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 84768500 of 10420 papers

TitleStatusHype
Deep multi-class learning from label proportions0
Toward Runtime-Throttleable Neural Networks0
Empirically Measuring Concentration: Fundamental Limits on Intrinsic RobustnessCode0
An Inertial Newton Algorithm for Deep LearningCode0
Replica-exchange Nosé-Hoover dynamics for Bayesian learning on large datasets0
A Study of BFLOAT16 for Deep Learning Training0
Training Data Subset Search with Ensemble Active Learning0
Image classification using quantum inference on the D-Wave 2X0
Bayesian Nonparametric Federated Learning of Neural NetworksCode0
Differential Privacy Has Disparate Impact on Model AccuracyCode0
Inference with Hybrid Bio-hardware Neural Networks0
CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural NetworksCode0
Texture CNN for Thermoelectric Metal Pipe Image Classification0
Texture CNN for Histopathological Image Classification0
A Compact Representation of Histopathology Images using Digital Stain Separation & Frequency-Based Encoded Local Projections0
Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion0
Efficient Object Embedding for Spliced Image Retrieval0
Why gradient clipping accelerates training: A theoretical justification for adaptivityCode0
RecNets: Channel-wise Recurrent Convolutional Neural Networks0
EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksCode3
Network DeconvolutionCode0
Capsule Routing via Variational BayesCode0
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function OptimizationCode0
Combating Label Noise in Deep Learning Using AbstentionCode1
On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural NetworksCode0
Show:102550
← PrevPage 340 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