1. symmetric：对称的
      1. We propose a symmetric encoder-decoder CNN architecture to extract global and multi-scale feature maps.
    2. as indicated by：如…所示
      1. The encoder-decoder network of Figure 1 uses a deep symmetric CNN architecture with skip connections as indicated by black arrows.
    3. objective & subjective：客观的 & 主观的
      1. This part is similar to U-Net, but the difference is that U-net is designed for image segmentation, which is objective and works well even with cropped feature maps. For saliency segmentation, it is subjective and easily affected in different scenarios.
    4. ultimately：最终
      1. We ultimately want to distinguish salient objects from background and so want to map image pixels into a feature space where that distance across salient and background regions is large, but within regions is small.
    5. endeavor：努力
      1. As the CNN becomes increasingly deeper, recent works endeavor to refine or reuse the features from previous layers through identity mappings or concatenation.
    6. diverge：分歧
      1. The CNNs designed for image-level, region-level, and pixel-level tasks begin to diverge in network structure.
    7. diversity：多样性
      1. All of them should be kept to improve the diversity of features.
    8. symbolize：象征着，标志着
      1. The remarkable improvement in the image recognition challenge ILSVRC achieved by AlexNet symbolizes a new era of deep learning for computer vision.
    9. is relieved by：被缓解
      1. Recently, the problem of vanishing gradient is greatly relieved by introducing the skip connections into the network.
    10. applicable：使用的
      1. Since the numbers of channels for image.png and image.pngare different, identity mapping is not applicable.