Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2407.13363 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917767103381504 |
|---|---|
| author | Liu, Chang Rizzoli, Giulia Zanuttigh, Pietro Li, Fu Niu, Yi |
| author_facet | Liu, Chang Rizzoli, Giulia Zanuttigh, Pietro Li, Fu Niu, Yi |
| contents | Current weakly-supervised incremental learning for semantic segmentation (WILSS) approaches only consider replacing pixel-level annotations with image-level labels, while the training images are still from well-designed datasets. In this work, we argue that widely available web images can also be considered for the learning of new classes. To achieve this, firstly we introduce a strategy to select web images which are similar to previously seen examples in the latent space using a Fourier-based domain discriminator. Then, an effective caption-driven reharsal strategy is proposed to preserve previously learnt classes. To our knowledge, this is the first work to rely solely on web images for both the learning of new concepts and the preservation of the already learned ones in WILSS. Experimental results show that the proposed approach can reach state-of-the-art performances without using manually selected and annotated data in the incremental steps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_13363 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation Liu, Chang Rizzoli, Giulia Zanuttigh, Pietro Li, Fu Niu, Yi Computer Vision and Pattern Recognition Current weakly-supervised incremental learning for semantic segmentation (WILSS) approaches only consider replacing pixel-level annotations with image-level labels, while the training images are still from well-designed datasets. In this work, we argue that widely available web images can also be considered for the learning of new classes. To achieve this, firstly we introduce a strategy to select web images which are similar to previously seen examples in the latent space using a Fourier-based domain discriminator. Then, an effective caption-driven reharsal strategy is proposed to preserve previously learnt classes. To our knowledge, this is the first work to rely solely on web images for both the learning of new concepts and the preservation of the already learned ones in WILSS. Experimental results show that the proposed approach can reach state-of-the-art performances without using manually selected and annotated data in the incremental steps. |
| title | Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.13363 |