CINIC-10 is not ImageNet or CIFAR-10
arXiv:1810.03505
Abstract
In this brief technical report we introduce the CINIC-10 dataset as a plug-in extended alternative for CIFAR-10. It was compiled by combining CIFAR-10 with images selected and downsampled from the ImageNet database. We present the approach to compiling the dataset, illustrate the example images for different classes, give pixel distributions for each part of the repository, and give some standard benchmarks for well known models. Details for download, usage, and compilation can be found in the associated github repository.
Dataset compilation, 9 pages, 11 figures, technical report
Cited by in corpus (17)
- Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
- Neural Architecture Transfer
- SpinalNet: Deep Neural Network with Gradual Input
- FedICT: Federated Multi-task Distillation for Multi-access Edge Computing
- Federated Continual Learning: Concepts, Challenges, and Solutions
- What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
- Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework
- Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning
- FedGreen: Federated Learning with Fine-Grained Gradient Compression for Green Mobile Edge Computing
- KDk: A Defense Mechanism Against Label Inference Attacks in Vertical Federated Learning
- Activation Function Optimization Scheme for Image Classification
- Leveraging Angular Distributions for Improved Knowledge Distillation
- Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data
- Downstream-Pretext Domain Knowledge Traceback for Active Learning
- Adversarial attacks to image classification systems using evolutionary algorithms
- Aggregating Soft Labels from Crowd Annotations Improves Uncertainty Estimation Under Distribution Shift
- BadVFL: Backdoor Attacks in Vertical Federated Learning