Salient object detection, which simulates human visual perception in locating the most
significant object (s) in a scene, has been widely applied to various computer vision tasks …

Due to object detection's close relationship with video analysis and image understanding, it
has attracted much research attention in recent years. Traditional object detection methods …

The recently proposed camouflaged object detection (COD) attempts to segment objects that
are visually blended into their surroundings, which is extremely complex and difficult in real …

Existing state-of-the-art saliency detection methods heavily rely on CNN-based
architectures. Alternatively, we rethink this task from a convolution-free sequence-to …

In this paper, we design a simple yet powerful deep network architecture, U 2-Net, for salient
object detection (SOD). The architecture of our U 2-Net is a two-level nested U-structure. The …

Most salient object detection approaches use U-Net or feature pyramid networks (FPN) as
their basic structures. These methods ignore two key problems when the encoder …

Deep-learning based salient object detection methods achieve great progress. However, the
variable scale and unknown category of salient objects are great challenges all the time …

Being able to learn dense semantic representations of images without supervision is an
important problem in computer vision. However, despite its significance, this problem …

Most of existing salient object detection models have achieved great progress by
aggregating multi-level features extracted from convolutional neural networks. However …

Fully convolutional neural networks (FCNs) have shown their advantages in the salient
object detection task. However, most existing FCNs-based methods still suffer from coarse …