We present a novel explicit shape representation for instance segmentation. Based on how to model the object shape, current instance segmentation systems can be divided into two categories, implicit and explicit models. The implicit methods, which represent the object mask/contour by intractable network parameters, and produce it through pixel-wise classification, are predominant. However, the explicit methods, which parameterize the shape with simple and explainable models, are less explored. Since the operations to generate the final shape are light-weighted, the explicit methods have a clear speed advantage over implicit methods, which is crucial for real-world applications. The proposed USD-Seg adopts a linear model, sparse coding with dictionary, for object shapes. First, it learns a dictionary from a large collection of shape datasets, making any shape being able to be decomposed into a linear combination through the dictionary. Hence the name "Universal Shape Dictionary". Then it adds a simple shape vector regression head to ordinary object detector, giving the detector segmentation ability with minimal overhead. For quantitative evaluation, we use both average precision (AP) and the proposed Efficiency of AP (AP$_E$) metric, which intends to also measure the computational consumption of the framework to cater to the requirements of real-world applications. We report experimental results on the challenging COCO dataset, in which our single model on a single Titan Xp GPU achieves 35.8 AP and 27.8 AP$_E$ at 65 fps with YOLOv4 as base detector, 34.1 AP and 28.6 AP$_E$ at 12 fps with FCOS as base detector.


翻译:我们展示了一个新型的清晰形状代表, 例如 区块 。 根据如何模拟对象形状, 当前的实例分割系统可以分为两类, 隐含和显性模型 。 隐含的方法, 以棘手的网络参数代表对象遮罩/ 颜色, 并通过像素分类生成它, 但是, 以简单和可解释的模型来测量形状的清晰方法, 探索较少。 由于生成最终形状的操作是轻量的, 清晰的方法比隐含的方法具有明显的速度优势, 这对真实世界的应用至关重要 。 拟议的 USSeg 采用了一种线性模型, 与字典一起稀释, 用于对象形状。 首先, 它从大量收集的形状数据集中学习了字典, 使任何形状能够通过字典将形状分解成线性组合。 因此, 名称“ Universal shape Dictionary ” 。 之后, 它增加了一个简单形状矢量的矢量回归模型头, 使检测或分解能力极小于真实世界应用 3, 3- 美元, 我们使用平均精确度 3- AS AS 标准 AS AS AS AS a AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AS AL AS AL 的计算结果 。

0
下载
关闭预览

相关内容

【干货书】真实机器学习,264页pdf,Real-World Machine Learning
100+篇《自监督学习(Self-Supervised Learning)》论文最新合集
专知会员服务
165+阅读 · 2020年3月18日
Stabilizing Transformers for Reinforcement Learning
专知会员服务
60+阅读 · 2019年10月17日
【哈佛大学商学院课程Fall 2019】机器学习可解释性
专知会员服务
105+阅读 · 2019年10月9日
【SIGGRAPH2019】TensorFlow 2.0深度学习计算机图形学应用
专知会员服务
41+阅读 · 2019年10月9日
Transferring Knowledge across Learning Processes
CreateAMind
29+阅读 · 2019年5月18日
论文浅尝 | Global Relation Embedding for Relation Extraction
开放知识图谱
12+阅读 · 2019年3月3日
Unsupervised Learning via Meta-Learning
CreateAMind
43+阅读 · 2019年1月3日
A Technical Overview of AI & ML in 2018 & Trends for 2019
待字闺中
18+阅读 · 2018年12月24日
disentangled-representation-papers
CreateAMind
26+阅读 · 2018年9月12日
Hierarchical Disentangled Representations
CreateAMind
4+阅读 · 2018年4月15日
论文浅尝 | Reinforcement Learning for Relation Classification
开放知识图谱
9+阅读 · 2017年12月10日
【推荐】YOLO实时目标检测(6fps)
机器学习研究会
20+阅读 · 2017年11月5日
Auto-Encoding GAN
CreateAMind
7+阅读 · 2017年8月4日
Learning Discriminative Model Prediction for Tracking
Learning Implicit Fields for Generative Shape Modeling
Arxiv
10+阅读 · 2018年12月6日
Arxiv
3+阅读 · 2018年3月5日
VIP会员
相关资讯
Transferring Knowledge across Learning Processes
CreateAMind
29+阅读 · 2019年5月18日
论文浅尝 | Global Relation Embedding for Relation Extraction
开放知识图谱
12+阅读 · 2019年3月3日
Unsupervised Learning via Meta-Learning
CreateAMind
43+阅读 · 2019年1月3日
A Technical Overview of AI & ML in 2018 & Trends for 2019
待字闺中
18+阅读 · 2018年12月24日
disentangled-representation-papers
CreateAMind
26+阅读 · 2018年9月12日
Hierarchical Disentangled Representations
CreateAMind
4+阅读 · 2018年4月15日
论文浅尝 | Reinforcement Learning for Relation Classification
开放知识图谱
9+阅读 · 2017年12月10日
【推荐】YOLO实时目标检测(6fps)
机器学习研究会
20+阅读 · 2017年11月5日
Auto-Encoding GAN
CreateAMind
7+阅读 · 2017年8月4日
Top
微信扫码咨询专知VIP会员