The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop
- URL: http://arxiv.org/abs/2106.01364v1
- Date: Wed, 2 Jun 2021 17:59:41 GMT
- Title: The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop
- Authors: Jong-Chyi Su and Subhransu Maji
- Abstract summary: Semi-iNat is a challenging dataset for semi-supervised classification with a long-tailed distribution of classes, fine-grained categories, and domain shifts between labeled and unlabeled data.
This dataset is behind the second iteration of the semi-supervised recognition challenge to be held at the FGVC8 workshop at CVPR 2021.
- Score: 42.02670649470055
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Semi-iNat is a challenging dataset for semi-supervised classification with a
long-tailed distribution of classes, fine-grained categories, and domain shifts
between labeled and unlabeled data. This dataset is behind the second iteration
of the semi-supervised recognition challenge to be held at the FGVC8 workshop
at CVPR 2021. Different from the previous one, this dataset (i) includes images
of species from different kingdoms in the natural taxonomy, (ii) is at a larger
scale --- with 810 in-class and 1629 out-of-class species for a total of 330k
images, and (iii) does not provide in/out-of-class labels, but provides coarse
taxonomic labels (kingdom and phylum) for the unlabeled images. This document
describes baseline results and the details of the dataset which is available
here: \url{https://github.com/cvl-umass/semi-inat-2021}.
Related papers
- A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect
Dataset [18.211840156134784]
This paper presents a curated million-image dataset, primarily to train computer-vision models capable of providing image-based taxonomic assessment.
The dataset also presents compelling characteristics, the study of which would be of interest to the broader machine learning community.
arXiv Detail & Related papers (2023-07-19T20:54:08Z) - Making Binary Classification from Multiple Unlabeled Datasets Almost
Free of Supervision [128.6645627461981]
We propose a new problem setting, i.e., binary classification from multiple unlabeled datasets with only one pairwise numerical relationship of class priors.
In MU-OPPO, we do not need the class priors for all unlabeled datasets.
We show that our framework brings smaller estimation errors of class priors and better performance of binary classification.
arXiv Detail & Related papers (2023-06-12T11:33:46Z) - Oracle-MNIST: a Realistic Image Dataset for Benchmarking Machine
Learning Algorithms [57.29464116557734]
We introduce the Oracle-MNIST dataset, comprising of 28$times $28 grayscale images of 30,222 ancient characters.
The training set totally consists of 27,222 images, and the test set contains 300 images per class.
arXiv Detail & Related papers (2022-05-19T09:57:45Z) - Generalized Category Discovery [148.32255950504182]
We consider a highly general image recognition setting wherein, given a labelled and unlabelled set of images, the task is to categorize all images in the unlabelled set.
Here, the unlabelled images may come from labelled classes or from novel ones.
We first establish strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task.
We then introduce a simple yet effective semi-supervised $k$-means method to cluster the unlabelled data into seen and unseen classes.
arXiv Detail & Related papers (2022-01-07T18:58:35Z) - Semi-Supervised Learning with Taxonomic Labels [42.02670649470055]
We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains.
On the Semi-iNat dataset consisting of 810 species across three Kingdoms, incorporating Phylum labels improves the Species level classification accuracy by 6%.
We propose a technique to select relevant data from a large collection of unlabeled images guided by the hierarchy which improves the robustness.
arXiv Detail & Related papers (2021-11-23T00:50:25Z) - A Strong Baseline for the VIPriors Data-Efficient Image Classification
Challenge [9.017660524497389]
We present a strong baseline for data-efficient image classification on the VIPriors challenge dataset.
Our baseline achieves 69.7% accuracy and outperforms 50% of submissions to the VIPriors 2021 challenge.
arXiv Detail & Related papers (2021-09-28T08:45:15Z) - The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop [42.02670649470055]
This document describes the details and the motivation behind a new dataset we collected for the semi-supervised recognition challengecitesemi-aves 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.
arXiv Detail & Related papers (2021-03-11T20:21:16Z) - Crop mapping from image time series: deep learning with multi-scale
label hierarchies [22.58506027920305]
We develop a crop classification method that exploits expert knowledge and significantly improves the mapping of rare crop types.
The three-level label hierarchy is encoded in a convolutional, recurrent neural network (convRNN)
We validate the proposed method on a new, large dataset that we make public.
arXiv Detail & Related papers (2021-02-17T15:27:49Z) - Background Splitting: Finding Rare Classes in a Sea of Background [55.03789745276442]
We focus on the real-world problem of training accurate deep models for image classification of a small number of rare categories.
In these scenarios, almost all images belong to the background category in the dataset (>95% of the dataset is background)
We demonstrate that both standard fine-tuning approaches and state-of-the-art approaches for training on imbalanced datasets do not produce accurate deep models in the presence of this extreme imbalance.
arXiv Detail & Related papers (2020-08-28T23:05:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.