AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915135590760448 |
|---|---|
| author | Alawode, Basit Ganapathi, Iyyakutti Iyappan Javed, Sajid Werghi, Naoufel Bennamoun, Mohammed Mahmood, Arif |
| author_facet | Alawode, Basit Ganapathi, Iyyakutti Iyappan Javed, Sajid Werghi, Naoufel Bennamoun, Mohammed Mahmood, Arif |
| contents | The preservation of aquatic biodiversity is critical in mitigating the effects of climate change. Aquatic scene understanding plays a pivotal role in aiding marine scientists in their decision-making processes. In this paper, we introduce AquaticCLIP, a novel contrastive language-image pre-training model tailored for aquatic scene understanding. AquaticCLIP presents a new unsupervised learning framework that aligns images and texts in aquatic environments, enabling tasks such as segmentation, classification, detection, and object counting. By leveraging our large-scale underwater image-text paired dataset without the need for ground-truth annotations, our model enriches existing vision-language models in the aquatic domain. For this purpose, we construct a 2 million underwater image-text paired dataset using heterogeneous resources, including YouTube, Netflix, NatGeo, etc. To fine-tune AquaticCLIP, we propose a prompt-guided vision encoder that progressively aggregates patch features via learnable prompts, while a vision-guided mechanism enhances the language encoder by incorporating visual context. The model is optimized through a contrastive pretraining loss to align visual and textual modalities. AquaticCLIP achieves notable performance improvements in zero-shot settings across multiple underwater computer vision tasks, outperforming existing methods in both robustness and interpretability. Our model sets a new benchmark for vision-language applications in underwater environments. The code and dataset for AquaticCLIP are publicly available on GitHub at xxx. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01785 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis Alawode, Basit Ganapathi, Iyyakutti Iyappan Javed, Sajid Werghi, Naoufel Bennamoun, Mohammed Mahmood, Arif Computer Vision and Pattern Recognition Artificial Intelligence The preservation of aquatic biodiversity is critical in mitigating the effects of climate change. Aquatic scene understanding plays a pivotal role in aiding marine scientists in their decision-making processes. In this paper, we introduce AquaticCLIP, a novel contrastive language-image pre-training model tailored for aquatic scene understanding. AquaticCLIP presents a new unsupervised learning framework that aligns images and texts in aquatic environments, enabling tasks such as segmentation, classification, detection, and object counting. By leveraging our large-scale underwater image-text paired dataset without the need for ground-truth annotations, our model enriches existing vision-language models in the aquatic domain. For this purpose, we construct a 2 million underwater image-text paired dataset using heterogeneous resources, including YouTube, Netflix, NatGeo, etc. To fine-tune AquaticCLIP, we propose a prompt-guided vision encoder that progressively aggregates patch features via learnable prompts, while a vision-guided mechanism enhances the language encoder by incorporating visual context. The model is optimized through a contrastive pretraining loss to align visual and textual modalities. AquaticCLIP achieves notable performance improvements in zero-shot settings across multiple underwater computer vision tasks, outperforming existing methods in both robustness and interpretability. Our model sets a new benchmark for vision-language applications in underwater environments. The code and dataset for AquaticCLIP are publicly available on GitHub at xxx. |
| title | AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.01785 |