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 78517875 of 10420 papers

TitleStatusHype
SESS: Self-Ensembling Semi-Supervised 3D Object DetectionCode0
Competing Ratio Loss for Discriminative Multi-class Image ClassificationCode0
Effective Data Augmentation with Multi-Domain Learning GANs0
Learn to Segment Retinal Lesions and BeyondCode0
An Analysis of the Expressiveness of Deep Neural Network Architectures Based on Their Lipschitz Constants0
Adversarial AutoAugment0
Big Transfer (BiT): General Visual Representation LearningCode2
Deep Manifold Embedding for Hyperspectral Image ClassificationCode0
A Deep Neuro-Fuzzy Network for Image ClassificationCode0
Learning to Impute: A General Framework for Semi-supervised LearningCode0
Multimodal Prediction based on Graph Representations0
Image Analytics for Legal Document Review: A Transfer Learning Approach0
A New Ensemble Method for Concessively Targeted Multi-model Attack0
Towards Verifying Robustness of Neural Networks Against Semantic PerturbationsCode0
Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic ConsolidationCode0
Making Better Mistakes: Leveraging Class Hierarchies with Deep NetworksCode0
ResNetX: a more disordered and deeper network architecture0
Invariant Attribute Profiles: A Spatial-Frequency Joint Feature Extractor for Hyperspectral Image Classification0
Continuous Meta-Learning without TasksCode0
Semantic Regularization: Improve Few-shot Image Classification by Reducing Meta Shift0
A Web Page Classifier Library Based on Random Image Content Analysis Using Deep Learning0
Direction Concentration Learning: Enhancing Congruency in Machine LearningCode0
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification0
PolSF: PolSAR image dataset on San FranciscoCode1
Transductive Zero-Shot Learning for 3D Point Cloud ClassificationCode1
Show:102550
← PrevPage 315 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
10RevCol-HTop 1 Accuracy90Unverified