Salient object detection is a task based on a visual attention mechanism, in which algorithms aim to explore objects or regions more attentive than the surrounding areas on the scene or images.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e. g., CIFAR-100 and ImageNet.
#5 best model for Image Classification on CIFAR-100
As an important problem in computer vision, salient object detection (SOD) from images has been attracting an increasing amount of research effort over the years.
In this paper, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection.
SOTA for Salient Object Detection on SOD
In this paper, we propose a novel Cascaded Partial Decoder (CPD) framework for fast and accurate salient object detection.
This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvLSTM).
Recent deep learning based salient object detection methods achieve gratifying performance built upon Fully Convolutional Neural Networks (FCNs).
Though deep learning techniques have made great progress in salient object detection recently, the predicted saliency maps still suffer from incomplete predictions due to the internal complexity of objects and inaccurate boundaries caused by strides in convolution and pooling operations.
RGB-D salient object detection aims to identify the most visually distinctive objects in a pair of color and depth images.
Salient object detection is then viewed as fine-grained object-level saliency segmentation and is progressively optimized with the guidance of the fixation map in a top-down manner.