Towards Reliable AI Model Deployments: Multiple Input Mixup for Out-of-Distribution Detection (2312.15514v1)
Abstract: Recent remarkable success in the deep-learning industries has unprecedentedly increased the need for reliable model deployment. For example, the model should alert the user if the produced model outputs might not be reliable. Previous studies have proposed various methods to solve the Out-of-Distribution (OOD) detection problem, however, they generally require a burden of resources. In this work, we propose a novel and simple method, Multiple Input Mixup (MIM). Our method can help improve the OOD detection performance with only single epoch fine-tuning. Our method does not require training the model from scratch and can be attached to the classifier simply. Despite its simplicity, our MIM shows competitive performance. Our method can be suitable for various environments because our method only utilizes the In-Distribution (ID) samples to generate the synthesized OOD data. With extensive experiments with CIFAR10 and CIFAR100 benchmarks that have been largely adopted in out-of-distribution detection fields, we have demonstrated our MIM shows comprehensively superior performance compared to the SOTA method. Especially, our method does not need additional computation on the feature vectors compared to the previous studies. All source codes are publicly available at https://github.com/ndb796/MultipleInputMixup.
- Bottou, L. 2012. Stochastic gradient descent tricks. In Neural Networks: Tricks of the Trade: Second Edition, 421–436. Springer.
- Entropy maximization and meta classification for out-of-distribution detection in semantic segmentation. In Proceedings of the ieee/cvf international conference on computer vision, 5128–5137.
- Describing textures in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3606–3613.
- The relationship between Precision-Recall and ROC curves. In Proceedings of the 23rd international conference on Machine learning, 233–240.
- The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 143(1): 29–36.
- Scaling out-of-distribution detection for real-world settings. arXiv preprint arXiv:1911.11132.
- A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136.
- Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606.
- Key feature replacement of in-distribution samples for out-of-distribution detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, 8246–8254.
- PyTorch-OOD: A Library for Out-of-Distribution Detection Based on PyTorch. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 4351–4360.
- Learning multiple layers of features from tiny images.
- Training confidence-calibrated classifiers for detecting out-of-distribution samples. arXiv preprint arXiv:1711.09325.
- A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Advances in neural information processing systems, 31.
- Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690.
- Energy-based out-of-distribution detection. Advances in neural information processing systems, 33: 21464–21475.
- Semantic-aware scene recognition. Pattern Recognition, 102: 107256.
- Reading digits in natural images with unsupervised feature learning.
- A simple fix to mahalanobis distance for improving near-ood detection. arXiv preprint arXiv:2106.09022.
- Imagenet large scale visual recognition challenge. International journal of computer vision, 115: 211–252.
- React: Out-of-distribution detection with rectified activations. Advances in Neural Information Processing Systems, 34: 144–157.
- DICE: Leveraging Sparsification for Out-of-Distribution Detection. In European Conference on Computer Vision.
- Manifold mixup: Better representations by interpolating hidden states. In International conference on machine learning, 6438–6447. PMLR.
- Vim: Out-of-distribution with virtual-logit matching. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 4921–4930.
- How transferable are features in deep neural networks? Advances in neural information processing systems, 27.
- Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365.
- Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE/CVF international conference on computer vision, 6023–6032.
- Wide residual networks. arXiv preprint arXiv:1605.07146.
- mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.