Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning
Model-agnostic meta-learning (MAML) is a popular method for few-shot learning but assumes that we have access to the meta-training set. In practice, training on the meta-training set may not always be an option due to data privacy concerns, intellectual property issues, or merely lack of computing resources. In this paper, we consider the novel problem of repurposing pretrained MAML checkpoints to solve new few-shot classification tasks. Because of the potential distribution mismatch, the original MAML steps may no longer be optimal. Therefore we propose an alternative meta-testing procedure and combine MAML gradient steps with adversarial training and uncertainty-based stepsize adaptation. Our method outperforms "vanilla" MAML on same-domain and cross-domains benchmarks using both SGD and Adam optimizers and shows improved robustness to the choice of base stepsize.
Code (1)
Tasks
Few-Shot LearningMeta-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
Vision-Language Models (VLMs) excel at tasks like zero-shot classification and cross-modal retrieval by mapping images and text to a shared space, but this requires expensive end-to-end training with massive paired datas…
Cross-Modal RetrievalData AugmentationDomain Expansion of Image Generators
Can one inject new concepts into an already trained generative model, while respecting its existing structure and knowledge? We propose a new task - domain expansion - to address this. Given a pretrained generator and no…
Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics
We show that off-the-shelf text-based Transformers, with no additional training, can perform few-shot in-context visual imitation learning, mapping visual observations to action sequences that emulate the demonstrator's …
Imitation LearningDistilling Internet-Scale Vision-Language Models into Embodied Agents
Instruction-following agents must ground language into their observation and action spaces. Learning to ground language is challenging, typically requiring domain-specific engineering or large quantities of human interac…
Instruction FollowingFew-shot link prediction via graph neural networks for Covid-19 drug-repurposing
Predicting interactions among heterogenous graph structured data has numerous applications such as knowledge graph completion, recommendation systems and drug discovery. Often times, the links to be predicted belong to r…
Drug DiscoveryFew-Shot LearningGraph LearningKnowledge Graph Completion+3