SOTAVerified

Image Classification

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Papers

Showing 85768600 of 10420 papers

TitleStatusHype
Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network RobustnessCode0
Variational Resampling Based Assessment of Deep Neural Networks under Distribution ShiftCode0
Unsupervised Feature Learning with K-means and An Ensemble of Deep Convolutional Neural Networks for Medical Image Classification0
TensorNetwork for Machine LearningCode0
StyleNAS: An Empirical Study of Neural Architecture Search to Uncover Surprisingly Fast End-to-End Universal Style Transfer Networks0
Should Adversarial Attacks Use Pixel p-Norm?0
Bad Global Minima Exist and SGD Can Reach ThemCode0
Iterative Self-Learning: Semi-Supervised Improvement to Dataset Volumes and Model Accuracy0
Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP0
Robust Attacks against Multiple ClassifiersCode0
PI-Net: A Deep Learning Approach to Extract Topological Persistence ImagesCode0
Collage Inference: Achieving low tail latency during distributed image classification using coded redundancy models0
c-Eval: A Unified Metric to Evaluate Feature-based Explanations via Perturbation0
Multi-way Encoding for Robustness0
Visual Confusion Label Tree For Image Classification0
Visual Tree Convolutional Neural Network in Image Classification0
Embedded hyper-parameter tuning by Simulated AnnealingCode0
Information Competing Process for Learning Diversified RepresentationsCode0
Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge IntelligenceCode0
An Introduction to Deep Morphological Networks0
Geo-Aware Networks for Fine-Grained RecognitionCode0
Deeply-supervised Knowledge SynergyCode0
Achieving Generalizable Robustness of Deep Neural Networks by Stability Training0
Hierarchical Auxiliary Learning0
Learning Representations by Maximizing Mutual Information Across ViewsCode0
Show:102550
← PrevPage 344 of 417Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94Unverified
4DaViT-GTop 1 Accuracy90.4Unverified
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified