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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 8601–8625 of 10420 papers

TitleStatusHype
Geometry aware convolutional filters for omnidirectional images representation—0
Multi-way Encoding for Robustness to Adversarial Attacks—0
signSGD via Zeroth-Order Oracle—0
Select Via Proxy: Efficient Data Selection For Training Deep Networks—0
Sufficient Conditions for Robustness to Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networks—0
How Training Data Affect the Accuracy and Robustness of Neural Networks for Image Classification—0
Optimal Attacks against Multiple Classifiers—0
Deep Transfer Learning for Few-Shot SAR Image Classification—0
Harmonic Networks with Limited Training SamplesCode1
PR Product: A Substitute for Inner Product in Neural NetworksCode0
Test Selection for Deep Learning Systems—0
Unsupervised Data Augmentation for Consistency TrainingCode1
Self-Attention Capsule Networks for Object Classification—0
HOG feature extraction from encrypted images for privacy-preserving machine learning—0
Domain Agnostic Learning with Disentangled RepresentationsCode0
Forget the Learning Rate, Decay Loss—0
Collage Inference: Using Coded Redundancy for Low Variance Distributed Image Classification—0
Analysis of Confident-Classifiers for Out-of-distribution DetectionCode0
Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of ResourcesCode0
Transformers with convolutional context for ASRCode1
Unsupervised Label Noise Modeling and Loss CorrectionCode0
Unsupervised Deep Learning by Neighbourhood DiscoveryCode0
Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers—0
Learning Discriminative Features Via Weights-biased Softmax Loss—0
Making Convolutional Networks Shift-Invariant AgainCode1
Show:102550
← PrevPage 345 of 417Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified