# Subject Invariant Contrastive Learning for Human Activity Recognition

arXiv: https://arxiv.org/abs/2507.03250 · HTML: https://mlsanity.com/paper/2507.03250/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Builds on (most cited first, 18 of 18)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation](https://mlsanity.com/paper/1804.06055/) (2018)
- [DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2308.02282/) (2023)
- [COCOA: Cross Modality Contrastive Learning for Sensor Data](https://mlsanity.com/paper/2208.00467/) (2022)
- [Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition](https://mlsanity.com/paper/2205.10071/) (2022)
- [FOCAL: A Cost-Aware Video Dataset for Active Learning](https://mlsanity.com/paper/2311.10591/) (2023)
- [HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms](https://mlsanity.com/paper/2410.23200/) (2024)
- [Hierarchical and Multimodal Data for Daily Activity Understanding](https://mlsanity.com/paper/2504.17696/) (2025)
- [Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning](https://mlsanity.com/paper/2412.13594/) (2024)
- [Personalizing human activity recognition models using incremental learning](https://mlsanity.com/paper/1905.12628/) (2019)
- [Multimodal Contrastive Learning with Hard Negative Sampling for Human Activity Recognition](https://mlsanity.com/paper/2309.01262/) (2023)
- [Taxes Are All You Need: Integration of Taxonomical Hierarchy Relationships into the Contrastive Loss](https://mlsanity.com/paper/2406.06848/) (2024)

## Built on by (most cited first, 3 of 3)

- [Countering Multi-modal Representation Collapse through Rank-targeted Fusion](https://mlsanity.com/paper/2511.06450/) (2025)
- [MER-DG: Modality-Entropy Regularization for Multimodal Domain Generalization](https://mlsanity.com/paper/2605.01967/) (2026)
- [SynCo: Learning Cross-Modal Synergy by Contrasting Interaction Residuals](https://mlsanity.com/paper/2609.32846/) (2026)

## Abstract (arXiv)

The high cost of annotating data makes self-supervised approaches, such as contrastive learning methods, appealing for Human Activity Recognition (HAR). Effective contrastive learning relies on selecting informative positive and negative samples. However, HAR sensor signals are subject to significant domain shifts caused by subject variability. These domain shifts hinder model generalization to unseen subjects by embedding subject-specific variations rather than activity-specific features. As a result, human activity recognition models trained with contrastive learning often struggle to generalize to new subjects. We introduce Subject-Invariant Contrastive Learning (SICL), a simple yet effective loss function to improve generalization in human activity recognition. SICL re-weights negative pairs drawn from the same subject to suppress subject-specific cues and emphasize activity-specific information. We evaluate our loss function on three public benchmarks: UTD-MHAD, MMAct, and DARai. We show that SICL improves performance by up to 11% over traditional contrastive learning methods. Additionally, we demonstrate the adaptability of our loss function across various settings, including multiple self-supervised methods, multimodal scenarios, and supervised learning frameworks.