ImageNet Dataset
ImageNet is a large-scale image dataset that has been instrumental in advancing the field of computer vision, primarily serving as a benchmark for evaluating the performance of image classification models. Current research focuses on improving model efficiency and accuracy through techniques like neural architecture search, network compression (e.g., using tropical geometry or pruning), and knowledge distillation, often employing architectures such as ResNets and Vision Transformers. The dataset's continued use in benchmarking and training contributes significantly to the development of more accurate, efficient, and robust computer vision systems with applications ranging from object recognition to medical image analysis.
Papers
Ensemble of Pre-Trained Neural Networks for Segmentation and Quality Detection of Transmission Electron Microscopy Images
Arun Baskaran, Yulin Lin, Jianguo Wen, Maria K. Y. Chan
A Principled Evaluation Protocol for Comparative Investigation of the Effectiveness of DNN Classification Models on Similar-but-non-identical Datasets
Esla Timothy Anzaku, Haohan Wang, Arnout Van Messem, Wesley De Neve