71 datasets found

Instance segmentation is a promising yet challenging topic in computer vision. Recent approaches such as Mask R-CNN typically divide this problem into two parts – a detection...

The iShape dataset is a dataset for irregular shape instance segmentation.

The dataset used in this paper for training and testing the KAISA optimizer framework.

LVIS is a large-vocabulary object detection and instance segmentation dataset.

The dataset used in the paper is ImageNet-1K and MS COCO.

The COCO-LT dataset is a long-tail version of the COCO dataset.

Real-time 3D object reconstruction pipeline based on streamed instance segmented data

The COCO test-dev dataset is used for instance segmentation. It contains 20k test-dev images.

Where are the blobs: Counting by localization with point supervision.

A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These labels require large human effort and for...

A large dataset of images of underwater trash collected from a variety of sources, annotated with bounding boxes and segmentation labels.

Multi-class histopathology nuclei analysis tasks, the lack of training data becomes a main bottleneck for the performance of learning-based methods.

Vehicle detection in real-time is a challenging and important task. The existing real-time vehicle detection lacks accuracy and speed. Real-time systems must detect and locate...

Instance segmentation dataset for VIPriors workshop at ICCV 2021

Semantic segmentation is a crucial and challenging task for image understanding. It aims to predict a dense labeling map for the input image, which assigns each pixel a unique...

Object detection is one of the most foundational computer vision task and is essential for many real-world applications. The object detection pipeline has been developed...

A hierarchical surgical tool dataset for evaluating deep learning techniques.

A novel dataset designed for recognizing and categorizing surgical instruments.

YOLACT++ is an improved version of YOLACT.

Real-time instance segmentation framework termed OrienMask is proposed, which integrates discriminative orientation maps with an anchor-based detector.