Pixel-level annotations are expensive and time consuming to obtain. Hence,
weak supervision using only image tags could have a significant impact in
semantic segmentation. Recently, CNN-based methods have proposed to fine-tune
pre-trained networks using image tags. Without additional information, this
leads to poor localization accuracy. This problem, however, was alleviated by
making use of objectness priors to generate foreground/background masks.
Unfortunately these priors either require training pixel-level
annotations/bounding boxes, or still yield inaccurate object boundaries. Here,
we propose a novel method to extract markedly more accurate masks from the
pre-trained network itself, forgoing external objectness modules. This is
accomplished using the activations of the higher-level convolutional layers,
smoothed by a dense CRF. We demonstrate that our method, based on these masks
and a weakly-supervised loss, outperforms the state-of-the-art tag-based
weakly-supervised semantic segmentation techniques. Furthermore, we introduce a
new form of inexpensive weak supervision yielding an additional accuracy boost.

在语义分割方面仅使用图像标签的弱监督方法在像素级注释方面费时昂贵。本文提出了一种不使用外部物体模块的新方法，使用卷积层的激活并通过稠密 CRF 平滑来从预训练网络本身中提取标记，以实现更精确地语义分割。此外，我们介绍了一种新的廉价的弱监督方法，可提高分类效果。

基于内置前 / 背景先验的弱监督语义分割

Built-in Foreground/Background Prior for Weakly-Supervised Semantic  Segmentation

Building on the success of recent discriminative mid-level elements, we
propose a surprisingly simple approach for object detection which performs
comparable to the current state-of-the-art approaches on PASCAL VOC comp-3
detection challenge (no external data). Through extensive experiments and
ablation analysis, we show how our approach effectively improves upon the
HOG-based pipelines by adding an intermediate mid-level representation for the
task of object detection. This representation is easily interpretable and
allows us to visualize what our object detector "sees". We also discuss the
insights our approach shares with CNN-based methods, such as sharing
representation between categories helps.

通过在对象检测任务中添加中层表示，本文提出一种简单的方法，通过广泛的实验和消融分析，在 PASCAL VOC comp-3 检测挑战中取得了与当前最先进方法相媲美的效果，并利用中层表示，有效地改进了 HOG-based pipelines，同时探讨了本方法与基于 CNN 的方法之间的共通之处。