We present Contextualized Local Visual Embeddings (CLoVE), a self-supervised
convolutional-based method that learns representations suited for dense
prediction tasks. CLoVE deviates from current methods and optimizes a single
loss function that operates at the level of contextualized local embeddings
learned from output feature maps of convolution neural network (CNN) encoders.
To learn contextualized embeddings, CLoVE proposes a normalized mult-head
self-attention layer that combines local features from different parts of an
image based on similarity. We extensively benchmark CLoVE's pre-trained
representations on multiple datasets. CLoVE reaches state-of-the-art
performance for CNN-based architectures in 4 dense prediction downstream tasks,
including object detection, instance segmentation, keypoint detection, and
dense pose estimation. Code:
$\href{https://github.com/sthalles/CLoVE}{this https URL}$.

我们提出了 Contextualized Local Visual Embeddings（CLoVE），一种用于密集预测任务的自监督卷积方法，它学习适用于密集预测任务的表示。CLoVE 通过优化单一损失函数来学习从卷积神经网络（CNN）编码器的输出特征图中学习的上下文化局部嵌入，与当前方法不同。为了学习上下文化嵌入，CLoVE 提出了一个标准化的多头自注意力层，该层根据相似性结合来自图像不同部分的局部特征。我们在多个数据集上对 CLoVE 的预训练表示进行了广泛的基准测试。在 4 个密集预测下游任务，包括目标检测、实例分割、关键点检测和密集姿态估计中，CLoVE 达到了基于 CNN 的架构的最先进性能。