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 84518475 of 10420 papers

TitleStatusHype
An analysis of over-sampling labeled data in semi-supervised learning with FixMatchCode0
Equivariant Transformer NetworksCode0
Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic ForgettingCode0
Equivariant neural networks and equivarificationCode0
Addressing Small and Imbalanced Medical Image Datasets Using Generative Models: A Comparative Study of DDPM and PGGANs with Random and Greedy K SamplingCode0
Genetic Programming and Gradient Descent: A Memetic Approach to Binary Image ClassificationCode0
Convolutional Neural Networks combined with Runge-Kutta MethodsCode0
Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser ModelsCode0
On the training dynamics of deep networks with L_2 regularizationCode0
Margin-bounded Confidence Scores for Out-of-Distribution DetectionCode0
GENNAPE: Towards Generalized Neural Architecture Performance EstimatorsCode0
Geo-Aware Networks for Fine-Grained RecognitionCode0
ConvNeXt Based Neural Network for Audio Anti-SpoofingCode0
Equivariance versus Augmentation for Spherical ImagesCode0
Geolocation Estimation of Photos using a Hierarchical Model and Scene ClassificationCode0
Spatial Graph Convolutional NetworksCode0
Exploring Adversarial Robustness of Vision Transformers in the Spectral PerspectiveCode0
Why gradient clipping accelerates training: A theoretical justification for adaptivityCode0
Fairness Explainability using Optimal Transport with Applications in Image ClassificationCode0
PSO-Convolutional Neural Networks with Heterogeneous Learning RateCode0
Automatic Configuration of Deep Neural Networks with EGOCode0
GeoMix: Towards Geometry-Aware Data AugmentationCode0
ConViT: Improving Vision Transformers with Soft Convolutional Inductive BiasesCode0
Geo-SIC: Learning Deformable Geometric Shapes in Deep Image ClassifiersCode0
Conviformers: Convolutionally guided Vision TransformerCode0
Show:102550
← PrevPage 339 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