Clustering-based Image-Text Graph Matching for Domain Generalization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910760215511040 |
|---|---|
| author | Park, Nokyung Chae, Daewon Shim, Jeongyong Kim, Sangpil Kim, Eun-Sol Kim, Jinkyu |
| author_facet | Park, Nokyung Chae, Daewon Shim, Jeongyong Kim, Sangpil Kim, Eun-Sol Kim, Jinkyu |
| contents | Learning domain-invariant visual representations is important to train a model that can generalize well to unseen target task domains. Recent works demonstrate that text descriptions contain high-level class-discriminative information and such auxiliary semantic cues can be used as effective pivot embedding for domain generalization problems. However, they use pivot embedding in a global manner (i.e., aligning an image embedding with sentence-level text embedding), which does not fully utilize the semantic cues of given text description. In this work, we advocate for the use of local alignment between image regions and corresponding textual descriptions to get domain-invariant features. To this end, we first represent image and text inputs as graphs. We then cluster nodes within these graphs and match the graph-based image node features to the nodes of textual graphs. This matching process is conducted both globally and locally, tightly aligning visual and textual semantic sub-structures. We experiment with large-scale public datasets, such as CUB-DG and DomainBed, and our model achieves matched or better state-of-the-art performance on these datasets. The code is available at: https://github.com/noparkee/Graph-Clustering-based-DG |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_02692 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Clustering-based Image-Text Graph Matching for Domain Generalization Park, Nokyung Chae, Daewon Shim, Jeongyong Kim, Sangpil Kim, Eun-Sol Kim, Jinkyu Computer Vision and Pattern Recognition Artificial Intelligence Learning domain-invariant visual representations is important to train a model that can generalize well to unseen target task domains. Recent works demonstrate that text descriptions contain high-level class-discriminative information and such auxiliary semantic cues can be used as effective pivot embedding for domain generalization problems. However, they use pivot embedding in a global manner (i.e., aligning an image embedding with sentence-level text embedding), which does not fully utilize the semantic cues of given text description. In this work, we advocate for the use of local alignment between image regions and corresponding textual descriptions to get domain-invariant features. To this end, we first represent image and text inputs as graphs. We then cluster nodes within these graphs and match the graph-based image node features to the nodes of textual graphs. This matching process is conducted both globally and locally, tightly aligning visual and textual semantic sub-structures. We experiment with large-scale public datasets, such as CUB-DG and DomainBed, and our model achieves matched or better state-of-the-art performance on these datasets. The code is available at: https://github.com/noparkee/Graph-Clustering-based-DG |
| title | Clustering-based Image-Text Graph Matching for Domain Generalization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2310.02692 |