MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels

Authors: Chuanyang Hu, Shipeng Yan, Zhitong Gao, Xuming He

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To validate our method, we perform extensive experiments on synthetic noisy datasets and real-world web data, and our strategy outperforms existing noisy-label learning methods.
Researcher Affiliation Academia Chuanyang Hu1 , Shipeng Yan1 , Zhitong Gao1 and Xuming He1,2 1Shanghai Tech University 2Shanghai Engineering Research Center of Intelligent Vision and Imaging {huchy3, yanshp, gaozht, hexm}@shanghaitech.edu.cn
Pseudocode Yes Algorithm 1 Pseudocode of Sample Selection
Open Source Code No The paper does not provide any explicit statements about releasing source code for their method, nor does it include a link to a code repository.
Open Datasets Yes For synthetic noise, we follow the protocol proposed in [Kim et al., 2021] to generate symmetric and asymmetric noise on CIFAR-10 [Krizhevsky et al., 2009] and CIFAR-100 [Krizhevsky et al., 2009] datasets. For real scenarios with web noises, We adopt Mini-Imagenet, Mini-Webvision and CIFAR-N datasets for evaluation. Besides, Mini-Image Net [Jiang et al., 2020] collects noisy images from Internet. Specifically, it annotates the correctness of the collected image labels manually. The dataset includes around 50,000 training images and 5,000 val images for 100 classes. Mini-Webvision [Li et al., 2017] is derived from Webvision dataset [Li et al., 2017] by picking top 50 categories of google images.
Dataset Splits Yes The dataset includes around 50,000 training images and 5,000 val images for 100 classes. Following FINE [Kim et al., 2021], we tune the hyper-parameters by an additional validation set for CIFAR-10 and CIFAR-100. Also following Divide Mix [Li et al., 2020], the validation set is provided to tune the hyper-parameters for web noise datasets like Mini Webvision and Mini-Image Net.
Hardware Specification No The paper does not specify the hardware used for running the experiments, such as particular GPU or CPU models, memory, or cloud computing instances.
Software Dependencies No The paper states, "Our implementation is based on Py Torch." However, it does not provide specific version numbers for PyTorch or any other software libraries or dependencies.
Experiment Setup Yes We adopt the SGD optimizer with an initial learning rate of 0.01, a momentum of 0.9. For Mini Webvision and Mini-Image Net, ... We use the SGD optimizer with an initial learning rate of 0.1, a momentum of 0.9. For all datasets, we use the cosine-annealing learning rate scheduler for each round and the batch size is set to 128. The training epochs of each round is 20, 50, 100, 100 for CIFAR-10, CIFAR-100, Mini-Imagenet and Mini-Webvision, respectively.