Non-local operation is widely explored to model the long-range dependencies.
However, the redundant computation in this operation leads to a prohibitive
complexity. In this paper, we present a Representative Graph (RepGraph) layer
to dynamically sample a few representative features, which dramatically reduces
redundancy. Instead of propagating the messages from all positions, our
RepGraph layer computes the response of one node merely with a few
representative nodes. The locations of representative nodes come from a learned
spatial offset matrix. The RepGraph layer is flexible to integrate into many
visual architectures and combine with other operations. With the application of
semantic segmentation, without any bells and whistles, our RepGraph network can
compete or perform favourably against the state-of-the-art methods on three
challenging benchmarks: ADE20K, Cityscapes, and PASCAL-Context datasets. In the
task of object detection, our RepGraph layer can also improve the performance
on the COCO dataset compared to the non-local operation. Code is available at
this https URL

本论文提出了一种名为 RepGraph 层的新型非本地操作方法，通过动态采样一些代表性特征来极大地减少冗余计算，该方法在语义分割和物体检测等任务上，与现有方法相比具有明显的竞争优势。

代表性图神经网络

Representative Graph Neural Network

This paper aims to tackle the challenging problem of one-shot object
detection. Given a query image patch whose class label is not included in the
training data, the goal of the task is to detect all instances of the same
class in a target image. To this end, we develop a novel {\em co-attention and
co-excitation} (CoAE) framework that makes contributions in three key technical
aspects. First, we propose to use the non-local operation to explore the
co-attention embodied in each query-target pair and yield region proposals
accounting for the one-shot situation. Second, we formulate a
squeeze-and-co-excitation scheme that can adaptively emphasize correlated
feature channels to help uncover relevant proposals and eventually the target
objects. Third, we design a margin-based ranking loss for implicitly learning a
metric to predict the similarity of a region proposal to the underlying query,
no matter its class label is seen or unseen in training. The resulting model is
therefore a two-stage detector that yields a strong baseline on both VOC and
MS-COCO under one-shot setting of detecting objects from both seen and
never-seen classes. Codes are available at
this https URL

本文提出了基于 “co-attention and co-excitation (CoAE)” 框架的一次性目标检测方法，利用无标签的 query image patch 来检测目标图像中与其同类别的所有实例，并通过非局部操作、squeeze-and-co-excitation 机制以及基于 margin 的排名损失等三个技术方面的贡献来提高模型性能。

基于 Co-Attention 和 Co-Excitation 的单次物体检测

One-Shot Object Detection with Co-Attention and Co-Excitation

Detecting fashion landmarks is a fundamental technique for visual clothing
analysis. Due to the large variation and non-rigid deformation of clothes,
localizing fashion landmarks suffers from large spatial variances across poses,
scales, and styles. Therefore, understanding contextual knowledge of clothes is
required for accurate landmark detection. To that end, in this paper, we
propose a fashion landmark detection network with a global-local embedding
module. The global-local embedding module is based on a non-local operation for
capturing long-range dependencies and a subsequent convolution operation for
adopting local neighborhood relations. With this processing, the network can
consider both global and local contextual knowledge for a clothing image. We
demonstrate that our proposed method has an excellent ability to learn advanced
deep feature representations for fashion landmark detection. Experimental
results on two benchmark datasets show that the proposed network outperforms
the state-of-the-art methods. Our code is available at
this https URL

本文介绍了一种基于全局 - 局部嵌入模块的时尚地标检测网络，能够考虑服装图像的全局和局部相关知识，其中包括非局部操作用于捕捉远距离依赖关系和接下来的卷积操作用于采用局部邻域关系。实验结果表明，该方法在时尚地标检测方面有着很好的能力，并且优于最先进的方法.

全局 - 局部嵌入式模块用于时尚关键点检测

A Global-Local Emebdding Module for Fashion Landmark Detection

This paper describes our solution for the 2$^\text{nd}$ YouTube-8M video
understanding challenge organized by Google AI. Unlike the video recognition
benchmarks, such as Kinetics and Moments, the YouTube-8M challenge provides
pre-extracted visual and audio features instead of raw videos. In this
challenge, the submitted model is restricted to 1GB, which encourages
participants focus on constructing one powerful single model rather than
incorporating of the results from a bunch of models. Our system fuses six
different sub-models into one single computational graph, which are categorized
into three families. More specifically, the most effective family is the model
with non-local operations following the NetVLAD encoding. The other two family
models are Soft-BoF and GRU, respectively. In order to further boost single
models performance, the model parameters of different checkpoints are averaged.
Experimental results demonstrate that our proposed system can effectively
perform the video classification task, achieving 0.88763 on the public test set
and 0.88704 on the private set in terms of GAP@20, respectively. We finally
ranked at the fourth place in the YouTube-8M video understanding challenge.

本文介绍了我们在 Google AI 组织的第二届 YouTube-8M 视频理解挑战中的解决方案，该方案利用非本地操作实现了多个子模型的融合来有效地执行视频分类任务。