上下文感知局部视觉嵌入的自监督学习
Self-supervised Learning of Contextualized Local Visual Embeddings
AI总结:
提出自监督卷积方法 CLoVE,通过归一化多头自注意力层学习上下文局部嵌入,在 4 项密集预测任务中实现 CNN 架构的 SOTA 性能。
摘要:
我们提出了上下文感知局部视觉嵌入(Contextualized Local Visual Embeddings,CLoVE),这是一种基于卷积的自监督方法,用于学习适用于密集预测任务的表征。CLoVE 与现有方法不同,它优化单个损失函数,该损失函数作用于从卷积神经网络(CNN)编码器输出特征图中学习到的上下文感知局部嵌入层面。为学习上下文感知嵌入,CLoVE 提出了一种归一化多头自注意力层,该层基于相似度融合图像不同区域的局部特征。我们在多个数据集上对 CLoVE 的预训练表征进行了广泛基准测试。CLoVE 在目标检测、实例分割、关键点检测和密集姿态估计这 4 项密集预测下游任务中,达到了基于 CNN 架构的最优性能。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。