Unlocking Transfer Learning for Open-World Few-Shot Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918151083524096 |
|---|---|
| author | Kim, Byeonggeun Lee, Juntae Shim, Kyuhong Chang, Simyung |
| author_facet | Kim, Byeonggeun Lee, Juntae Shim, Kyuhong Chang, Simyung |
| contents | Few-Shot Open-Set Recognition (FSOSR) targets a critical real-world challenge, aiming to categorize inputs into known categories, termed closed-set classes, while identifying open-set inputs that fall outside these classes. Although transfer learning where a model is tuned to a given few-shot task has become a prominent paradigm in closed-world, we observe that it fails to expand to open-world. To unlock this challenge, we propose a two-stage method which consists of open-set aware meta-learning with open-set free transfer learning. In the open-set aware meta-learning stage, a model is trained to establish a metric space that serves as a beneficial starting point for the subsequent stage. During the open-set free transfer learning stage, the model is further adapted to a specific target task through transfer learning. Additionally, we introduce a strategy to simulate open-set examples by modifying the training dataset or generating pseudo open-set examples. The proposed method achieves state-of-the-art performance on two widely recognized benchmarks, miniImageNet and tieredImageNet, with only a 1.5\% increase in training effort. Our work demonstrates the effectiveness of transfer learning in FSOSR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_09986 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unlocking Transfer Learning for Open-World Few-Shot Recognition Kim, Byeonggeun Lee, Juntae Shim, Kyuhong Chang, Simyung Computer Vision and Pattern Recognition Artificial Intelligence Few-Shot Open-Set Recognition (FSOSR) targets a critical real-world challenge, aiming to categorize inputs into known categories, termed closed-set classes, while identifying open-set inputs that fall outside these classes. Although transfer learning where a model is tuned to a given few-shot task has become a prominent paradigm in closed-world, we observe that it fails to expand to open-world. To unlock this challenge, we propose a two-stage method which consists of open-set aware meta-learning with open-set free transfer learning. In the open-set aware meta-learning stage, a model is trained to establish a metric space that serves as a beneficial starting point for the subsequent stage. During the open-set free transfer learning stage, the model is further adapted to a specific target task through transfer learning. Additionally, we introduce a strategy to simulate open-set examples by modifying the training dataset or generating pseudo open-set examples. The proposed method achieves state-of-the-art performance on two widely recognized benchmarks, miniImageNet and tieredImageNet, with only a 1.5\% increase in training effort. Our work demonstrates the effectiveness of transfer learning in FSOSR. |
| title | Unlocking Transfer Learning for Open-World Few-Shot Recognition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2411.09986 |