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 26012625 of 10420 papers

TitleStatusHype
Certified Defenses against Adversarial ExamplesCode0
Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural NetworksCode0
Certification for Differentially Private Prediction in Gradient-Based TrainingCode0
Inception-inspired LSTM for Next-frame Video PredictionCode0
Improvising the Learning of Neural Networks on Hyperspherical ManifoldCode0
Center Smoothing: Certified Robustness for Networks with Structured OutputsCode0
An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine CompositesCode0
Cells are Actors: Social Network Analysis with Classical ML for SOTA Histology Image ClassificationCode0
Improving Transferability of Adversarial Examples with Input DiversityCode0
In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image ClassificationCode0
Cell image classification: a comparative overviewCode0
Improving the Gating Mechanism of Recurrent Neural NetworksCode0
Improving the repeatability of deep learning models with Monte Carlo dropoutCode0
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical EnergyCode0
CECT: Controllable Ensemble CNN and Transformer for COVID-19 Image ClassificationCode0
Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase SamplingCode0
Improving the Efficiency of Human-in-the-Loop Systems: Adding Artificial to Human ExpertsCode0
Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and RetrainingCode0
Multi-Label Noise Robust Collaborative Learning for Remote Sensing Image ClassificationCode0
Improving Random-Sampling Neural Architecture Search by Evolving the Proxy Search SpaceCode0
Improving Pairwise Ranking for Multi-label Image ClassificationCode0
Improving Pre-Trained Weights Through Meta-Heuristics Fine-TuningCode0
Anomaly Detection of Adversarial Examples using Class-conditional Generative Adversarial NetworksCode0
CBIR using features derived by Deep LearningCode0
Improving Nonlinear Projection Heads using Pretrained Autoencoder EmbeddingsCode0
Show:102550
← PrevPage 105 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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified