SAM-IF: Leveraging SAM for Incremental Few-Shot Instance Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910745805979648 |
|---|---|
| author | Zhou, Xudong He, Wenhao |
| author_facet | Zhou, Xudong He, Wenhao |
| contents | We propose SAM-IF, a novel method for incremental few-shot instance segmentation leveraging the Segment Anything Model (SAM). SAM-IF addresses the challenges of class-agnostic instance segmentation by introducing a multi-class classifier and fine-tuning SAM to focus on specific target objects. To enhance few-shot learning capabilities, SAM-IF employs a cosine-similarity-based classifier, enabling efficient adaptation to novel classes with minimal data. Additionally, SAM-IF supports incremental learning by updating classifier weights without retraining the decoder. Our method achieves competitive but more reasonable results compared to existing approaches, particularly in scenarios requiring specific object segmentation with limited labeled data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11034 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SAM-IF: Leveraging SAM for Incremental Few-Shot Instance Segmentation Zhou, Xudong He, Wenhao Computer Vision and Pattern Recognition We propose SAM-IF, a novel method for incremental few-shot instance segmentation leveraging the Segment Anything Model (SAM). SAM-IF addresses the challenges of class-agnostic instance segmentation by introducing a multi-class classifier and fine-tuning SAM to focus on specific target objects. To enhance few-shot learning capabilities, SAM-IF employs a cosine-similarity-based classifier, enabling efficient adaptation to novel classes with minimal data. Additionally, SAM-IF supports incremental learning by updating classifier weights without retraining the decoder. Our method achieves competitive but more reasonable results compared to existing approaches, particularly in scenarios requiring specific object segmentation with limited labeled data. |
| title | SAM-IF: Leveraging SAM for Incremental Few-Shot Instance Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.11034 |