482 datasets found

Semantic segmentation is one of the fundamental prob-lems in computer vision, whose task is to assign a seman-tic label to each pixel of an image so that different classes can...

NeRF [33] has demonstrated amazing ability to synthesize images of 3D scenes from novel views. However, they rely upon specialized volumetric rendering algorithms based on ray...

The COCO2017 dataset is used for the trainability experiment, which includes 47,429 images with 210,893 objects.

The COCO-Thing-Stuff dataset is used for the L2I task, which includes 118,287 training images and 5,000 validation images. Each image is annotated with bounding boxes and...

The CornerNet dataset is a single-stage object detection benchmark.

Grid R-CNN is a novel object detection framework that adopts a grid guided localisation mechanism for accurate object detection.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

The dataset used for training and validation of the proposed approach to combine semantic segmentation and dense outlier detection.

Instance segmentation (IS) is an important computer vision task, aiming at simultaneously predicting the class label and the binary mask for each instance of interest in an image.

The Cityscapes dataset is a large and famous city street scene semantic segmentation dataset. 19 classes of which 30 classes of this dataset are considered for training and...

The dataset used in the paper is the KITTI dataset, which is a benchmark for monocular depth estimation. The dataset consists of a large collection of images and corresponding...

The Microsoft COCO dataset was used for training and evaluating the CNNs because it has become a standard benchmark for testing algorithms aimed at scene understanding and...

A benchmark for low-shot recognition was proposed by Hariharan & Girshick (2017) and consists of a representation learning phase without access to the low-shot classes and a...

The dataset used for pedestrian detection, occlusion and body part relevance assessment.

The HRSC2016 dataset is a high resolution ship recognition dataset annotated with oriented bounding boxes which contains 1061 images, and the image size ranges from 300 × 300 to...

The DOTA dataset is a large aerial image dataset for oriented objects detection which contains 2806 images with the size ranges from 800 × 800 to 4000 × 4000 and 188282...

The KITTI 2015 dataset is a real-world dataset of street views, containing 200 training stereo image pairs with sparsely labeled disparity from LiDAR data.

Joint-DetNAS is a unified framework for object detection that jointly optimizes NAS, pruning, and dynamic distillation.

Transformer-based detectors (DETRs) are becoming popular for their simple framework, but the large model size and heavy time consumption hinder their deployment in the real world.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used it for language modeling and image classification tasks.