Modular Adaptation for Cross-Domain Few-Shot Learning

Abstract

Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples. While literature has demonstrated great successes via representation learning, in this work, we show that substantial performance improvement of downstream tasks can also be achieved by appropriate designs of the adaptation process. Specifically, we propose a modular adaptation method that selectively performs multiple state-of-the-art (SOTA) adaptation methods in sequence. As different downstream tasks may require different types of adaptation, our modular adaptation enables the dynamic configuration of the most suitable modules based on the downstream task. Moreover, as an extension to existing cross-domain 5-way k-shot benchmarks (e.g., miniImageNet -> CUB), we create a new high-way (~100) k-shot benchmark with data from 10 different datasets. This benchmark provides a diverse set of domains and allows the use of stronger representations learned from ImageNet. Experimental results show that by customizing adaptation process towards downstream tasks, our modular adaptation pipeline (MAP) improves 3.1% in 5-shot classification accuracy over baselines of finetuning and Prototypical Networks.

References in corpus (13)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Prototypical Networks for Few-shot Learning
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Fine-Grained Visual Classification of Aircraft
• Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• On First-Order Meta-Learning Algorithms
• Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
• Rethinking the Hyperparameters for Fine-tuning
• Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
• Self-Supervised Learning For Few-Shot Image Classification
• Cross-Domain Few-Shot Learning with Meta Fine-Tuning

Cited by in corpus (1)

• TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning