Saliency Detection
130 papers with code • 7 benchmarks • 13 datasets
Saliency Detection is a preprocessing step in computer vision which aims at finding salient objects in an image.
Source: An Unsupervised Game-Theoretic Approach to Saliency Detection
Benchmarks
These leaderboards are used to track progress in Saliency Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Saliency Detection models and implementations
PASCAL Context
PASCAL-S
DUTS
HKU-IS
DUT-OMRON
iSUN
CAT2000
ECSSD
ReDWeb-S
Lytro Illum
Subtasks
Latest papers with no code
All in One: RGB, RGB-D, and RGB-T Salient Object Detection
We propose an innovative model framework that provides a unified solution for the salient object detection task of three types of data (RGB, RGB-D, and RGB-T).
Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReID
While deep learning has significantly improved ReID model accuracy under the independent and identical distribution (IID) assumption, it has also become clear that such models degrade notably when applied to an unseen novel domain due to unpredictable/unknown domain shift.
Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context
Unsupervised salient object detection aims to detect salient objects without using supervision signals eliminating the tedious task of manually labeling salient objects.
Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects
To this end, we develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure.
Multi-Modal Hybrid Learning and Sequential Training for RGB-T Saliency Detection
To address this, we first propose a Multi-Modal Hybrid loss (MMHL) that comprises supervised and self-supervised loss functions.
Visual Saliency Detection in Advanced Driver Assistance Systems
A dedicated 1D temporal deep convolutional network has been devised to classify the collected PPG time-series, enabling us to assess the driver level of attentiveness.
Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation
Specifically, we employ an asymmetric encoder to learn the compensating features of the RGB and the thermal images.
Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition
Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision.
Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings
Human sketch has already proved its worth in various visual understanding tasks (e. g., retrieval, segmentation, image-captioning, etc).
Spectrum-inspired Low-light Image Translation for Saliency Detection
Saliency detection methods are central to several real-world applications such as robot navigation and satellite imagery.
