Out-of-Distribution Detection using Multiple Semantic Label Representations

Abstract

Deep Neural Networks are powerful models that attained remarkable results on a variety of tasks. These models are shown to be extremely efficient when training and test data are drawn from the same distribution. However, it is not clear how a network will act when it is fed with an out-of-distribution example. In this work, we consider the problem of out-of-distribution detection in neural networks. We propose to use multiple semantic dense representations instead of sparse representation as the target label. Specifically, we propose to use several word representations obtained from different corpora or architectures as target labels. We evaluated the proposed model on computer vision, and speech commands detection tasks and compared it to previous methods. Results suggest that our method compares favorably with previous work. Besides, we present the efficiency of our approach for detecting wrongly classified and adversarial examples.

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Neural Machine Translation by Jointly Learning to Align and Translate
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Understanding deep learning requires rethinking generalization
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• Verb Semantics and Lexical Selection
• A note on the evaluation of generative models
• Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks

Cited by in corpus (12)

• Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
• Contrastive Training for Improved Out-of-Distribution Detection
• Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output
• Operational Calibration: Debugging Confidence Errors for DNNs in the Field
• A Less Biased Evaluation of Out-of-distribution Sample Detectors
• On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation
• Improved Adversarial Robustness by Reducing Open Space Risk via Tent Activations
• Novelty Detection Via Blurring
• Adaptive Confidence Smoothing for Generalized Zero-Shot Learning
• Redesigning the classification layer by randomizing the class representation vectors
• Robust Deep Learning Ensemble against Deception
• Leveraging Auxiliary Text for Deep Recognition of Unseen Visual Relationships