Many open-world applications require the detection of novel objects, yet
state-of-the-art object detection and instance segmentation networks do not
excel at this task. The key issue lies in their assumption that regions without
any annotations should be suppressed as negatives, which teaches the model to
treat the unannotated objects as background. To address this issue, we propose
a simple yet surprisingly powerful data augmentation and training scheme we
call Learning to Detect Every Thing (LDET). To avoid suppressing hidden
objects, background objects that are visible but unlabeled, we paste annotated
objects on a background image sampled from a small region of the original
image. Since training solely on such synthetically-augmented images suffers
from domain shift, we decouple the training into two parts: 1) training the
region classification and regression head on augmented images, and 2)~training
the mask heads on original images. In this way, a model does not learn to
classify hidden objects as background while generalizing well to real images.
LDET leads to significant improvements on many datasets in the open-world
instance segmentation task, outperforming baselines on cross-category
generalization on COCO, as well as cross-dataset evaluation on UVO and
Cityscapes.

为了解决现有网络对未注释区域默认为负样本的问题，引入了一种数据增广和训练方法，称为 Learning to Detect Every Thing (LDET)。在 LDET 中，实现将带注释物体贴在一张采样自原始图像局部区域的背景图像上，然后将训练过程分为两部分进行，最终在包括 COCO、UVO 和 Cityscapes 等多个数据集上获得了优异的结果。

学习在开放世界中检测所有事物

Learning to Detect Every Thing in an Open World

What defines an action like "kicking ball"? We argue that the true meaning of
an action lies in the change or transformation an action brings to the
environment. In this paper, we propose a novel representation for actions by
modeling an action as a transformation which changes the state of the
environment before the action happens (precondition) to the state after the
action (effect). Motivated by recent advancements of video representation using
deep learning, we design a Siamese network which models the action as a
transformation on a high-level feature space. We show that our model gives
improvements on standard action recognition datasets including UCF101 and
HMDB51. More importantly, our approach is able to generalize beyond learned
action categories and shows significant performance improvement on
cross-category generalization on our new ACT dataset.

本文提出将动作作为转换模型的一种新方法，并通过设计 Siamese 网络来学习动作的高层次特征，实现了对于视频数据的动作识别，同时在 ACT 数据集上显示出了重要的跨类别泛化性能改进。