The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop

03/11/2021
by   Jong-Chyi Su, et al.
9

This document describes the details and the motivation behind a new dataset we collected for the semi-supervised recognition challenge <cit.> at the FGVC7 workshop at CVPR 2020. The dataset contains 1000 species of birds sampled from the iNat-2018 dataset for a total of nearly 150k images. From this collection, we sample a subset of classes and their labels, while adding the images from the remaining classes to the unlabeled set of images. The presence of out-of-domain data (novel classes), high class-imbalance, and fine-grained similarity between classes poses significant challenges for existing semi-supervised recognition techniques in the literature. The dataset is available here: <https://github.com/cvl-umass/semi-inat-2020>

READ FULL TEXT

page 1

page 2

research
06/02/2021

The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop

Semi-iNat is a challenging dataset for semi-supervised classification wi...
research
11/23/2021

Semi-Supervised Learning with Taxonomic Labels

We propose techniques to incorporate coarse taxonomic labels to train im...
research
08/08/2019

iCassava 2019Fine-Grained Visual Categorization Challenge

Viral diseases are major sources of poor yields for cassava, the 2nd lar...
research
08/17/2022

How does the degree of novelty impacts semi-supervised representation learning for novel class retrieval?

Supervised representation learning with deep networks tends to overfit t...
research
06/01/2021

Cleaning and Structuring the Label Space of the iMet Collection 2020

The iMet 2020 dataset is a valuable resource in the space of fine-graine...
research
12/06/2021

Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data

Despite great strides made on fine-grained visual classification (FGVC),...
research
08/20/2020

ImagiFilter: A resource to enable the semi-automatic mining of images at scale

Datasets (semi-)automatically collected from the web can easily scale to...

Please sign up or login with your details

Forgot password? Click here to reset