ImageNet Challenge

The ImageNet challenge, a large-scale visual object recognition competition, has significantly advanced the field of deep learning by driving the development and evaluation of image classification models. Current research focuses on improving model robustness against spurious correlations and biases in training data, often employing techniques like language-guided data augmentation and test-time augmentations such as zooming. This involves exploring various architectures, including convolutional neural networks and transformers, and optimizing training strategies for efficiency and accuracy across diverse hardware platforms. The challenge's impact extends to broader computer vision applications and continues to serve as a benchmark for evaluating progress in the field.

Papers

August 19, 2023

ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations
Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Sakshi Singh, Sanjoy Chowdhury, Dinesh Manocha
Language Model Native Robustness Data Augmentation Spurious Correlation Fake Image Image Domain Sensor Simulation ImageNet Challenge

April 11, 2023

ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
Mohammad Reza Taesiri, Giang Nguyen, Sarra Habchi, Cor-Paul Bezemer, Anh Nguyen
Image Classification Large Vision Language Model State of the Art Image Classifier Image Complexity ImageNet E ImageNet Challenge Spatial Bias

March 24, 2023

Mathematical Challenges in Deep Learning
Vahid Partovi Nia, Guojun Zhang, Ivan Kobyzev, Michael R. Metel, Xinlin Li, Ke Sun, Sobhan Hemati, Masoud Asgharian, Linglong Kong, Wulong Liu, Boxing Chen
Deep Learning Artificial Intelligence Autonomous Vehicle Deep Model ImageNet Challenge

January 17, 2023

DQNAS: Neural Architecture Search using Reinforcement Learning
Anshumaan Chauhan, Siddhartha Bhattacharyya, S. Vadivel
Reinforcement Learning Convolutional Neural Network Neural Architecture Search Neural Architecture ImageNet Challenge

September 2, 2022

Impact of Scaled Image on Robustness of Deep Neural Networks
Chengyin Hu, Weiwen Shi
Deep Neural Network Native Robustness Global Impact State of the Art Deep Large Scale ImageNet ImageNet Challenge Scaled Image

April 7, 2022

Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results
Tal Ridnik, Hussam Lawen, Emanuel Ben-Baruch, Asaf Noy
Supervised ImageNet Unified Framework CNN Model Computer Vision Model Key Result Backbone Fine Tuning Numerous Cutting Edge Backbone ImageNet Challenge

March 21, 2022

ImageNet Challenging Classification with the Raspberry Pi: An Incremental Local Stochastic Gradient Descent Algorithm
Thanh-Nghi Do
Raspberry Pi Parallel Stochastic ImageNet Challenge