Doubly Perturbed Task Free Continual Learning
Authors: Byung Hyun Lee, Min-hwan Oh, Se Young Chun
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate that our proposed method outperforms the state-of-the-art baseline methods by large margins on various TF-CL benchmarks. In experiments, our method significantly outperforms the existing rehearsal-based methods on various CL setups and benchmarks. |
| Researcher Affiliation | Academia | Byung Hyun Lee1, Min-hwan Oh2, Se Young Chun1,3, 1Department of Electrical and Computer Engineering, Seoul National University 2Graduate School of Data Science, Seoul National University 3INMC & IPAI, Seoul National University |
| Pseudocode | No | The paper describes its methods and optimization in detail with mathematical formulations, but it does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement about releasing code or a link to an open-source repository for the described methodology. |
| Open Datasets | Yes | We evaluate on three CL benchmark datasets. CIFAR100 (Rebuffi et al. 2017) and CIFAR100-SC (Yoon et al. 2019) contains 50,000 samples and 10,000 samples for training and test. Image Net-100 (Douillard et al. 2020) is a subset of ILSVRC2012 with 100 randomly selected classes which consists of about 130K samples for training and 5000 samples for test. |
| Dataset Splits | Yes | CIFAR100 (Rebuffi et al. 2017) and CIFAR100-SC (Yoon et al. 2019) contains 50,000 samples and 10,000 samples for training and test. For both CIFAR100 and CIFAR100-SC, we split 100 classes into 5 tasks by randomly selecting 20 classes for each task (Rebuffi et al. 2017)... For Imagenet-100, we split 100 classes into 10 tasks by randomly selecting 10 classes for each task (Douillard et al. 2020). |
| Hardware Specification | No | The paper does not specify any particular hardware (e.g., GPU models, CPU types, or memory amounts) used for running the experiments. It mentions "training GPU memory" in Table 3 as a metric, but not the specific hardware. |
| Software Dependencies | No | The paper mentions using specific tools/libraries like "Res Net34", "Adam optimizer", "Auto Augment", and "Cut Mix", but it does not provide specific version numbers for these or for any underlying programming languages or frameworks (e.g., Python, PyTorch version). |
| Experiment Setup | Yes | We used a batch size of 16 and 3 updates per sample for CIFAR100 and CIFAR100-SC and batch size of 64 and 0.25 updates per sample for Image Net-100. We used a memory size of 2000 for all datasets. We utilized the Adam optimizer (Kingma and Ba 2015) with an initial learning rate of 0.0003 and applied an exponential learning rate scheduler except CLIB and the optimization configurations reported in the original papers were used for CLIB. |