Self-Supervised and Invariant Representations for Wireless Localization

Abstract

In this work, we present a wireless localization method that operates on self-supervised and unlabeled channel estimates. Our self-supervising method learns general-purpose channel features robust to fading and system impairments. Learned representations are easily transferable to new environments and ready to use for other wireless downstream tasks. To the best of our knowledge, the proposed method is the first joint-embedding self-supervised approach to forsake the dependency on contrastive channel estimates. Our approach outperforms fully-supervised techniques in small data regimes under fine-tuning and, in some cases, linear evaluation. We assess the performance in centralized and distributed massive MIMO systems for multiple datasets. Moreover, our method works indoors and outdoors without additional assumptions or design changes.

References in corpus (9)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Decoupled Weight Decay Regularization
• Massive MIMO for Next Generation Wireless Systems
• An Overview of Signal Processing Techniques for Millimeter Wave MIMO Systems
• VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
• CSI-fingerprinting Indoor Localization via Attention-Augmented Residual Convolutional Neural Network
• Efficient Self-supervised Vision Transformers for Representation Learning
• Attention Aided CSI Wireless Localization
• A CNN-LSTM Quantifier for Single Access Point CSI Indoor Localization