Image Processing

To investigate SAM's potential in the continual scenario, we construct a benchmark for continual segmentation, called Continual SAM Adaptation Benchmark (CoSAM), which aims to systematically evaluate SAM-related algorithms's performance in the streaming scenarios. Specifically, CoSAM offers a set of 8 tasks covering diverse domains, including industrial defects, medical imaging, and camouflaged objects, to serve as a realistic and effective benchmark for evaluating current methods.
- Categories:
The UQTR dataset consists of 7838 real and synthetic images of the Université du Québec à Trois-Rivières (UQTR) campus road under normal and snow conditions. The image resolution is 1280×720. It includes lane labels in .txt files, where each row stores the set of points of a lane. The points are stored as x1 y1 x2 y2, as in the tutorial by Ruijin Liu, Zejian Yuan, Tie Liu, Zhiliang Xiong: Train and Test Your Custom Data.
- Categories:

Shape completion remains a fundamental challenge in computer vision and image processing, particularly for tasks involving hand-drawn sketches and occluded objects. Traditional deep learning methods such as Generative Adversarial Networks (GANs) and Convolutional Neural Networks (CNNs) often suffer from high computational costs and poor generalization on sparse, abstract structures.
- Categories:

<p>ImageNet is a large-scale visual database widely used in the field of computer vision, especially for object recognition tasks. It contains millions of labeled images, organized into multiple categories, and is used for training and evaluating image classification models. ImageNet datasets are widely used for training deep learning models, particularly Convolutional Neural Networks (CNNs). ILSVRC2012 (ImageNet Large Scale Visual Recognition Challenge 2012) is a part of ImageNet and is a competition for image classification and object detection.
- Categories:

ImageNet is a large-scale visual database widely used in the field of computer vision, especially for object recognition tasks. It contains millions of labeled images, organized into multiple categories, and is used for training and evaluating image classification models. ImageNet datasets are widely used for training deep learning models, particularly Convolutional Neural Networks (CNNs).
- Categories:

<p>ImageNet is a large-scale visual database widely used in the field of computer vision, especially for object recognition tasks. It contains millions of labeled images, organized into multiple categories, and is used for training and evaluating image classification models. ImageNet datasets are widely used for training deep learning models, particularly Convolutional Neural Networks (CNNs). ILSVRC2012 (ImageNet Large Scale Visual Recognition Challenge 2012) is a part of ImageNet and is a competition for image classification and object detection.
- Categories:
This dataset comprises 32-bit floating-point SAR images in TIFF format, capturing coastal regions. It includes corresponding ground truth masks that differentiate between land and water areas. The covered regions include the Netherlands, London, Ireland, Spain, France, Lisbon, the USA, India, Africa, and Italy. The SAR images were acquired in Interferometric Wide (IW) mode with dual polarization at a spatial resolution of 10m × 10m.
- Categories:

Sample dataset of a freehand 3D ultrafast Doppler scan acquired during brain tumor resection surgery. The dataset includes the beamformed ultrasound images, as well as the simultaneously acquired optical tracking data, describing the position of the ultrasound probe in space.
- Categories:
The TUROS-TS encompasses 5,357 Google Street View images with 8,775 traffic sign instances covering 9 categories and 28 classes. Three subsets of the dataset were created: test (10%-1050 images 579), validation (20% -1050 images), and training (70% - 3728 images). It is available upon request. If you want to train and test the data set. Please send an email to afef.zwidi@regim.usf.tn
- Categories: