效能超越何愷明Mask R-CNN!華科大開源影象分割新方法

AMiner學術頭條發表於2019-05-15

CVPR是IEEE Conference on Computer Vision and Pattern Recongnition的縮寫,即IEEE國際計算機視覺模式識別會議。該會議是由IEEE舉辦的計算機視覺模式識別領域的頂級會議。

效能超越何愷明Mask R-CNN!華科大開源影象分割新方法

CVPR 2019一共收到5165篇有效投遞,一共接收了1300篇。本文選取了其中的口頭報告論文進行推薦。

  • 論文題目

    Mask Scoring R-CNN

  • 作者

    Zhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, Xinggang Wang

  • 會議/年份

    CVPR 2019

  • 連結

    https://arxiv.org/abs/1903.00241v1

  • Abstract

    Letting a deep network be aware of the quality of its own predictions is an interesting yet important problem. In the task of instance segmentation, the confidence of instance classification is used as mask quality score in most instance segmentation frameworks. However, the mask quality, quantified as the IoU between the instance mask and its ground truth, is usually not well correlated with classification score. In this paper, we study this problem and propose Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks. The proposed network block takes the instance feature and the corresponding predicted mask together to regress the mask IoU. The mask scoring strategy calibrates the misalignment between mask quality and mask score, and improves instance segmentation performance by prioritizing more accurate mask predictions during COCO AP evaluation. By extensive evaluations on the COCO dataset, Mask Scoring R-CNN brings consistent and noticeable gain with different models, and outperforms the state-of-the-art Mask R-CNN. We hope our simple and effective approach will provide a new direction for improving instance segmentation. The source code of our method is available at \url{this https URL}.

推薦理由

華中科技大學的黃釗金作為一作完成的研究Mask Scoring R-CNN,在COCO影象例項分割任務上超越了何愷明的Mask R-CNN,拿下了計算機視覺頂會CVPR 2019的口頭報告,也就是說這篇論文從5000多篇投稿中脫穎而出,成為最頂尖的5.6%。

這篇論文中,研究人員提出了一種給演算法的“例項分割假設”打分的新方法。這個分數打得是否準確,就會影響例項分割模型的效能。而Mask R-CNN等前輩,用的打分方法就不太合適。這些模型在例項分割任務裡,雖然輸出結果是一個蒙版,但打分卻是和邊界框目標檢測共享的,都是針對目標區域分類置信度算出來的分數。這個分數,和影象分割蒙版的質量可未必一致,用來評價蒙版的質量,可能就會出偏差。

效能超越何愷明Mask R-CNN!華科大開源影象分割新方法

效能超越何愷明Mask R-CNN!華科大開源影象分割新方法

於是,這篇CPR 2019論文就提出了一種新的打分方法:給蒙版打分,他們稱之為蒙版得分(mask score)。

效能超越何愷明Mask R-CNN!華科大開源影象分割新方法

效能超越何愷明Mask R-CNN!華科大開源影象分割新方法

上圖為COCO 2017測試集(Test-De set)上MS R-CNN和其他例項分割方法的成績對比。無論基幹網路是純粹的ResNet-101,還是用了DCN、FPN,MS R-CNN的AP成績都比Mask R-CNN高出一點幾個百分點。

傳送門:

論文地址:

https://arxiv.org/pdf/1903.00241v1.pdf

該專案已開源:

https://github.com/zjhuang22/maskscoring_rcnn

相關文章