Representation Consolidation from Multiple Expert Teachers
A library of diverse expert models transfers better to a novel task than a single generalist model. However, growing such a library indefinitely is impractical. Hence, we explore the problem of learning a consolidated image feature representation from a collection of related task-specific teachers that transfer well on novel recognition tasks. This differs from traditional knowledge distillation in which a student model is trained to emulate the input/output functionality of a teacher. Indeed, we observe experimentally that standard distillation of task-specific teachers, or using these teacher representations directly, **reduces** downstream transferability compared to a task-agnostic generalist model. We show that a simple multi-head, multi-task distillation method using an unlabeled proxy dataset and adding a generalist teacher is sufficient to consolidate representations from task-specific teacher(s). We improve downstream performance, outperforming the teacher (or best of all teachers) as well as the strong baseline of ImageNet pre-trained features. Our method almost reaches the performance of a multi-task joint training oracle, reaping the benefit of the teachers without replaying their training data.
PDF Abstract
CUB-200-2011
Oxford 102 Flower
Places
DTD
Food-101
iNaturalist
Caltech-256
RESISC45
