Tiny ImageNet

Dataset Card for tiny-imagenet Dataset Summary Tiny ImageNet contains 100000 images of 200 classes (500 for each class) downsized to 64×64 colored images. Each class has 500 training images, 50 validation images, and 50 test images. Languages The class labels in the dataset are in English. Dataset Structure Data Instan

Papers using Tiny ImageNet (7)

ADS-C: Antidistillation Sampling for Classification2026Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks2026RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance2026Enhancing All-to-X Backdoor Attacks with Optimized Target Class Mapping2025DOPA: Stealthy and Generalizable Backdoor Attacks from a Single Client under Challenging Federated Constraints2025Membership Inference Attack Using Self Influence Functions2022 · 3 citesAdvancing Adversarial Robustness Through Adversarial Logit Update2023