Search Results for "benchmark"

...The iHarmony4 dataset comprises four sub-datasets (HCOCO, HAdobe5k, HFlickr, Hday2night), each making composite images by combining a foreground from one image with a background from another, along with associated ground truth harmonized images and foreground masks. The dataset is intended as a benchmark resource to enable and standardize research in image harmonization. Each composite sample has: composite image, foreground mask, and corresponding real harmonized image.

Evolutionary multi-objective optimization platform. PlatEMO consists of a number of MATLAB functions without using any other libraries. Any machines able to run MATLAB can use PlatEMO regardless of the operating system. PlatEMO includes more than ninety existing popular MOEAs, including genetic algorithm, differential evolution, particle swarm optimization, memetic algorithm, estimation of distribution algorithm, and surrogate model-based algorithm. Most of them are representative algorithms...

...It implements the architecture presented in the CVPR 2017 paper RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation and its extended version published in TPAMI 2019. The framework uses multi-path refinement and improved residual pooling to achieve high-quality segmentation results across multiple benchmark datasets. It provides trained models for datasets such as PASCAL VOC 2012, Cityscapes, NYUDv2, Person_Parts, PASCAL_Context, SUNRGBD, and ADE20k, with versions based on ResNet-101 and ResNet-152 backbones. The repository supports both single-scale and multi-scale prediction, with scripts for training, testing, and evaluating segmentation performance. ...

...The dataset provides both an image representation of each character and the time-ordered stroke coordinates ([x, y, t]) for each instance. Includes stroke data (time-sequenced coordinates) per sample. The repository is intended as a benchmark dataset in few-shot / meta-learning research, not as a plug-and-play detection or classification engine. Pre-split “background” and “evaluation” alphabets for standard benchmarking.

S³FD (Single Shot Scale-invariant Face Detector) is a real-time face detection framework designed to handle faces of various sizes with high accuracy using a single deep neural network. Developed by Shifeng Zhang, S³FD introduces a scale-compensation anchor matching strategy and enhanced detection architecture that makes it especially effective for detecting small faces—a long-standing challenge in face detection research. The project builds upon the SSD framework in Caffe, with...