Scalable Ensemble Diversification for OOD Generalization and Detection
- URL: http://arxiv.org/abs/2409.16797v1
- Date: Wed, 25 Sep 2024 10:30:24 GMT
- Title: Scalable Ensemble Diversification for OOD Generalization and Detection
- Authors: Alexander Rubinstein, Luca Scimeca, Damien Teney, Seong Joon Oh,
- Abstract summary: SED identifies hard training samples on the fly and encourages the ensemble members to disagree on these.
We show how to avoid the expensive computations in existing methods of exhaustive pairwise disagreements across models.
For OOD generalization, we observe large benefits from the diversification in multiple settings including output-space (classical) ensembles and weight-space ensembles (model soups)
- Score: 68.8982448081223
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and enabling the detection of OOD samples via Bayesian principles. An existing approach to diverse ensemble training encourages the models to disagree on provided OOD samples. However, the approach is computationally expensive and it requires well-separated ID and OOD examples, such that it has only been demonstrated in small-scale settings. $\textbf{Method.}$ This work presents a method for Scalable Ensemble Diversification (SED) applicable to large-scale settings (e.g. ImageNet) that does not require OOD samples. Instead, SED identifies hard training samples on the fly and encourages the ensemble members to disagree on these. To improve scaling, we show how to avoid the expensive computations in existing methods of exhaustive pairwise disagreements across models. $\textbf{Results.}$ We evaluate the benefits of diversification with experiments on ImageNet. First, for OOD generalization, we observe large benefits from the diversification in multiple settings including output-space (classical) ensembles and weight-space ensembles (model soups). Second, for OOD detection, we turn the diversity of ensemble hypotheses into a novel uncertainty score estimator that surpasses a large number of OOD detection baselines. Code is available here: https://github.com/AlexanderRubinstein/diverse-universe-public.
Related papers
- DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection [10.834698906236405]
Out-of-distribution (OOD) detection is essential for ensuring the robustness of machine learning models.
Recent advances in multimodal models have demonstrated the potential of leveraging multiple modalities to enhance detection performance.
We propose Dynamic Prototype Updating (DPU), a novel plug-and-play framework for multimodal OOD detection.
arXiv Detail & Related papers (2024-11-12T22:43:16Z) - Diversified Outlier Exposure for Out-of-Distribution Detection via
Informative Extrapolation [110.34982764201689]
Out-of-distribution (OOD) detection is important for deploying reliable machine learning models on real-world applications.
Recent advances in outlier exposure have shown promising results on OOD detection via fine-tuning model with informatively sampled auxiliary outliers.
We propose a novel framework, namely, Diversified Outlier Exposure (DivOE), for effective OOD detection via informative extrapolation based on the given auxiliary outliers.
arXiv Detail & Related papers (2023-10-21T07:16:09Z) - General-Purpose Multi-Modal OOD Detection Framework [5.287829685181842]
Out-of-distribution (OOD) detection identifies test samples that differ from the training data, which is critical to ensuring the safety and reliability of machine learning (ML) systems.
We propose a general-purpose weakly-supervised OOD detection framework, called WOOD, that combines a binary classifier and a contrastive learning component.
We evaluate the proposed WOOD model on multiple real-world datasets, and the experimental results demonstrate that the WOOD model outperforms the state-of-the-art methods for multi-modal OOD detection.
arXiv Detail & Related papers (2023-07-24T18:50:49Z) - Calibrated Out-of-Distribution Detection with a Generic Representation [28.658200157111505]
Out-of-distribution detection is a common issue in deploying vision models in practice and solving it is an essential building block in safety critical applications.
We propose a novel OOD method, called GROOD, that formulates the OOD detection as a Neyman-Pearson task with well calibrated scores and which achieves excellent performance.
The method achieves state-of-the-art performance on a number of OOD benchmarks, reaching near perfect performance on several of them.
arXiv Detail & Related papers (2023-03-23T10:03:12Z) - Pseudo-OOD training for robust language models [78.15712542481859]
OOD detection is a key component of a reliable machine-learning model for any industry-scale application.
We propose POORE - POsthoc pseudo-Ood REgularization, that generates pseudo-OOD samples using in-distribution (IND) data.
We extensively evaluate our framework on three real-world dialogue systems, achieving new state-of-the-art in OOD detection.
arXiv Detail & Related papers (2022-10-17T14:32:02Z) - Understanding, Detecting, and Separating Out-of-Distribution Samples and
Adversarial Samples in Text Classification [80.81532239566992]
We compare the two types of anomalies (OOD and Adv samples) with the in-distribution (ID) ones from three aspects.
We find that OOD samples expose their aberration starting from the first layer, while the abnormalities of Adv samples do not emerge until the deeper layers of the model.
We propose a simple method to separate ID, OOD, and Adv samples using the hidden representations and output probabilities of the model.
arXiv Detail & Related papers (2022-04-09T12:11:59Z) - WOOD: Wasserstein-based Out-of-Distribution Detection [6.163329453024915]
Training data for deep-neural-network-based classifiers are usually assumed to be sampled from the same distribution.
When part of the test samples are drawn from a distribution that is far away from that of the training samples, the trained neural network has a tendency to make high confidence predictions for these OOD samples.
We propose a Wasserstein-based out-of-distribution detection (WOOD) method to overcome these challenges.
arXiv Detail & Related papers (2021-12-13T02:35:15Z) - Towards Consistent Predictive Confidence through Fitted Ensembles [6.371992222487036]
This paper introduces separable concept learning framework to measure the performance of classifiers in presence of OOD examples.
We present a new strong baseline for more consistent predictive confidence in deep models, called fitted ensembles.
arXiv Detail & Related papers (2021-06-22T21:32:31Z) - Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection [72.35532598131176]
We propose an unsupervised method to detect OOD samples using a $k$-NN density estimate.
We leverage a recent insight about label smoothing, which we call the emphLabel Smoothed Embedding Hypothesis
We show that our proposal outperforms many OOD baselines and also provide new finite-sample high-probability statistical results.
arXiv Detail & Related papers (2021-02-09T21:04:44Z) - Multi-Scale Positive Sample Refinement for Few-Shot Object Detection [61.60255654558682]
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances.
We propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD.
MPSR generates multi-scale positive samples as object pyramids and refines the prediction at various scales.
arXiv Detail & Related papers (2020-07-18T09:48:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.