Summary of Coda: a Cost-efficient Test-time Domain Adaptation Mechanism For Har, by Minghui Qiu (dsa et al.
CODA: A COst-efficient Test-time Domain Adaptation Mechanism for HAR
by Minghui Qiu, Yandao Huang, Lin Chen, Lu Wang, Kaishun Wu
First submitted to arxiv on: 22 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Networking and Internet Architecture (cs.NI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed CODA (COst-efficient Domain Adaptation) mechanism is a novel approach to mobile sensing that addresses real-time drifts in human-centric sensing scenarios. By incorporating a clustering loss and importance-weighted active learning algorithm, CODA retains the relationship between different clusters during cost-effective instance-level updates, preserving meaningful structure within the data distribution. The method ensures robustness against uncertain drifting conditions and is shown to be effective for Human Activity Recognition tasks, even without learnable parameters. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary CODA is a new way to make mobile sensing better by adapting to changes in real-world conditions. It’s like a special filter that helps keep data accurate and useful. CODA works by grouping similar things together and then updating its understanding of those groups based on new information. This makes it good at recognizing human activities, even when there are surprises or unexpected changes. |
Keywords
* Artificial intelligence * Active learning * Activity recognition * Clustering * Domain adaptation
