMAIL |
| Pseudocode | Yes | Our algorithm is outlined in Appendix. |
| Open Source Code | Yes | Code https://github.com/Virusdoll/OGC |
| Open Datasets | Yes | we evaluate our proposed method using two well-known datasets: CIFAR-10 and CIFAR-100 (Krizhevsky, Hinton et al. 2009). ... we conduct experiments on Web Vision 1.0 dataset. Web Vision 1.0 (Li et al. 2017) contains more than 2.4 million web images crawled from the internet by using queries generated from the 1,000 class labels of the ILSVRC 2012 (Deng et al. 2009) benchmark. |
| Dataset Splits | No | The paper uses standard benchmark datasets like CIFAR-10, CIFAR-100, and Web Vision 1.0, which typically have predefined splits. However, the main text does not explicitly provide the specific percentages, sample counts, or methodology for the training, validation, and test splits used in their experiments. It states that "Noise generation, training, and parameter settings are in Appendix." but this does not explicitly provide the dataset split information in the main body. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware used to run its experiments, such as GPU models, CPU models, or cloud resources with specifications. It only mentions general experimental settings. |
| Software Dependencies | No | The paper does not explicitly list specific software dependencies with their version numbers (e.g., Python, PyTorch, TensorFlow, CUDA versions) that would be needed to reproduce the experiment. |
| Experiment Setup | Yes | For our GCE+OGC, GCE equipped with OGC, we set the parameters (q, ϵ0) to (0.7, 20.0). Experimental details. Noise generation, training, and parameter settings are in Appendix. |