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 2301–2350 of 10419 papers

TitleStatusHype
Multi‑camera trajectory matching based on hierarchical clustering and constraintsCode1
Using Logic Programming and Kernel-Grouping for Improving Interpretability of Convolutional Neural Networks—0
WeedCLR: Weed Contrastive Learning through Visual Representations with Class-Optimized Loss in Long-Tailed Datasets—0
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and GenerationCode1
Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial ExamplesCode0
Monarch Mixer: A Simple Sub-Quadratic GEMM-Based ArchitectureCode2
Image Clustering with External GuidanceCode1
Towards Exploring Fairness in Visual Transformer based Natural and GAN Image Detection SystemsCode0
United We Stand: Using Epoch-wise Agreement of Ensembles to Combat OverfitCode0
Instilling Inductive Biases with SubnetworksCode0
VeRA: Vector-based Random Matrix Adaptation—0
Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs—0
Transparent Anomaly Detection via Concept-based Explanations—0
A Non-monotonic Smooth Activation Function—0
RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNetsCode1
Real-Fake: Effective Training Data Synthesis Through Distribution MatchingCode1
Soft ascent-descent as a stable and flexible alternative to floodingCode0
A Survey of Graph and Attention Based Hyperspectral Image Classification Methods for Remote Sensing Data—0
Prior-Free Continual Learning with Unlabeled Data in the WildCode0
Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attacks—0
TS-ENAS:Two-Stage Evolution for Cell-based Network Architecture Search—0
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningCode7
Two Sides of The Same Coin: Bridging Deep Equilibrium Models and Neural ODEs via Homotopy ContinuationCode0
Efficient Model-Agnostic Multi-Group Equivariant Networks—0
Plug-and-Play Feature Generation for Few-Shot Medical Image Classification—0
Subspace Adaptation Prior for Few-Shot LearningCode0
PaLI-3 Vision Language Models: Smaller, Faster, StrongerCode1
Fusion framework and multimodality for the Laplacian approximation of Bayesian neural networks—0
Self-supervised visual learning for analyzing firearms trafficking activities on the Web—0
Leveraging Vision-Language Models for Improving Domain Generalization in Image ClassificationCode1
Strategies and impact of learning curve estimation for CNN-based image classification—0
AutoVP: An Automated Visual Prompting Framework and BenchmarkCode1
Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks—0
DualAug: Exploiting Additional Heavy Augmentation with OOD Data RejectionCode0
NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional VisualizationsCode0
Multiview Transformer: Rethinking Spatial Information in Hyperspectral Image Classification—0
Histopathological Image Classification and Vulnerability Analysis using Federated Learning—0
Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configurationCode0
Human-Centered Evaluation of XAI Methods—0
Efficient Adaptation of Large Vision Transformer via Adapter Re-ComposingCode1
Distributed Transfer Learning with 4th Gen Intel Xeon Processors—0
Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real ImagesCode0
Adversarial Masked Image Inpainting for Robust Detection of Mpox and Non-Mpox—0
SpikeCLIP: A Contrastive Language-Image Pretrained Spiking Neural NetworkCode0
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
Text-driven Prompt Generation for Vision-Language Models in Federated Learning—0
ViTs are Everywhere: A Comprehensive Study Showcasing Vision Transformers in Different Domain—0
Unleashing the power of Neural Collapse for Transferability Estimation—0
What do larger image classifiers memorise?—0
Transformer Fusion with Optimal TransportCode1
Show:102550
← PrevPage 47 of 209Next →
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
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified