Few-shot learning aims to transfer the knowledge acquired from training on a diverse set of tasks to unseen tasks from the same task distribution with a limited amount of labeled data. The underlying requirement for effective few-shot generalization is to learn a good representation of the task manifold. This becomes more difficult when only a limited number of tasks are available for training. In such a few-task few-shot setting, it is beneficial to explicitly preserve the local neighborhoods from the task manifold and exploit this to generate artificial tasks for training. To this end, we introduce the notion of interval bounds from the provably robust training literature to few-shot learning. The interval bounds are used to characterize neighborhoods around the training tasks. These neighborhoods can then be preserved by minimizing the distance between a task and its respective bounds. We then use a novel strategy to artificially form new tasks for training by interpolating between the available tasks and their respective interval bounds. We apply our framework to both model-agnostic meta-learning as well as prototype-based metric-learning paradigms. The efficacy of our proposed approach is evident from the improved performance on several datasets from diverse domains compared to current methods.

Few times in history has mankind ever united to solve a single goal. Even the ultimate moonshot in history--putting a man on the moon--was driven by international competition rather than unification. So it's perhaps fitting that mankind is now uniting to understand the organ that fundamentally makes us human: our brain. First envisioned in 2016 through a series of discussions on the "grand challenges" in neuroscience at Johns Hopkins University, the International Brain Initiative (IBI) "came out" this week in a forward-looking paper in Neuron. Rather than each country formulating their own brain projects independently, the project argues, it's high time for the world to come together and share their findings, resources, and expertise across borders.