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 3976–4000 of 10420 papers

TitleStatusHype
MS-Twins: Multi-Scale Deep Self-Attention Networks for Medical Image Segmentation—0
Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment—0
Robust MRI Reconstruction by Smoothed Unrolling (SMUG)Code0
Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification—0
RAFIC: Retrieval-Augmented Few-shot Image ClassificationCode0
Initialization Matters for Adversarial Transfer LearningCode0
Speed Up Federated Learning in Heterogeneous Environment: A Dynamic Tiering ApproachCode0
TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot Image Classification—0
Subject-Based Domain Adaptation for Facial Expression RecognitionCode0
Scientific Preparation for CSST: Classification of Galaxy and Nebula/Star Cluster Based on Deep Learning—0
Annotation-Free Group Robustness via Loss-Based Resampling—0
Human-in-the-Loop Visual Re-ID for Population Size EstimationCode0
An adversarial attack approach for eXplainable AI evaluation on deepfake detection modelsCode0
FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning—0
Transferable Candidate Proposal with Bounded UncertaintyCode0
Text as Image: Learning Transferable Adapter for Multi-Label Classification—0
Cross-Modal Alternating Learning with Task-Aware Representations for Continual LearningCode0
On the Robustness of Large Multimodal Models Against Image Adversarial Attacks—0
Riemannian Complex Matrix Convolution Network for PolSAR Image Classification—0
Classification for everyone : Building geography agnostic models for fairer recognition—0
Unsupervised learning on spontaneous retinal activity leads to efficient neural representation geometry—0
GDN: A Stacking Network Used for Skin Cancer DiagnosisCode0
CLAMP: Contrastive LAnguage Model Prompt-tuning—0
A Comprehensive Literature Review on Sweet Orange Leaf Diseases—0
Federated Active Learning for Target Domain GeneralisationCode0
Show:102550
← PrevPage 160 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