Salient Object Detection
235 papers with code • 6 benchmarks • 16 datasets
Libraries
Use these libraries to find Salient Object Detection models and implementations
PASCAL-S
DUTS
HKU-IS
DUT-OMRON
ECSSD
SOC
VT5000
HRSOD
EORSSD
Most implemented papers
Res2Net: A New Multi-scale Backbone Architecture
rwightman/pytorch-image-models
•
•
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.
U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
NathanUA/U-2-Net
•
•
In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD).
RGB-D Salient Object Detection: A Survey
Further, considering that the light field can also provide depth maps, we review SOD models and popular benchmark datasets from this domain as well.
EGNet: Edge Guidance Network for Salient Object Detection
mindspore-ai/models
•
•
ICCV 2019
In the second step, we integrate the local edge information and global location information to obtain the salient edge features.
Reverse Attention-Based Residual Network for Salient Object Detection
mindspore-ai/models
•
•
IEEE Transactions on Image Processing 2020
Benefiting from the quick development of deep convolutional neural networks, especially fully convolutional neural networks (FCNs), remarkable progresses have been achieved on salient object detection recently.
A Simple Pooling-Based Design for Real-Time Salient Object Detection
backseason/PoolNet
•
•
CVPR 2019
We further design a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway.
Deeply supervised salient object detection with short connections
Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs).
F3Net: Fusion, Feedback and Focus for Salient Object Detection
weijun88/F3Net
•
•
Furthermore, different from binary cross entropy, the proposed PPA loss doesn't treat pixels equally, which can synthesize the local structure information of a pixel to guide the network to focus more on local details.
HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS
The decoder part is inspired by the Cascaded Partial Decoder, known for fast and accurate salient object detection.
Reverse Attention for Salient Object Detection
ShuhanChen/RAS_ECCV18
•
•
ECCV 2018
Benefit from the quick development of deep learning techniques, salient object detection has achieved remarkable progresses recently.
