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 99019925 of 10420 papers

TitleStatusHype
Improving training of deep neural networks via Singular Value Bounding0
Expert Gate: Lifelong Learning with a Network of ExpertsCode0
Generalized BackPropagation, Étude De Cas: Orthogonality0
Inverting The Generator Of A Generative Adversarial Network0
Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization0
PolyNet: A Pursuit of Structural Diversity in Very Deep NetworksCode0
Image Credibility Analysis with Effective Domain Transferred Deep Networks0
S3Pool: Pooling with Stochastic Spatial SamplingCode0
Deep Transfer Learning for Person Re-identification0
Aggregated Residual Transformations for Deep Neural NetworksCode1
Constrained Low-Rank Learning Using Least Squares-Based Regularization0
Automatic discovery of discriminative parts as a quadratic assignment problem0
Selfie Detection by Synergy-Constraint Based Convolutional Neural Network0
Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes0
Adaptive Deep Pyramid Matching for Remote Sensing Scene Classification0
Learning Multi-Scale Deep Features for High-Resolution Satellite Image Classification0
X-ray Scattering Image Classification Using Deep Learning0
Understanding deep learning requires rethinking generalizationCode0
Delving into Transferable Adversarial Examples and Black-box AttacksCode0
Neural Networks Designing Neural Networks: Multi-Objective Hyper-Parameter Optimization0
Designing Neural Network Architectures using Reinforcement LearningCode0
Does Distributionally Robust Supervised Learning Give Robust Classifiers?0
Neural Architecture Search with Reinforcement LearningCode0
Learning Identity Mappings with Residual Gates0
Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning RatesCode0
Show:102550
← PrevPage 397 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