FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation

07/29/2019
by   Tianhan Wei, et al.
4

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. To our surprise, we found that training our model from scratch using FSS-1000 achieves comparable and even better results than training with weights pre-trained by ImageNet which is more than 100 times larger than FSS-1000. Both our approach and dataset are simple, effective, and easily extensible to learn segmentation of new object classes given very few annotated training examples. Dataset is available at https://github.com/HKUSTCV/FSS-1000.

READ FULL TEXT

page 3

page 4

page 6

page 7

page 8

research
08/06/2019

Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector

Conventional methods for object detection usually requires substantial a...
research
04/06/2020

Objectness-Aware One-Shot Semantic Segmentation

While deep convolutional neural networks have led to great progress in i...
research
08/06/2018

Visual Question Generation for Class Acquisition of Unknown Objects

Traditional image recognition methods only consider objects belonging to...
research
10/19/2018

ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch

Current state-of-the-art object objectors are fine-tuned from the off-th...
research
12/02/2021

PartImageNet: A Large, High-Quality Dataset of Parts

A part-based object understanding facilitates efficient compositional le...
research
07/17/2020

Impact of base dataset design on few-shot image classification

The quality and generality of deep image features is crucially determine...
research
09/28/2022

Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks

Visual tasks vary a lot in their output formats and concerned contents, ...

Please sign up or login with your details

Forgot password? Click here to reset