Supervised ImageNet

Supervised ImageNet research focuses on improving image classification models by leveraging the massive ImageNet dataset. Current efforts concentrate on enhancing data curation strategies, developing more efficient training methods (including exploring alternative architectures like binary neural networks and leveraging self-supervised learning), and addressing challenges like dataset bias and the need for explainable AI. These advancements are crucial for improving the accuracy, efficiency, and trustworthiness of computer vision systems across various applications, from medical imaging to agricultural technology.

Papers

January 13, 2022

Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
Self Supervised Learning Supervised ImageNet Continuum Limit Label Information Self Supervised Vision Transformer ResNet Based Self Supervised Representation

January 12, 2022

BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations
Daiqing Li, Huan Ling, Seung Wook Kim, Karsten Kreis, Adela Barriuso, Sanja Fidler, Antonio Torralba
Generative Adversarial Network Supervised ImageNet Pixel Level Annotation Conditional GANs

January 5, 2022

Problem-dependent attention and effort in neural networks with applications to image resolution and model selection
Chris Rohlfs
Neural Network Image Classification Supervised ImageNet Model Selection Attention Based Ensemble Approach Manual Effort Image Resolution Ensemble Based

January 1, 2022

Turath-150K: Image Database of Arab Heritage
Dani Kiyasseh, Rasheed El-Bouri
Supervised ImageNet MAESTRO Dataset Diverse Image Arabic Language Image Database

December 31, 2021

PCACE: A Statistical Approach to Ranking Neurons for CNN Interpretability
Sílvia Casacuberta, Esra Suel, Seth Flaxman
Convolutional Neural Network Inherent Interpretability Supervised ImageNet Deep Learning Architecture Convolution Layer Statistical Approach Neuron Importance

December 30, 2021

Towards Robustness of Neural Networks
Steven Basart
Neural Network Native Robustness Supervised ImageNet Segmentation Task Robust Representation ImageNet E

December 22, 2021

Improved skin lesion recognition by a Self-Supervised Curricular Deep Learning approach
Kirill Sirotkin, Marcos Escudero-Viñolo, Pablo Carballeira, Juan Carlos SanMiguel
Pre Trained Supervised ImageNet Curriculum Learning Skin Lesion Self Supervised Pretext Task

December 21, 2021

Improving Robustness with Image Filtering
Matteo Terzi, Mattia Carletti, Gian Antonio Susto
Native Robustness Adversarial Training Adversarial Robustness Supervised ImageNet Image Filtering Graph Extraction

December 20, 2021

Are Large-scale Datasets Necessary for Self-Supervised Pre-training?
Alaaeldin El-Nouby, Gautier Izacard, Hugo Touvron, Ivan Laptev, Hervé Jegou, Edouard Grave
Self Supervised Supervised ImageNet Supervised Autoencoder Pre Training Self Supervised Pre Training Large Scale Datasets

December 17, 2021

Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation
Bichen Wu, Ruizhe Cheng, Peizhao Zhang, Tianren Gao, Peter Vajda, Joseph E. Gonzalez
Zero Shot Supervised ImageNet Image Text Pair Text Encoder Image Text Matching Optimal Transport Distillation

December 16, 2021

Masked Feature Prediction for Self-Supervised Visual Pre-Training
Chen Wei, Haoqi Fan, Saining Xie, Chao-Yuan Wu, Alan Yuille, Christoph Feichtenhofer
Supervised ImageNet Self Supervised Pre Training Visual Recognition Masked Prediction Contrast Adaptation

December 10, 2021

December 5, 2021

Dynamic Token Normalization Improves Vision Transformers
Wenqi Shao, Yixiao Ge, Zhaoyang Zhang, Xuyuan Xu, Xiaogang Wang, Ying Shan, Ping Luo
Vision Transformer Supervised ImageNet Layer Normalization Various Vision Transformer

December 2, 2021

December 1, 2021

The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
Yuki M. Asano, Aaqib Saeed
Neural Network Supervised ImageNet Single Image Natural Image Visual Imagery Image Prior Visual Based Class

Supervised ImageNet

Papers

Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?

BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations

Problem-dependent attention and effort in neural networks with applications to image resolution and model selection

Turath-150K: Image Database of Arab Heritage

PCACE: A Statistical Approach to Ranking Neurons for CNN Interpretability

Towards Robustness of Neural Networks

Improved skin lesion recognition by a Self-Supervised Curricular Deep Learning approach

Improving Robustness with Image Filtering

Are Large-scale Datasets Necessary for Self-Supervised Pre-training?

Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation

Masked Feature Prediction for Self-Supervised Visual Pre-Training

CPPE-5: Medical Personal Protective Equipment Dataset

An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network

A Comparative Analysis of Machine Learning Approaches for Automated Face Mask Detection During COVID-19

Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks

Tradeoffs Between Contrastive and Supervised Learning: An Empirical Study

Dynamic Token Normalization Improves Vision Transformers

N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras

Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency

The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image