datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
COIN-collection
COIN collection dataset
This is the dataset for our paper "Predicting the Encoding Error of SIRENs". It consists of 300,000 small SIREN networks trained to encode images from the MSCOCO dataset.
We will publish a loading script for this dataset soon, but until then, see the following instructions:
How to Use
First, download this repository using:
huggingface-cli repo download predict-SIREN-PSNR/COIN-collection --repo_type datasets
There are two types of files in this… See the full description on the dataset page: https://huggingface.co/datasets/predict-SIREN-PSNR/COIN-collection.COinCO-resources
📦 COinCO-resources
This repository contains all necessary preprocessed resources and pretrained models required to run the code for the COinCO. It supports the following downstream tasks:
In- and out-of-context classification
Objects-from-Context Prediction
Context-empowered fake localization
📁 Repository Contents
After cloning, you will find the following files:
checkpoints.zip:Pretrained model checkpoints for downstream tasks such as context classification… See the full description on the dataset page: https://huggingface.co/datasets/COinCO/COinCO-resources.COinCO-dataset
🖼️ COinCO: Common Inpainted Objects In-N-Out of Context
Authors: Tianze Yang*, Tyson Jordan*, Ruitong Sun* Ninghao Liu, Jin Sun*Equal contributionAffiliation: University of GeorgiaStatus: Accepted to CVPR 2026
📦 1. Dataset Overview
The COinCO dataset is a large-scale benchmark constructed from the COCO dataset to study object-scene contextual relationships via inpainting. Each image in COinCO contains one inpainted object, and annotations are provided for… See the full description on the dataset page: https://huggingface.co/datasets/COinCO/COinCO-dataset.