update

ZHAOBenyun · Sep 2, 2024 · ac47f9a · ac47f9a
1 parent aeae791
commit ac47f9a
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 15 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/README.md b/README.md
@@ -26,24 +26,11 @@ Benyun Zhao<sup>1</sup>, Xunkuai Zhou<sup>2,1</sup>, Guidong Yang<sup>1</sup>, J
 </button>
 </div>
 
-<!-- <button style="background-color: #000000; color: white;margin-right: 15px; padding: 10px 15px; border: none; border-radius: 5px;">
-<a href="https://zhaobenyun.github.io/CUBIT/ICASSP_2024_Appendix.pdf" style="color: white; text-decoration: none;">Supplementary;</a>
-</button> -->
-
-<!-- <button style="background-color: #000000; color: white;margin-right: 15px; padding: 10px 15px;border: none; border-radius: 5px;">
-<a href="https://zhaobenyun.github.io/CUBIT/" style="color: white; text-decoration: none;">Project Page;</a>
-</button> -->
-
-<br>
+<!-- <br>
 <button style="background-color: #000000; color: white; margin: 0 auto; padding: 10px 15px;border: none; border-radius: 5px;">
 Dataset can be available at: <br><a href="https://mycuhk-my.sharepoint.com/:f:/g/personal/1155145791_link_cuhk_edu_hk/EvIGO4s7idhAuIj_WrfJ3wgB5HS6bSfPbce8WJxqLEwEWA?e=ftelDM" style="color: white; text-decoration: none;">https://mycuhk-my.sharepoint.com/:f:/g/personal/1155145791_link_cuhk_edu_hk/EvIGO4s7idhAuIj_WrfJ3wgB5HS6bSfPbce8WJxqLEwEWA?e=ftelDM</a>
-</button>
-
-<!-- <div style="text-align: center; font-family: 'American Typewriter'; font-weight: 400; "> 
-<h2>Abstract</h2>
-</div>
+</button> -->
 
-Learning-based visual inspection, integrated with unmanned robotic system, offers a more effective, efficient, and safer alternative for infrastructure inspection tasks that are traditionally heavily reliant on human labor. However, the potential of learning-based inspection methods remains limited due to the lack of publicly available, high-quality datasets. This paper presents CUBIT, a high-resolution defect detection dataset comprising more than $5500$ images with resolutions up to $8000\times6000$ which covers a broader spectrum of practical situations, backgrounds, and defect categories than existing publicly available datasets. We conduct extensive experiments to benchmark the performance of state-of-the-art real-time detection methods on our proposed dataset, validating the effectiveness of it. Moreover, based on the benchmark results, we develop a module named GIPFPP to integrate multi-scale feature, enhancing the AP by 3\% while reducing the number of parameters by 10\% on baseline model. Additionally, a real-site UAV-based inspection has been conducted to verify the reliability of the dataset. -->
 
 <div style="text-align: center; font-family: 'American Typewriter'; font-weight: 400; "> 
 <h2>Sample images in CUBIT</h2>