Summary of A Survey on Deep Active Learning: Recent Advances and New Frontiers, by Dongyuan Li and Zhen Wang and Yankai Chen and Renhe Jiang and Weiping Ding and Manabu Okumura
A Survey on Deep Active Learning: Recent Advances and New Frontiers
by Dongyuan Li, Zhen Wang, Yankai Chen, Renhe Jiang, Weiping Ding, Manabu Okumura
First submitted to arxiv on: 1 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 paper conducts an advanced and comprehensive survey on deep learning-based active learning (DAL), exploring its broad applicability in areas such as Natural Language Processing, Computer Vision, and Data Mining. The authors formally define the DAL task and summarize influential baselines, widely used datasets, and various methods from five perspectives: annotation types, query strategies, deep model architectures, learning paradigms, and training processes. They also analyze the strengths and weaknesses of each method and discuss main applications, challenges, and perspectives in this burgeoning field. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Active learning is a technique that asks an oracle to label new selected samples to achieve strong performance with fewer training samples. The proposed survey focuses on deep learning-based active learning (DAL), which has gained popularity due to its broad applicability. The authors introduce a reviewed paper collection and filtering, formally define the DAL task, and summarize influential baselines and widely used datasets. They also provide a taxonomy of DAL methods from five perspectives, analyze their strengths and weaknesses, and discuss main applications, challenges, and perspectives. |
Keywords
» Artificial intelligence » Active learning » Deep learning » Natural language processing
