Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding
Authors: Lan-Zhe Guo, Yu-Feng Li
ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we give comprehensive evaluations on various class-imbalanced SSL scenarios. We first describe the experimental setups in Section 5.1. Then, we present empirical results of our proposal and other compared methods under extensive setups in Section 5.2. Finally, we present detailed analyses to help understand the superiority of our proposal in Section 5.3. |
| Researcher Affiliation | Academia | 1National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China. Correspondence to: Yu-Feng Li <liyf@lamda.nju.edu.cn>. |
| Pseudocode | Yes | Algorithm 1 Adsh Algorithm. |
| Open Source Code | Yes | The code of this paper has been released on http://www.lamda.nju.edu.cn/code_ADSH.ashx. |
| Open Datasets | Yes | We conduct experiments on longtailed variants of CIFAR-10 (Krizhevsky & Hinton, 2009), SVHN (Netzer et al., 2011) and STL-10 (Coates et al., 2011) datasets with various levels of class imbalance and different ratios of labeled data. |
| Dataset Splits | No | The paper mentions labeled and unlabeled training data and a test set, but does not explicitly provide details for a separate validation dataset split distinct from the final test set for reproduction. It states: 'For all algorithms, we evaluate the model on the test dataset every 512 iterations and record the average test accuracy of the last 20 evaluations,' which uses the test set for intermediate evaluation rather than a dedicated validation split. |
| Hardware Specification | Yes | All experiments are conducted on Tesla V100 GPUs. |
| Software Dependencies | No | The paper mentions optimizers (Adam, SGD) and techniques (EMA) but does not provide specific version numbers for software dependencies like programming languages (e.g., Python), deep learning frameworks (e.g., PyTorch, TensorFlow), or specific libraries used. |
| Experiment Setup | Yes | In all experiments, we adopt the Wide Res Net-28-2 as the backbone. We train the model with batch size 64 for 218 training iterations. For training with semi-supervised learning algorithms, we adopt Adam optimizer with a learning rate of 2 × 10−3. For the hyper-parameters of Adam, we use β1 = 0.9, β2 = 0.999 and ϵ = 10−8 which is the default choice. The exponential moving average (EMA) technique is applied with a decay rate of 0.999. For training with re-balancing algorithms, we use SGD with a learning rate of 0.1, momentum 0.9, and weight decay 5 × 10−4. The learning rate of SGD decays by 0.01 at the time step 80% and 90% iterations. For Fix Match, we use µ = 2 to determine the ratio of unlabeled data and set λu = 1, τ = 0.95 as the original paper. For our Adsh we set τ1 = 0.95 as Fix Match and update s every 512 iterations. |