Imagenet Transfer

Imagenet transfer learning leverages pre-trained models, initially trained on the massive ImageNet dataset, to improve performance on diverse downstream tasks with limited data. Current research explores the effectiveness of this approach across various architectures (including CNNs, Vision Transformers, and even quantum neural networks), focusing on factors like model robustness, sparsity, and the impact of data augmentation strategies. This technique significantly accelerates development and improves accuracy in applications ranging from medical image analysis (e.g., seizure detection) and remote sensing (e.g., forest mapping) to industrial processes (e.g., material classification), demonstrating its broad utility across scientific domains.

Papers

September 28, 2023

Nondestructive chicken egg fertility detection using CNN-transfer learning algorithms
Shoffan Saifullah, Rafal Drezewski, Anton Yudhana, Andri Pranolo, Wilis Kaswijanti, Andiko Putro Suryotomo, Seno Aji Putra, Alin Khaliduzzaman, Anton Satria Prabuwono, Nathalie Japkowicz
Transfer Learning Practical Algorithm Precision Livestock Farming Chicken Egg Imagenet Transfer

August 9, 2023

Deep Learning Model Transfer in Forest Mapping using Multi-source Satellite SAR and Optical Images
Shaojia Ge, Oleg Antropov, Tuomas Häme, Ronald E. McRoberts, Jukka Miettinen
Transfer Learning Optical Imaging Model Transfer Forest Mapping Deep Regression Forest Imagenet Transfer Forest Structure

January 11, 2023

Does progress on ImageNet transfer to real-world datasets?
Alex Fang, Simon Kornblith, Ludwig Schmidt
Pre Trained Model Supervised ImageNet Real World Datasets Image Classification Datasets ImageNet Accuracy Imagenet Transfer

January 4, 2023

GUAP: Graph Universal Attack Through Adversarial Patching
Xiao Zang, Jie Chen, Bo Yuan
Adversarial Attack Graph Attention Network Adversarial Patch Attack Performance Graph Adversarial Attack Imagenet Transfer

October 18, 2022

Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material Classification
Prakash Chandra Chhipa, Richa Upadhyay, Rajkumar Saini, Lars Lindqvist, Richard Nordenskjold, Seiichi Uchida, Marcus Liwicki
Self Supervised Learning Self Supervised Representation Efficient Representation Depth Feature Imagenet Transfer

August 31, 2022

Classical-to-quantum convolutional neural network transfer learning
Juhyeon Kim, Joonsuk Huh, Daniel K. Park
Quantum Circuit Quantum Convolutional Neural Network Quantum Transfer Learning Imagenet Transfer Quantum Convolution Quantum Classical Convolutional Neural Network

April 8, 2022

Does Robustness on ImageNet Transfer to Downstream Tasks?
Yutaro Yamada, Mayu Otani
Vision Transformer Native Robustness Supervised ImageNet Downstream Task ImageNet Accuracy Imagenet Transfer

February 16, 2022

Low Latency Real-Time Seizure Detection Using Transfer Deep Learning
Vahid Khalkhali, Nabila Shawki, Vinit Shah, Meysam Golmohammadi, Iyad Obeid, Joseph Picone
Deep Learning Seizure Detection Imagenet Transfer Temple University Hospital Scalp EEG

November 26, 2021

How Well Do Sparse Imagenet Models Transfer?
Eugenia Iofinova, Alexandra Peste, Mark Kurtz, Dan Alistarh
Convolutional Neural Network Transfer Learning Pruning Method Imagenet Transfer