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 37263750 of 10420 papers

TitleStatusHype
Image Quality Assessment Guided Deep Neural Networks TrainingCode0
Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuseCode0
Demon: Improved Neural Network Training with Momentum DecayCode0
Automated Knowledge Distillation via Monte Carlo Tree SearchCode0
Adaptive Adversarial Cross-Entropy Loss for Sharpness-Aware MinimizationCode0
Image Classification with CondenseNeXt for ARM-Based Computing PlatformsCode0
Image Classification with Hierarchical Multigraph NetworksCode0
Image classification in frequency domain with 2SReLU: a second harmonics superposition activation functionCode0
Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network EnsembleCode0
Image Classification Using Singular Value Decomposition and OptimizationCode0
DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease DetectionCode0
DDA: Dimensionality Driven Augmentation Search for Contrastive Learning in Laparoscopic SurgeryCode0
Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image ClassificationCode0
Image-Caption Encoding for Improving Zero-Shot GeneralizationCode0
All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene ClassificationCode0
Image classification and retrieval with random depthwise signed convolutional neural networksCode0
Image Classification with Classic and Deep Learning TechniquesCode0
Soft ascent-descent as a stable and flexible alternative to floodingCode0
Improving Generalization of Batch Whitening by Convolutional Unit OptimizationCode0
Identifying Transients in the Dark Energy Survey using Convolutional Neural NetworksCode0
Distilling Effective Supervision from Severe Label NoiseCode0
AutoGAN: Neural Architecture Search for Generative Adversarial NetworksCode0
DCFNet: Deep Neural Network with Decomposed Convolutional FiltersCode0
Identifying Adversarially Attackable and Robust SamplesCode0
Model Input-Output Configuration Search with Embedded Feature Selection for Sensor Time-series and Image ClassificationCode0
Show:102550
← PrevPage 150 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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified