Authors
- Weiming Zhuang
- Chen Chen
- Zhizhong Li
- Sina Sajadmanesh
- Jingtao Li
- Jiabo Huang
- Vikash Sehwag
- Vivek Sharma
- Hirotaka Shinozaki
- Felan Carlo Garcia
- Yihao Zhan
- Naohiro Adachi
- Ryoji Eki
- Michael Spranger
- Peter Stone
- Lingjuan Lyu
Venue
- CVPR-25
Date
- 2025
Argus: A Compact and Versatile Foundation Model for Vision
Chen Chen
Zhizhong Li
Jingtao Li
Jiabo Huang
Vivek Sharma
Hirotaka Shinozaki
Felan Carlo Garcia
Yihao Zhan
Naohiro Adachi
Ryoji Eki
CVPR-25
2025
Abstract
While existing vision and multi-modal foundation models can handle multiple computer vision tasks, they often suffer from significant limitations, including huge demand for data and computational resources during training and inconsistent performance across vision tasks at deployment time. To address these challenges, we introduce Argus (The name comes from Argus Panoptes--a hundred-eyed giant with ''all-seeing'' capability in Greek mythology), a compact and versatile vision foundation model designed to support a wide range of vision tasks through a unified multitask architecture. Argus employs a two-stage training strategy: (i) multitask pretraining over core vision tasks with a shared backbone that includes a lightweight adapter to inject task-specific inductive biases, and (ii) scalable and efficient adaptation to new tasks by fine-tuning only the task-specific decoders. Extensive evaluations demonstrate that Argus, despite its relatively compact and training-efficient design of merely 100M backbone parameters (only 13.6% of which are trained using 1.6M images), competes with and even surpasses much larger models. Compared to state-of-the-art foundation models, Argus not only covers a broader set of vision tasks but also matches or outperforms the models with similar sizes on 12 tasks. We expect that Argus will accelerate the real-world adoption of vision foundation models in resource-constrained scenarios.
Related Publications
Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment. Referred to as ``zero-shot learning," this ability remains elusive for general-purpose reinforcement learning algorithms. While rec…
The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered that the state-of-the-art visual generative models can generate content that bears a striking r…
Scaling up the model size and computation has brought consistent performance improvements in supervised learning. However, this lesson often fails to apply to reinforcement learning (RL) because training the model on non-stationary data easily leads to overfitting and unstab…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.