This content originally appeared on HackerNoon and was authored by Segmentation
:::info Authors:
(1) Zhaoqing Wang, The University of Sydney and AI2Robotics;
(2) Xiaobo Xia, The University of Sydney;
(3) Ziye Chen, The University of Melbourne;
(4) Xiao He, AI2Robotics;
(5) Yandong Guo, AI2Robotics;
(6) Mingming Gong, The University of Melbourne and Mohamed bin Zayed University of Artificial Intelligence;
(7) Tongliang Liu, The University of Sydney.
:::
Table of Links
3. Method and 3.1. Problem definition
3.2. Baseline and 3.3. Uni-OVSeg framework
4. Experiments
6. Broader impacts and References
5. Conclusion
In conclusion, this paper proposes an innovative framework for weakly-supervised open-vocabulary segmentation, named Uni-OVSeg. Using independent image-text and image-mask pairs, Uni-OVSeg effectively reduces the dependency on labour-intensive image-mask-text triplets, meanwhile achieving impressive segmentation performance in open-vocabulary settings. Using the LVLM to refine text descriptions and multi-scale ensemble to enhance the quality of region embeddings, we alleviate the noise in masktext correspondences, achieving substantial performance improvements. Notably, Uni-OVSeg significantly outper
\
\ forms previous state-of-the-art weakly-supervised methods and even surpasses the cutting-edge fully-supervised method on the Challenging PASCAL Context-459 dataset. This impressive advancement demonstrates the superiority of our proposed framework and paves the way for further research.
\
:::info This paper is available on arxiv under CC BY 4.0 DEED license.
:::
\
This content originally appeared on HackerNoon and was authored by Segmentation
Segmentation | Sciencx (2024-11-12T22:27:11+00:00) Uni-OVSeg: Weakly-Supervised Open-Vocabulary Segmentation with Cutting-Edge Performance. Retrieved from https://www.scien.cx/2024/11/12/uni-ovseg-weakly-supervised-open-vocabulary-segmentation-with-cutting-edge-performance/
Please log in to upload a file.
There are no updates yet.
Click the Upload button above to add an update.