论文标题
通过中间距离回归监督改善像素嵌入学习
Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation
论文作者
论文摘要
作为一种无建议的方法，通过像素嵌入学习和聚类的实例分割正在越来越重视。与框架框的细化方法（例如蒙版R-CNN）相比，它在处理复杂形状和密集的物体方面具有潜在的优势。在这项工作中，我们提出了一种简单但高效的架构，用于对象感知的嵌入学习。将距离回归模块合并到我们的体系结构中，以生成用于快速聚类的种子。同时，我们表明，距离回归模块所学的功能能够显着促进学到的对象感知嵌入的精度。通过简单地将距离回归模块的特征与嵌入模块的输入相连，与没有串联的相同设置相比，CVPPP叶片分割挑战的MSBD得分可以进一步提高8％以上，从而在Codalab的排行榜中产生最佳的总体结果。
As a proposal-free approach, instance segmentation through pixel embedding learning and clustering is gaining more emphasis. Compared with bounding box refinement approaches, such as Mask R-CNN, it has potential advantages in handling complex shapes and dense objects. In this work, we propose a simple, yet highly effective, architecture for object-aware embedding learning. A distance regression module is incorporated into our architecture to generate seeds for fast clustering. At the same time, we show that the features learned by the distance regression module are able to promote the accuracy of learned object-aware embeddings significantly. By simply concatenating features of the distance regression module to the images as inputs of the embedding module, the mSBD scores on the CVPPP Leaf Segmentation Challenge can be further improved by more than 8% compared to the identical set-up without concatenation, yielding the best overall result amongst the leaderboard at CodaLab.
