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

March 26, 2022

On the Viability of Monocular Depth Pre-training for Semantic Segmentation
Dong Lao, Alex Wong, Samuel Lu, Stefano Soatto
Semantic Segmentation Pre Trained Supervised ImageNet Depth Estimation Monocular Depth Myocardial Viability Semantic Task

March 24, 2022

A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range
Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn
Supervised ImageNet Step Size Superior Optimizer Copy Suppression Adaptive Optimizers Analytic Calculus Crack AdaBoost Code Adaptive Stepsizes DNN Optimization

March 22, 2022

Self-supervision through Random Segments with Autoregressive Coding (RandSAC)
Tianyu Hua, Yonglong Tian, Sucheng Ren, Michalis Raptis, Hang Zhao, Leonid Sigal
Vision Transformer Supervised ImageNet Self Supervision Feature Representation Random Participation Skip Connection Autoregressive Coding

March 15, 2022

One Network Doesn't Rule Them All: Moving Beyond Handcrafted Architectures in Self-Supervised Learning
Sharath Girish, Debadeepta Dey, Neel Joshi, Vibhav Vineet, Shital Shah, Caio Cesar Teodoro Mendes, Abhinav Shrivastava, Yale Song
Self Supervised Learning Self Supervised Supervised ImageNet Network Programming Image Classification Benchmark

March 14, 2022

RecursiveMix: Mixed Learning with History
Lingfeng Yang, Xiang Li, Borui Zhao, Renjie Song, Jian Yang
Supervised ImageNet Historical Text Deep Vision Model Mixed Supervised Learning Downstream Object Detection

March 12, 2022

The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy
Tianlong Chen, Zhenyu Zhang, Yu Cheng, Ahmed Awadallah, Zhangyang Wang
Vision Transformer Supervised ImageNet Diversity Awareness General Principle Information Redundancy Different Level Traditional Convolutional Representation Diversity

March 11, 2022

The Role of ImageNet Classes in Fr\'echet Inception Distance
Tuomas Kynkäänniemi, Tero Karras, Miika Aittala, Timo Aila, Jaakko Lehtinen
Supervised ImageNet Integral Role Feature Space Inception Distance ImageNet Classification Data Driven Generative ImageNet Class

March 9, 2022

March 8, 2022

Evolutionary Neural Cascade Search across Supernetworks
Alexander Chebykin, Tanja Alderliesten, Peter A. N. Bosman
Neural Architecture Search Supervised ImageNet Neural Network Architecture Supernet Training Evolutionary Search Neural Architecture Transfer

March 7, 2022

Regularising for invariance to data augmentation improves supervised learning
Aleksander Botev, Matthias Bauer, Soham De
LeArning Abstract Data Augmentation Supervised ImageNet Alpha Invariance Explicit Regularization Regularization Property Augmentation Composition

March 6, 2022

Fidelity of Interpretability Methods and Perturbation Artifacts in Neural Networks
Lennart Brocki, Neo Christopher Chung
Neural Network Deep Neural Network Supervised ImageNet Interpretability Method Fidelity Reward Fidelity Metric Post Hoc Interpretability Perturbation Artifact

March 4, 2022

March 2, 2022

What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors
Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei, Magnus Söderberg, Kevin Smith
Transfer Learning Medical Image Supervised ImageNet Inductive Bias Medical Domain Feature Reuse

February 21, 2022

ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond
Qiming Zhang, Yufei Xu, Jing Zhang, Dacheng Tao
Vision Transformer Supervised ImageNet Inductive Bias Image Recognition Convolutional Block Baseline Transformer

February 18, 2022

Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
Mark Collier, Rodolphe Jenatton, Efi Kokiopoulou, Jesse Berent
Neural Network Supervised ImageNet Supervised Learning Label Noise Formality Transfer Privileged Information

February 17, 2022

Visual Ground Truth Construction as Faceted Classification
Fausto Giunchiglia, Mayukh Bagchi, Xiaolei Diao
Supervised ImageNet Ground Truth Hierarchical Classification Recognition Benchmark ImageNet Hierarchy

February 16, 2022

Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
Priya Goyal, Quentin Duval, Isaac Seessel, Mathilde Caron, Ishan Misra, Levent Sagun, Armand Joulin, Piotr Bojanowski
Self Supervised Learning Supervised ImageNet Vision Model Unlabeled Image Fine Grained Recognition Image Classification Datasets Supervised Classification

February 14, 2022

Orthogonalising gradients to speed up neural network optimisation
Mark Tuddenham, Adam Prügel-Bennett, Jonathan Hare
Neural Network Supervised ImageNet Natural Gradient Learned Representation Post Hoc Orthogonalization