Tiny ImageNet Challenge

By Jiayu Wu, Qixiang Zhang, Guoxia Xu. 2017

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connector (2021, neutral): “TinyIm-ageNet [39] contains 120,000 images of 200 classes.”
Training Networks in Null Space of Feature Covariance for Continual Learning (2021, methodology): “25-split-TinyImageNet is constructed by splitting TinyImageNet [50] containing 64 × 64 RGB images into 25 tasks, which is a harder setting due to longer sequence.”
Falcon: Honest-Majority Maliciously Secure Framework for Private Deep Learning (2020, methodology): “This extensive support makes F ALCON expressive, thereby supporting evaluation of large networks with hundreds of millions parameters such as VGG16 [14] and AlexNet [15] over datasets such as MNIST [16], CIFAR-10 [17] as well as Tiny ImageNet [18] including in both the LAN and WAN network settings.”
Continuous-in-Depth Neural Networks (2020, result): “(In Appendix B, we show similar results for Tiny ImageNet [76].)”
Gabor Convolutional Networks (2017, background): “This subset is also applied in [36], [37].”
Elastic Feature Consolidation for Cold Start Exemplar-free Incremental Learning (2024, methodology): “For Tiny-ImageNet, both the 10-step and 20-step scenarios use a large first task consisting of 100 classes.”
Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification (2019, methodology): “, natural and bio-medical images) of datasets like CIFAR-10 and CIFAR-100 [18], Tiny ImageNet [21], and CRCHistoPhenotypes [22].”