Existing meta-learners primarily focus on improving the average task accuracy across multiple episodes. Different episodes, however, may vary in hardness and quality leading to a wide gap in the meta-learner's performance across episodes. Understanding this issue is particularly critical in industrial few-shot settings, where there is limited control over test episodes as they are typically uploaded by end-users. In this paper, we empirically analyse the behaviour of meta-learners on episodes of varying hardness across three standard benchmark datasets: CIFAR-FS, mini-ImageNet, and tiered-ImageNet. Surprisingly, we observe a wide gap in accuracy of around 50% between the hardest and easiest episodes across all the standard benchmarks and meta-learners. We additionally investigate various properties of hard episodes and highlight their connection to catastrophic forgetting during meta-training. To address the issue of sub-par performance on hard episodes, we investigate and benchmark different meta-training strategies based on adversarial training and curriculum learning. We find that adversarial training strategies are much more powerful than curriculum learning in improving the prediction performance on hard episodes.
翻译:现有的中继器主要侧重于提高不同时段的平均任务精确度。 但是,不同时段在难度和质量上可能各异,导致超脱器不同时段的性能出现巨大差距。 理解这一问题在工业几发环境中尤为关键,因为在工业几发环境中,对测试过程的控制有限,因为测试过程通常由最终用户上传。 在本文件中,我们根据三个标准基准数据集(CIFAR-FS、微型ImageNet和分级的ImageNet)的难度变化,对中继器的行为进行了经验分析。 令人惊讶的是,我们发现在所有标准基准和超载器中,最难和最容易发生的情况之间有大约50%的准确性差距。 我们进一步调查困难事件的各种特性,强调它们在元培训中与灾难性的遗忘之间的联系。 为了解决硬事件分级性表现问题,我们根据对立式培训和课程学习,调查并衡量不同的元培训战略。 我们发现,在改进硬片预测性表现方面,对立式培训战略比课程学习能力大得多。