Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2405.00631 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913338296893440 |
|---|---|
| author | Wahd, Assefa Seyoum |
| author_facet | Wahd, Assefa Seyoum |
| contents | In this paper, we present a novel approach that combines deep metric learning and synthetic data generation using diffusion models for out-of-distribution (OOD) detection. One popular approach for OOD detection is outlier exposure, where models are trained using a mixture of in-distribution (ID) samples and ``seen" OOD samples. For the OOD samples, the model is trained to minimize the KL divergence between the output probability and the uniform distribution while correctly classifying the in-distribution (ID) data. In this paper, we propose a label-mixup approach to generate synthetic OOD data using Denoising Diffusion Probabilistic Models (DDPMs). Additionally, we explore recent advancements in metric learning to train our models.
In the experiments, we found that metric learning-based loss functions perform better than the softmax. Furthermore, the baseline models (including softmax, and metric learning) show a significant improvement when trained with the generated OOD data. Our approach outperforms strong baselines in conventional OOD detection metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_00631 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Metric Learning-Based Out-of-Distribution Detection with Synthetic Outlier Exposure Wahd, Assefa Seyoum Computer Vision and Pattern Recognition In this paper, we present a novel approach that combines deep metric learning and synthetic data generation using diffusion models for out-of-distribution (OOD) detection. One popular approach for OOD detection is outlier exposure, where models are trained using a mixture of in-distribution (ID) samples and ``seen" OOD samples. For the OOD samples, the model is trained to minimize the KL divergence between the output probability and the uniform distribution while correctly classifying the in-distribution (ID) data. In this paper, we propose a label-mixup approach to generate synthetic OOD data using Denoising Diffusion Probabilistic Models (DDPMs). Additionally, we explore recent advancements in metric learning to train our models. In the experiments, we found that metric learning-based loss functions perform better than the softmax. Furthermore, the baseline models (including softmax, and metric learning) show a significant improvement when trained with the generated OOD data. Our approach outperforms strong baselines in conventional OOD detection metrics. |
| title | Deep Metric Learning-Based Out-of-Distribution Detection with Synthetic Outlier Exposure |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.00631 |