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 1040110420 of 10420 papers

TitleStatusHype
Selective sampling for accelerating training of deep neural networksCode0
Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled DataCode0
Staleness-aware Async-SGD for Distributed Deep LearningCode0
Stacked What-Where Auto-encodersCode0
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning FrameworkCode0
Explaining Image Classification with Visual DebatesCode0
ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back PropagationCode0
Unifying Synergies between Self-supervised Learning and Dynamic ComputationCode0
Wide Contextual Residual Network with Active Learning for Remote Sensing Image ClassificationCode0
SRM : A Style-based Recalibration Module for Convolutional Neural NetworksCode0
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial ConvolutionsCode0
SRE-Conv: Symmetric Rotation Equivariant Convolution for Biomedical Image ClassificationCode0
Sharpness-Aware Minimization: General Analysis and Improved RatesCode0
SqueezeNAS: Fast neural architecture search for faster semantic segmentationCode0
SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image ClassificationCode0
SpineNet: Learning Scale-Permuted Backbone for Recognition and LocalizationCode0
United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across TasksCode0
United We Stand: Using Epoch-wise Agreement of Ensembles to Combat OverfitCode0
FasTrCaps: An Integrated Framework for Fast yet Accurate Training of Capsule NetworksCode0
Universal Adversarial Perturbations: Efficiency on a small image datasetCode0
Show:102550
← PrevPage 417 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