Diversity Matters When Learning From Ensembles
원문 초록
Deep ensembles excel in large-scale image classification tasks both in terms of prediction accuracy and calibration. Despite being simple to train, the computation and memory cost of deep ensembles limits their practicability. While some recent works propose to distill an ensemble model into a single model to reduce such costs, there is still a performance gap between the ensemble and distilled models. We propose a simple approach for reducing this gap, i.e., making the distilled performance close to the full ensemble. Our key assumption is that a distilled model should absorb as much function diversity inside the ensemble as possible. We first empirically show that the typical distillation procedure does not effectively transfer such diversity, especially for complex models that achieve near-zero training error. To fix this, we propose a perturbation strategy for distillation that reveals diversity by seeking inputs for which ensemble member outputs disagree. We empirically show that a model distilled with such perturbed samples indeed exhibits enhanced diversity, leading to improved performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Cross-Part Learning for Fine-Grained Image Classification
A Supervised Segmentation Network for Hyperspectral Image Classification
Evaluating the Performance of TAAF for image classification models
FewVS: A Vision-Semantics Integration Framework for Few-Shot Image Classification
Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification
Evolving Efficient CNN Based Model for Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.