In this paper, we introduce a novel network, called discriminative feature
network (DFNet), to address the unsupervised video object segmentation task. To
capture the inherent correlation among video frames, we learn discriminative
features (D-features) from the input images that reveal feature distribution
from a global perspective. The D-features are then used to establish
correspondence with all features of test image under conditional random field
(CRF) formulation, which is leveraged to enforce consistency between pixels.
The experiments verify that DFNet outperforms state-of-the-art methods by a
large margin with a mean IoU score of 83.4% and ranks first on the DAVIS-2016
leaderboard while using much fewer parameters and achieving much more efficient
performance in the inference phase. We further evaluate DFNet on the FBMS
dataset and the video saliency dataset ViSal, reaching a new state-of-the-art.
To further demonstrate the generalizability of our framework, DFNet is also
applied to the image object co-segmentation task. We perform experiments on a
challenging dataset PASCAL-VOC and observe the superiority of DFNet. The
thorough experiments verify that DFNet is able to capture and mine the
underlying relations of images and discover the common foreground objects.

本文提出了一种名为 DFNet 的新型网络，用于解决无监督视频物体分割任务，通过提取刻画全局特征分布的判别性特征，使用条件随机场 (CRF) 建立与测试图像的特征对应关系，并在像素级别上进行一致性约束。实验结果表明，该方法在使用更少的参数和更高效的推断性能的情况下，获得了优于当前最先进方法的 83.4% 的平均 IoU 分数，并在 DAVIS-2016 排行榜上排名第一。DFNet 进一步应用于图像对象协同分割任务，并在具有挑战性的数据集 PASCAL-VOC 上展示出其广泛适用性。

基于 CRF 的学习鉴别性特征方法用于非监督视频对象分割

Learning Discriminative Feature with CRF for Unsupervised Video Object  Segmentation

This work proposes a novel attentive graph neural network (AGNN) for
zero-shot video object segmentation (ZVOS). The suggested AGNN recasts this
task as a process of iterative information fusion over video graphs.
Specifically, AGNN builds a fully connected graph to efficiently represent
frames as nodes, and relations between arbitrary frame pairs as edges. The
underlying pair-wise relations are described by a differentiable attention
mechanism. Through parametric message passing, AGNN is able to efficiently
capture and mine much richer and higher-order relations between video frames,
thus enabling a more complete understanding of video content and more accurate
foreground estimation. Experimental results on three video segmentation
datasets show that AGNN sets a new state-of-the-art in each case. To further
demonstrate the generalizability of our framework, we extend AGNN to an
additional task: image object co-segmentation (IOCS). We perform experiments on
two famous IOCS datasets and observe again the superiority of our AGNN model.
The extensive experiments verify that AGNN is able to learn the underlying
semantic/appearance relationships among video frames or related images, and
discover the common objects.

提出了一种新的关注图神经网络 (AGNN)，用于零样本视频对象分割 (ZVOS)。所提出的 AGNN 将此任务作为视频图上迭代信息融合的过程。通过参数化消息传递，AGNN 能够有效地捕捉和挖掘视频帧之间更丰富和更高阶的关系，因此实现更全面的视频内容理解和更准确的前景估计。扩展 AGNN 到另一个任务时，我们进一步证明了我们的框架的通用性。广泛的实验验证了 AGNN 能够学习视频帧或相关图像之间的潜在语义 / 外观关系，并发现共同的对象。