Abstract | ||
---|---|---|
Unlike most computer vision approaches, which depend on hundreds or thousands of training images, humans can typically learn from a single visual example. Humans achieve this ability using background knowledge. Rule-based machine learning approaches such as Inductive Logic Programming (ILP) provide a framework for incorporating domain specific background knowledge. These approaches have the potential for human-like learning from small data or even one-shot learning, i.e. learning from a single positive example. By contrast, statistics based computer vision algorithms, including Deep Learning, have no general mechanisms for incorporating background knowledge. This paper presents an approach for one-shot rule learning called One-Shot Hypothesis Derivation (OSHD) based on using a logic program declarative bias. We apply this approach to two challenging human-like computer vision tasks: 1) Malayalam character recognition and 2) neurological diagnosis using retinal images. We compare our results with a state-of-the-art Deep Learning approach, called Siamese Network, developed for one-shot learning. The results suggest that our approach can generate human-understandable rules and outperforms the deep learning approach with a significantly higher average predictive accuracy. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-030-97454-1_17 | INDUCTIVE LOGIC PROGRAMMING (ILP 2021) |
DocType | Volume | ISSN |
Conference | 13191 | 0302-9743 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dany Varghese | 1 | 0 | 0.34 |
Roman Bauer | 2 | 15 | 3.53 |
Daniel Baxter-Beard | 3 | 0 | 0.34 |
Stephen Muggleton | 4 | 3915 | 619.54 |
Alireza Tamaddoni-Nezhad | 5 | 0 | 0.34 |