# The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop

arXiv: https://arxiv.org/abs/2106.01364 · HTML: https://mlsanity.com/paper/2106.01364/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 4 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 3 of 3)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification](https://mlsanity.com/paper/2104.00679/) (2021)
- [The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop](https://mlsanity.com/paper/2103.06937/) (2021)

## Built on by (most cited first, 16 of 16)

- [Class-Aware Contrastive Semi-Supervised Learning](https://mlsanity.com/paper/2203.02261/) (2022)
- [Prompting Scientific Names for Zero-Shot Species Recognition](https://mlsanity.com/paper/2310.09929/) (2023)
- [Continual Learning with Evolving Class Ontologies](https://mlsanity.com/paper/2210.04993/) (2022)
- [SimMatchV2: Semi-Supervised Learning with Graph Consistency](https://mlsanity.com/paper/2308.06692/) (2023)
- [Semi-Supervised Learning with Taxonomic Labels](https://mlsanity.com/paper/2111.11595/) (2021)
- [RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data](https://mlsanity.com/paper/2302.14483/) (2023)
- [Discriminative Class Tokens for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17155/) (2023)
- [Formal Abductive Latent Explanations for Prototype-Based Networks](https://mlsanity.com/paper/2511.16588/) (2025)
- [WikiChurches: A Fine-Grained Dataset of Architectural Styles with Real-World Challenges](https://mlsanity.com/paper/2108.06959/) (2021)
- [FATE: A Prompt-Tuning-Based Semi-Supervised Learning Framework for Extremely Limited Labeled Data](https://mlsanity.com/paper/2504.09828/) (2025)
- [LiT Tuned Models for Efficient Species Detection](https://mlsanity.com/paper/2302.10281/) (2023)
- [Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers](https://mlsanity.com/paper/2505.24443/) (2025)
- [BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition](https://mlsanity.com/paper/2107.06768/) (2021)
- [SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes](https://mlsanity.com/paper/2311.01646/) (2023)
- [PlantTraitNet: An Uncertainty-Aware Multimodal Framework for Global-Scale Plant Trait Inference from Citizen Science Data](https://mlsanity.com/paper/2511.06943/) (2025)
- [Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation](https://mlsanity.com/paper/2603.08364/) (2026)

## Abstract (arXiv)

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: urlhttps://github.com/cvl-umass/semi-inat-2021.