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 1012610150 of 10420 papers

TitleStatusHype
FireCaffe: near-linear acceleration of deep neural network training on compute clusters0
Spiking Deep Networks with LIF NeuronsCode0
Aggregating Deep Convolutional Features for Image RetrievalCode0
How Important is Weight Symmetry in Backpropagation?Code1
Layer-Specific Adaptive Learning Rates for Deep Networks0
Deep convolutional neural networks for pedestrian detectionCode0
DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer0
Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks0
Relaxed Multiple-Instance SVM with Application to Object Discovery0
Cross-convolutional-layer Pooling for Image Recognition0
Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks0
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and TreeCode0
Mapping Generative Models onto a Network of Digital Spiking Neurons0
Learning Wake-Sleep Recurrent Attention Models0
Tensorizing Neural NetworksCode0
Evaluating the visualization of what a Deep Neural Network has learnedCode1
Medical Image Classification via SVM using LBP Features from Saliency-Based Folded Data0
Model Accuracy and Runtime Tradeoff in Distributed Deep Learning:A Systematic StudyCode0
Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks0
DeepSat - A Learning framework for Satellite ImageryCode0
Deep Attributes from Context-Aware Regional Neural Codes0
Image Classification with Rejection using Contextual Information0
Computational Integration of Human Vision and Natural Language through Bitext Alignment0
Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification0
Fisher Vectors Meet Neural Networks: A Hybrid Classification Architecture0
Show:102550
← PrevPage 406 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