Interventional Few-Shot Learning

Authors: Zhongqi Yue, Hanwang Zhang, Qianru Sun, Xian-Sheng Hua

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conducted experiments on benchmark datasets in FSL literature: 1) mini Image Net [62] containing 600 images per class over 100 classes. We followed the split proposed in [48]: 64/16/20 classes for train/val/test. ... Table 1: Acc (%) averaged over 2000 5-way FSL tasks before and after applying IFSL. ... Overall, our IFSL achieves the new state-of-the-art on both datasets.
Researcher Affiliation Collaboration Zhongqi Yue1,3, Hanwang Zhang1, Qianru Sun2, Xian-Sheng Hua3 1Nanyang Technological University, 2Singapore Management University, 3Alibaba Group
Pseudocode No The paper describes its algorithmic implementations but does not include structured pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes Code is released at https://github. com/yue-zhongqi/ifsl.
Open Datasets Yes We conducted experiments on benchmark datasets in FSL literature: 1) mini Image Net [62]... 2) tiered Image Net [49]... 3) Caltech-UCSD Birds-200-2011 (CUB) [65] for crossdomain evaluation.
Dataset Splits Yes We followed the split proposed in [48]: 64/16/20 classes for train/val/test.
Hardware Specification No The paper mentions 'donations of GPUs' in the acknowledgements, but does not provide specific details about the hardware used for experiments, such as GPU models, CPU types, or memory.
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used in the experiments.
Experiment Setup Yes Training and evaluation settings on mini Image Net and tiered Image Net are included in Appendix 5. (Appendix 5 states: 'In all experiments, we used Adam optimizer [31] with an initial learning rate of 1e-3, which decays by 0.5 every 25 epochs up to 75 epochs. The batch size is 16.')