AdaptIS: Adaptive Instance Selection Networkhtml
2019-09-19 12:58:07git
Paper: https://arxiv.org/pdf/1909.07829.pdf github
Code (MXNet): https://github.com/saic-vul/adaptis 函数
Pretrained model for ToyV1: https://drive.google.com/open?id=1IuJUh0JvbKYILBxCeO2h6U4LG-9DoTHi
Pretrained model for ToyV2: https://drive.google.com/open?id=1RxepfpJF5gRpRNYu1urdV748suF3TL5k优化
Related Paper: ui
Panoptic Segmentation, Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, Piotr Dollar google
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization [Paper] [Code] [Blog] spa
An intriguing failing of convolutional neural networks and the CoordConv solution [Paper] [Code] [Blog] orm
1. Background and Motivation: htm
本文提出一种新的分割方式,即:给出一个 BBox,该方法能够将该位置的物体分割出来,而不是所有分割出来。示意图以下所示:
本文所提出方法的名称为:AdaptIS,不依赖于 bounding box proposal。而是直接优化目标分割精度。给定一张图像 I 和 一个固定的 point proposal (x, y),做者直接优化目标损失函数。咱们利用一个 pixel-wise loss 来计算 AdaptIS 预测 和 target object 的 mask。