MNIST-Gen automatically builds MNIST-style datasets for user-defined categories using CLIP semantic scoring, reinforcement learning, and hierarchical category definitions, demonstrated on Tree-MNIST and Food-MNIST.
Fine-grained plant classification using convolutional neural networks for feature extraction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MNIST-Gen: A Modular MNIST-Style Dataset Generation Using Hierarchical Semantics, Reinforcement Learning, and Category Theory
MNIST-Gen automatically builds MNIST-style datasets for user-defined categories using CLIP semantic scoring, reinforcement learning, and hierarchical category definitions, demonstrated on Tree-MNIST and Food-MNIST.