Uni-OVSeg: Weakly-Supervised Open-Vocabulary Segmentation with Cutting-Edge Performance

Uni-OVSeg offers a powerful solution for open-vocabulary segmentation, outperforming both weakly-supervised and fully-supervised methods. By reducing reliance on complex image-mask-text triplets and refining text descriptions, it achieves remarkable improvements in segmentation quality, especially on the challenging PASCAL Context-459 dataset.


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.

:::

Abstract and 1. Introduction

2. Related works

3. Method and 3.1. Problem definition

3.2. Baseline and 3.3. Uni-OVSeg framework

4. Experiments

4.1. Implementation details

4.2. Main results

4.3. Ablation study

5. Conclusion

6. Broader impacts and References

\ A. Framework details

B. Promptable segmentation

C. Visualisation

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

\ Table 4. Mask classification performance. we first pool the region features based on the provided ground truth masks. Thesepooled features are then projected into the CLIP embedding space, where they are classified using text embeddings. We report the Top-1 accuracy (%) and time (sec. / sample).

\ 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


Print Share Comment Cite Upload Translate Updates
APA

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/

MLA
" » Uni-OVSeg: Weakly-Supervised Open-Vocabulary Segmentation with Cutting-Edge Performance." Segmentation | Sciencx - Tuesday November 12, 2024, https://www.scien.cx/2024/11/12/uni-ovseg-weakly-supervised-open-vocabulary-segmentation-with-cutting-edge-performance/
HARVARD
Segmentation | Sciencx Tuesday November 12, 2024 » Uni-OVSeg: Weakly-Supervised Open-Vocabulary Segmentation with Cutting-Edge Performance., viewed ,<https://www.scien.cx/2024/11/12/uni-ovseg-weakly-supervised-open-vocabulary-segmentation-with-cutting-edge-performance/>
VANCOUVER
Segmentation | Sciencx - » Uni-OVSeg: Weakly-Supervised Open-Vocabulary Segmentation with Cutting-Edge Performance. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2024/11/12/uni-ovseg-weakly-supervised-open-vocabulary-segmentation-with-cutting-edge-performance/
CHICAGO
" » Uni-OVSeg: Weakly-Supervised Open-Vocabulary Segmentation with Cutting-Edge Performance." Segmentation | Sciencx - Accessed . https://www.scien.cx/2024/11/12/uni-ovseg-weakly-supervised-open-vocabulary-segmentation-with-cutting-edge-performance/
IEEE
" » Uni-OVSeg: Weakly-Supervised Open-Vocabulary Segmentation with Cutting-Edge Performance." Segmentation | Sciencx [Online]. Available: https://www.scien.cx/2024/11/12/uni-ovseg-weakly-supervised-open-vocabulary-segmentation-with-cutting-edge-performance/. [Accessed: ]
rf:citation
» Uni-OVSeg: Weakly-Supervised Open-Vocabulary Segmentation with Cutting-Edge Performance | Segmentation | Sciencx | 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.

You must be logged in to translate posts. Please log in or register.