ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations
Authors: Xuyang Zhao, Tianqi Du, Yisen Wang, Jun Yao, Weiran Huang
ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiments on several datasets and show that Ar CL significantly improves the transferability of contrastive learning. |
| Researcher Affiliation | Collaboration | Xuyang Zhao1,2 Tianqi Du1,3 Yisen Wang3,4 Jun Yao5 Weiran Huang2 1 School of Mathematical Sciences, Peking University 2 Qing Yuan Research Institute, Shanghai Jiao Tong University 3 National Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University 4 Institute for Artificial Intelligence, Peking University 5 Huawei Noah s Ark Lab |
| Pseudocode | Yes | Algorithm 1: Sim CLR + Ar CL |
| Open Source Code | No | The paper does not contain an explicit statement about open-sourcing code or a link to a code repository. |
| Open Datasets | Yes | We use CIFAR10 to train the representation. In this part, we will first train an encoder on Image Net (Deng et al., 2009) using Mo Co v2 modified with our proposed Ar CL. |
| Dataset Splits | No | The paper mentions 'train' and 'linear evaluation' but does not explicitly provide percentages or specific counts for training, validation, and test splits within its own experimental setup, nor does it cite predefined splits for these purposes. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or cloud instance types) used for running the experiments. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | Our representations are trained on CIFAR-10 (Krizhevsky, 2009) using Sim CLR modified with our proposed Ar CL. Different batch sizes (256, 512) and number of views (m = 4, 6, 8) are considered. We use Res Net-18 as the encoder and a 2-layer MLP as the projection head. We train the representation with 500 epochs. The temperature is 0.5. Warm-up is not used. |