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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4926–4950 of 10420 papers

TitleStatusHype
FV-MgNet: Fully Connected V-cycle MgNet for Interpretable Time Series Forecasting—0
Structured mutation inspired by evolutionary theory enriches population performance and diversity—0
Weight Prediction Boosts the Convergence of AdamW—0
Deep Dependency Networks for Multi-Label Classification—0
Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms—0
Reverse engineering adversarial attacks with fingerprints from adversarial examples—0
NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese NetworksCode0
Does Deep Active Learning Work in the Wild?—0
Rethinking Soft Label in Label Distribution Learning Perspective—0
Inference Time Evidences of Adversarial Attacks for Forensic on Transformers—0
Transfer Learning and Class Decomposition for Detecting the Cognitive Decline of Alzheimer Disease—0
Training with Mixed-Precision Floating-Point Assignments—0
Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser ModelsCode0
NeSyFOLD: Neurosymbolic Framework for Interpretable Image ClassificationCode0
Language-Driven Anchors for Zero-Shot Adversarial RobustnessCode0
Identifying Adversarially Attackable and Robust SamplesCode0
Lateralized Learning for Multi-Class Visual Classification Tasks—0
DAFD: Domain Adaptation via Feature Disentanglement for Image Classification—0
Massively Scaling Heteroscedastic Classifiers—0
The Influences of Color and Shape Features in Visual Contrastive Learning—0
Anticipate, Ensemble and Prune: Improving Convolutional Neural Networks via Aggregated Early Exits—0
Supervision Complexity and its Role in Knowledge Distillation—0
MetaNO: How to Transfer Your Knowledge on Learning Hidden Physics—0
PECAN: A Deterministic Certified Defense Against Backdoor Attacks—0
Explore the Power of Dropout on Few-shot Learning—0
Show:102550
← PrevPage 198 of 417Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10RevCol-HTop 1 Accuracy90—Unverified