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

November 24, 2023

ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification
Vasilis Siomos, Sergio Naval-Marimont, Jonathan Passerat-Palmbach, Giacomo Tarroni
Supervised ImageNet New Initialization Architecture Perspective Normalization Layer Federated Image Classification Medical Image Classification Task Diva 360

November 22, 2023

Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend
McKell Woodland, Austin Castelo, Mais Al Taie, Jessica Albuquerque Marques Silva, Mohamed Eltaher, Frank Mohn, Alexander Shieh, Suprateek Kundu, Joshua P. Yung, Ankit B. Patel, Kristy K. Brock
Medical Image Supervised ImageNet Synthetic Image Feature Extraction Recent Trend Inception Distance Pre Trained Feature Extractor Medical Generative

November 16, 2023

Overcoming Data Scarcity in Biomedical Imaging with a Foundational Multi-Task Model
Raphael Schäfer, Till Nicke, Henning Höfener, Annkristin Lange, Dorit Merhof, Friedrich Feuerhake, Volkmar Schulz, Johannes Lotz, Fabian Kiessling
Foundation Model Supervised ImageNet Multi Task Medical Imaging Data Scarcity Pretrained Model Image Analysis Validation

November 15, 2023

November 14, 2023

Introducing an Improved Information-Theoretic Measure of Predictive Uncertainty
Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi, Sepp Hochreiter
Machine Learning Model Supervised ImageNet Predictive Uncertainty Predictive Distribution Bayesian Model Averaging Information Theoretic Measure

November 13, 2023

Automated Classification of Model Errors on ImageNet
Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin Vechev
Computer Vision Supervised ImageNet ImageNet Dataset Classification Error Automatic Classification Error Classification Model Error

November 9, 2023

Are "Hierarchical" Visual Representations Hierarchical?
Ethan Shen, Ali Farhadi, Aditya Kusupati
Supervised ImageNet Visual Representation Hierarchical Representation Visual Imagery

November 8, 2023

SODAWideNet -- Salient Object Detection with an Attention augmented Wide Encoder Decoder network without ImageNet pre-training
Rohit Venkata Sai Dulam, Chandra Kambhamettu
Supervised ImageNet Human Attention Receptive Field SALient Object Detection Wide Neural Network Multi Scale Attention

November 7, 2023

Random Field Augmentations for Self-Supervised Representation Learning
Philip Andrew Mansfield, Arash Afkanpour, Warren Richard Morningstar, Karan Singhal
Supervised ImageNet Self Supervised Representation Learning Learned Representation Image Augmentation Random Field Random Augmentation

November 3, 2023

A Simple and Efficient Baseline for Data Attribution on Images
Vasu Singla, Pedro Sandoval-Segura, Micah Goldblum, Jonas Geiping, Tom Goldstein
Self Supervised Learning Supervised ImageNet Large Model Data Attribution Efficient Baseline

November 2, 2023

Scattering Vision Transformer: Spectral Mixing Matters
Badri N. Patro, Vijay Srinivas Agneeswaran
Vision Transformer Supervised ImageNet Vision Task Scattering Network Spectral Mixture

October 30, 2023

October 28, 2023

Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness
Soumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi, Zachariah Carmichael, Vineet Gundecha, Sahand Ghorbanpour, Ricardo Luna, Gutierrez Antonio Guillen, Avisek Naug
Supervised ImageNet Adversarial Sample Distortion Aware Image Classifier Image Classification Model Adversarial Benchmark

October 25, 2023

ConvNets Match Vision Transformers at Scale
Samuel L. Smith, Andrew Brock, Leonard Berrada, Soham De
Vision Transformer Supervised ImageNet Visual Analogue Scale High Performing 1D ConvNet nnU Net Performant Neural Network

October 24, 2023

Supervised ImageNet

Papers

ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification

Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend

Overcoming Data Scarcity in Biomedical Imaging with a Foundational Multi-Task Model

MoCo-Transfer: Investigating out-of-distribution contrastive learning for limited-data domains

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy

Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations

Introducing an Improved Information-Theoretic Measure of Predictive Uncertainty

Automated Classification of Model Errors on ImageNet

Are "Hierarchical" Visual Representations Hierarchical?

SODAWideNet -- Salient Object Detection with an Attention augmented Wide Encoder Decoder network without ImageNet pre-training

Random Field Augmentations for Self-Supervised Representation Learning

A Simple and Efficient Baseline for Data Attribution on Images

Scattering Vision Transformer: Spectral Mixing Matters

Addressing Weak Decision Boundaries in Image Classification by Leveraging Web Search and Generative Models

Are Natural Domain Foundation Models Useful for Medical Image Classification?

Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learning

Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness

ConvNets Match Vision Transformers at Scale

Yin Yang Convolutional Nets: Image Manifold Extraction by the Analysis of Opposites

Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data