Dichotomous Image Segmentation
22 papers with code • 6 benchmarks • 2 datasets
Currently, existing image segmentation tasks mainly focus on segmenting objects with specific characteristics, e.g., salient, camouflaged, meticulous, or specific categories. Most of them have the same input/output formats, and barely use exclusive mechanisms designed for segmenting targets in their models, which means almost all tasks are dataset-dependent. Thus, it is very promising to formulate a category-agnostic DIS task for accurately segmenting objects with different structure complexities, regardless of their characteristics. Compared with semantic segmentation, the proposed DIS task usually focuses on images with single or a few targets, from which getting richer accurate details of each target is more feasible.
Libraries
Use these libraries to find Dichotomous Image Segmentation models and implementations
STARE
DIS5K
Most implemented papers
U-Net: Convolutional Networks for Biomedical Image Segmentation
labmlai/annotated_deep_learning_paper_implementations
•
•
There is large consent that successful training of deep networks requires many thousand annotated training samples.
Rethinking Atrous Convolution for Semantic Image Segmentation
To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates.
Pyramid Scene Parsing Network
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
Searching for MobileNetV3
tensorflow/models
•
•
ICCV 2019
We achieve new state of the art results for mobile classification, detection and segmentation.
Deep High-Resolution Representation Learning for Visual Recognition
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
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).
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
PaddlePaddle/PaddleSeg
•
•
ECCV 2018
Semantic segmentation requires both rich spatial information and sizeable receptive field.
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
We focus on the challenging task of real-time semantic segmentation in this paper.
Rethinking BiSeNet For Real-time Semantic Segmentation
MichaelFan01/STDC-Seg
•
•
CVPR 2021
BiSeNet has been proved to be a popular two-stream network for real-time segmentation.
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.
