<- Back to Datasets

FSS-1000

A 1000-Class Dataset for Few-Shot Segmentation

FSS-1000

Over the past few years, we have witnessed the success of deep learning in image recognition thanks to the availability of large-scale human-annotated datasets such as PASCAL VOC, ImageNet, and COCO. Although these datasets have covered a wide range of object categories, there are still a significant number of objects that are not included. Can we perform the same task without a lot of human annotations? In this paper, we are interested in few-shot object segmentation where the number of annotated training examples are limited to 5 only. To evaluate and validate the performance of our approach, we have built a few-shot segmentation dataset, FSS-1000, which consists of 1000 object classes with pixelwise annotation of ground-truth segmentation. Unique in FSS-1000, our dataset contains significant number of objects that have never been seen or annotated in previous datasets, such as tiny daily objects, merchandise, cartoon characters, logos, etc. We build our baseline model using standard backbone networks such as VGG-16, ResNet-101, and Inception.

View this Dataset
->
View author website
Task
Remote Sensing
Annotation Types
Semantic Segmentation
10000
Items
1000
Classes
10000
Labels
Models using this dataset
Last updated on 
January 20, 2022
Licensed under 
Research Only
Gain control of your training data
15,000+ ML engineers can’t be wrong