.png){kind=icon}
.png){kind=icon}
Return
Segmentation Mask Refinement Using Image Transformations
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2017.2772269.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper discusses object proposal generation, which is a crucial step of instance-level semantic segmentation (instance segmentation). Known as a challenging computer vision task, the instance segmentation requires jointly detecting and segmenting individual instances of objects in an image. A common approach to this task is first to propose a set of class-agnostic object candidates in the forms of segmentation masks, which represent both object locations and boundaries, and then to perform classification on each object candidate. In this paper, we propose an effective refinement process that employs image transformations and mask matching to increase the accuracy of object segmentation masks. The proposed refinement process is applied to three state-of-the-art object proposal methods (DeepMask, SharpMask, and FastMask), and is evaluated on two standard benchmarks (Microsoft COCO and PASCAL VOC). Both the quantitative and qualitative results show the effectiveness of the process across various experimental settings.
Keywords:
Instance segmentation
object proposal
segmentation mask
convolutional neural networks
deep learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.