| Proj No. | A3212-251 |
| Title | Few-Shot Deep Learning for Medical Image Classification: Part 2 |
| Summary | Few-Shot Image Classification focuses on training models to classify images with very few examples per category. Traditional models need large datasets, which are often impractical to obtain. Few-shot learning aims to overcome this limitation by enabling models to generalize from a small number of examples. This project provides a foundation for understanding and implementing few-shot learning. There are papers with codes on Few-Shot Image Classification at https://paperswithcode.com/task/few-shot-image-classification . The student will download an existing code, reproduce the experimental results reported in the paper, and attempt to apply the method to medical images (download from the internet some medical image datasets). The student should compare with the results published by other researchers on the same dataset. This is part 2 of the project. The students in both parts will coordinate with the supervisor and each other so that each student will improve a different approach and then compare the results with each other. |
| Supervisor | A/P Wang Lipo (Loc:S1 > S1 B1C > S1 B1C 98, Ext: +65 67906372) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Computer Engineering I (Loc: S2-B4c-15) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |