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 93019325 of 10420 papers

TitleStatusHype
Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural NetworksCode0
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy LabelsCode1
Wavelet Convolutional Neural NetworksCode1
Deep Predictive Coding Network with Local Recurrent Processing for Object RecognitionCode0
Adversarial Structure Matching for Structured Prediction TasksCode0
Neural Network Compression using Transform Coding and Clustering0
Progressive Ensemble Networks for Zero-Shot Recognition0
Image Classification Based on Quantum KNN Algorithm0
Optical Neural Networks0
Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students0
Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks0
Energy Efficient Hadamard Neural Networks0
Improving Predictive Uncertainty Estimation using Dropout -- Hamiltonian Monte Carlo0
Born Again Neural NetworksCode0
Adaptive Selection of Deep Learning Models on Embedded Systems0
Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model0
Ensemble Soft-Margin Softmax Loss for Image Classification0
Dense and Diverse Capsule Networks: Making the Capsules Learn BetterCode0
Laconic Deep Learning Computing0
Learning to Teach0
Anchor Cascade for Efficient Face Detection0
Evaluating ResNeXt Model Architecture for Image ClassificationCode0
Robust Classification with Convolutional Prototype LearningCode1
A Performance Evaluation of Convolutional Neural Networks for Face Anti Spoofing0
Enhancing the Regularization Effect of Weight Pruning in Artificial Neural Networks0
Show:102550
← PrevPage 373 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
10RevCol-HTop 1 Accuracy90Unverified