Learn from Concepts: Towards the Purified Memory for Few-shot Learning
Authors: Xuncheng Liu, Xudong Tian, Shaohui Lin, Yanyun Qu, Lizhuang Ma, Wang Yuan, Zhizhong Zhang, Yuan Xie
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments performed on several benchmarks demonstrate the proposed method can consistently outperform a vast number of state-of-the-art few-shot learning methods. |
| Researcher Affiliation | Academia | 1School of Computer Science and Technology, East China Normal University, China 2School of Information Science and Engineering, Xiamen University, China {51194501055, 51194501066, 51184501076}@stu.ecnu.edu.cn, {shlin, lzma, zzzhang}@cs.ecnu.edu.cn, yyqu@xmu.edu.cn, xieyuan8589@foxmail.com |
| Pseudocode | No | No structured pseudocode or algorithm blocks were found in the paper. |
| Open Source Code | No | The paper does not provide any concrete access to source code (specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described. |
| Open Datasets | Yes | Datasets. We evaluate our approach on four few-shot learning benchmarks followed by [Yang et al., 2020]: mini Image Net [Vinyals et al., 2016], tiered Image Net [Ren et al., 2018], CUB-200-2011[Wah et al., 2011] and CIFAR-FS [Bertinetto et al., 2018]. |
| Dataset Splits | Yes | For evaluation, all the results are obtained under standard few-shot classification protocol: 5-way 1-shot and 5-shot task. No matter in 1 or 5-shot setting, only 1 query sample each class is used to test the accuracy. We report the mean accuracy (%) of 10K randomly generated episodes as well as the 95% intervals on test set. Notice that all the hyperparameters are determined from the validation sets. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions software components like 'Adam optimizer' but does not provide specific version numbers for any key software dependencies or libraries. |
| Experiment Setup | Yes | Training. In the pre-training stage, the baseline following prior work [Chen et al., 2020] is trained from scratch with a batch size of 128 by minimizing the standard crossentropy loss on base classes. After that, we randomly select 40 episodes per iteration for training the Conv Net in the meta-train stage. This sampling strategy is slightly different for Res Net12, where 5-way 5-shot task, we only sample 20 episodes per iteration due to the memory cost. The Adam optimizer is used in all experiments with the initial learning rate of 10 3. We decay the learning rate by 0.1 per 8000 iterations and set the weight dacay to 10 5. We train 50,000 epochs in total, and the encoder are frozen for the first 25000 iterations. |