Posts List

Notes for Adversarial Discriminative Domain Adaptation

About this paper Title: Adversarial Discriminative Domain Adaptation Authors: Eric Tzeng, Judy Hoffman, Kate Saenko, Trevor Darrell Topic: Domain Adaptation From: arXiv:1702.05464, appearing in CVPR 2017 Contributions 将之前的论文里提到的一些方法,例如weight sharing、base models、adversarial loss等,归入了统一的框架之中,并进行了测试; 提出了一种新的框架ADDA,主要思想是不做分类器的自适应,而是设法将目标域的数据映射到域源域差不多的特征空间上,这样就能够复用源域的分类器。

Something about GAN

最近在看关于GANs的论文,并且自己动手用PyTorch写了一些经典文章的实现,想要稍微总结一下,故有此文。在最后我总结了我自己看过的有关GANs的一些比较好的资源,希望对读者有所帮助。

Let's talk about Zero-Shot Learning.

最近在看Zero-Shot learning方面的文章,有些想要记录备忘的东西,就写在这儿吧。

Notes for Amortized Inference and Learning in Latent CRF

This is my notes for Amortized Inference and Learning in Latent Conditional Random Fields for Weakly-Supervised Semantic Image Segmentation. arXiv:1705.01262 Poster & Slides

Notes for SEC

This is my notes for Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation. arxiv: https://arxiv.org/abs/1603.06098 github: https://github.com/kolesman/SEC

Notes: From Faster R-CNN to Mask R-CNN

That’s my notes for the talk “From Faster-RCNN to Mask-RCNN” by Shaoqing Ren on April 26th, 2017. Yesterday – background and pre-works of Mask R-CNN Key functions Classification - What are in the image? Localization - Where are they? Mask (per pixel) classification - Where+ ? More precise to bounding box Landmarks localization - What+, Where+ ? Not only per-pixel mask, but also key points in the objects

Notes for ScribbleSup

毕设需要写一个图像标注的软件, 来给场景分割的数据集做标注. 经学长推荐, 看了今年的这篇文章, 作者中竟然还有 Kaiming He 大神, 给微软膜一秒. 这篇文章讲了一个弱监督的场景分割的算法 ScribbleSup, 主要是先通过 Graph Cut 将输入的 scribble 信息广播到没有标注的像素, 然后用 FCN 来做像素级别的预测. 令人遗憾的是 Github 上并没有人实现 (不能偷懒了TAT).

Notes for YOLO

前几天发烧流鼻涕, 睡不了觉, 因此就熬夜读完了 YOLO 的论文. 可以说, YOLO 的实现方式相较于之前 R-CNN 一系的 Region Proposal 的方法来说, 很有新意. YOLO 将 Classification 和 Bounding Box Regression 合起来放进了 CNN 的输出层里面, 从而大大加快了速度.

Notes for SLIC

文章介绍了当前 State-of-the-Art 的5种超像素 (Superpixel) 的算法, 并主要从其对于图像边缘信息的拟合程度 (their ability to adhere to image boundaries), 速度, 内存利用效率, 以及它们对于图像分割性能的影响 (their impact on segmentation performance) 来综合评价. 同时, 本文还提出了一种 SLIC (simple linear iterative clustering) 的算法, 用的是 k-means clustering 的方法.