English

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

Machine Learning 2024-05-28 v2 Computer Vision and Pattern Recognition

Abstract

Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce uncalibrated closed-set predictions for OOD data. A more robust classifiers with the uncertainty estimation typically require a potentially unavailable OOD dataset for outlier exposure training, or a considerable amount of additional memory and compute to build ensemble models. In this work, we improve on uncertainty estimation without extra OOD data or additional inference costs using an alternative Split-Ensemble method. Specifically, we propose a novel subtask-splitting ensemble training objective, where a common multiclass classification task is split into several complementary subtasks. Then, each subtask's training data can be considered as OOD to the other subtasks. Diverse submodels can therefore be trained on each subtask with OOD-aware objectives. The subtask-splitting objective enables us to share low-level features across submodels to avoid parameter and computational overheads. In particular, we build a tree-like Split-Ensemble architecture by performing iterative splitting and pruning from a shared backbone model, where each branch serves as a submodel corresponding to a subtask. This leads to improved accuracy and uncertainty estimation across submodels under a fixed ensemble computation budget. Empirical study with ResNet-18 backbone shows Split-Ensemble, without additional computation cost, improves accuracy over a single model by 0.8%, 1.8%, and 25.5% on CIFAR-10, CIFAR-100, and Tiny-ImageNet, respectively. OOD detection for the same backbone and in-distribution datasets surpasses a single model baseline by, correspondingly, 2.2%, 8.1%, and 29.6% mean AUROC.

Keywords

Cite

@article{arxiv.2312.09148,
  title  = {Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting},
  author = {Anthony Chen and Huanrui Yang and Yulu Gan and Denis A Gudovskiy and Zhen Dong and Haofan Wang and Tomoyuki Okuno and Yohei Nakata and Kurt Keutzer and Shanghang Zhang},
  journal= {arXiv preprint arXiv:2312.09148},
  year   = {2024}
}

Comments

ICML2024. Project website is available at https://antonioo-c.github.io/projects/split-ensemble

R2 v1 2026-06-28T13:51:19.332Z