Can multi-label classification networks know what they don't know?
arXiv:2109.14162
Abstract
Estimating out-of-distribution (OOD) uncertainty is a central challenge for safely deploying machine learning models in the open-world environment. Improved methods for OOD detection in multi-class classification have emerged, while OOD detection methods for multi-label classification remain underexplored and use rudimentary techniques. We propose JointEnergy, a simple and effective method, which estimates the OOD indicator scores by aggregating energy scores from multiple labels. We show that JointEnergy can be mathematically interpreted from a joint likelihood perspective. Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels. We demonstrate the effectiveness of our method on three common multi-label classification benchmarks, including MS-COCO, PASCAL-VOC, and NUS-WIDE. We show that JointEnergy can reduce the FPR95 by up to 10.05% compared to the previous best baseline, establishing state-of-the-art performance.
arXiv commentPaper published at NeurIPS 2021
References in corpus (11)
- Auto-Encoding Variational Bayes
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Conditional Image Generation with PixelCNN Decoders
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
- Density estimation using Real NVP
- Generalized Out-of-Distribution Detection: A Survey
- Deep Convolutional Ranking for Multilabel Image Annotation
- A Theory of Generative ConvNet
- Input complexity and out-of-distribution detection with likelihood-based generative models
- ReAct: Out-of-distribution Detection With Rectified Activations