arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.06810cs.CV
收藏

See More,Know More:使用Co-Attention Siamese Networks的无监督视频对象分割

See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks

Inception Institute of Artificial Intelligence(人工智能研究院);Shanghai Jiao Tong University(上海交通大学);Australian National University(澳大利亚国立大学)

Xiankai Lu, Wenguan Wang, Chao Ma, Jianbing Shen, Ling Shao, Fatih Porikli

摘要:

我们引入了一种新的网络,称为共同注意连体网络(COSNet),从整体上解决无监督视频对象分割任务。我们强调视频帧之间的内在相关性的重要性,并结合全局共同注意力机制,以进一步改进最先进的基于深度学习的解决方案,该解决方案主要关注于学习短期时间段中的外观和运动的区别性前景表示。我们网络中的共同关注层通过联合计算并将共同关注响应附加到联合特征空间中,为捕获全局相关性和场景上下文提供了有效和胜任的阶段。我们用成对的视频帧来训练COSNet,这自然会增加训练数据并提高学习能力。在分割阶段,共同注意模型通过一起处理多个参考帧来编码有用信息,从而更好地推断频繁再现和显著的前景对象。我们提出了一个统一的端到端的可训练框架,其中可以导出不同的共同注意力变体,用于挖掘视频中的丰富上下文。我们在三个大型基准测试中进行的广泛实验表明,COSNet的性能远远优于当前的替代品。

英文摘要:

We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view. We emphasize the importance of inherent correlation among video frames and incorporate a global co-attention mechanism to improve further the state-of-the-art deep learning based solutions that primarily focus on learning discriminative foreground representations over appearance and motion in short-term temporal segments. The co-attention layers in our network provide efficient and competent stages for capturing global correlations and scene context by jointly computing and appending co-attention responses into a joint feature space. We train COSNet with pairs of video frames, which naturally augments training data and allows increased learning capacity. During the segmentation stage, the co-attention model encodes useful information by processing multiple reference frames together, which is leveraged to infer the frequently reappearing and salient foreground objects better. We propose a unified and end-to-end trainable framework where different co-attention variants can be derived for mining the rich context within videos. Our extensive experiments over three large benchmarks manifest that COSNet outperforms the current alternatives by a large margin.

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。

↑