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 38513900 of 10420 papers

TitleStatusHype
A Unified View of Masked Image ModelingCode0
Semi-Supervised Learning with Pseudo-Negative Labels for Image ClassificationCode0
Image Classification with Hierarchical Multigraph NetworksCode0
Image Classification Using Singular Value Decomposition and OptimizationCode0
Image Classification with Classic and Deep Learning TechniquesCode0
DATA: Differentiable ArchiTecture ApproximationCode0
Color Channel Perturbation Attacks for Fooling Convolutional Neural Networks and A Defense Against Such AttacksCode0
Adapting Object Detectors via Selective Cross-Domain AlignmentCode0
Exploring Target Representations for Masked AutoencodersCode0
Architectural Vision for Quantum Computing in the Edge-Cloud ContinuumCode0
Image Classification with CondenseNeXt for ARM-Based Computing PlatformsCode0
ColorMAE: Exploring data-independent masking strategies in Masked AutoEncodersCode0
Data-dependent Initializations of Convolutional Neural NetworksCode0
Image classification and retrieval with random depthwise signed convolutional neural networksCode0
ColorNet: Investigating the importance of color spaces for image classificationCode0
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language TasksCode0
Image-Caption Encoding for Improving Zero-Shot GeneralizationCode0
Exploring the Limits of Weakly Supervised PretrainingCode0
Exploring the Open World Using Incremental Extreme Value MachinesCode0
Adversarial Style Augmentation for Domain Generalized Urban-Scene SegmentationCode0
Image classification in frequency domain with 2SReLU: a second harmonics superposition activation functionCode0
Distilling Effective Supervision from Severe Label NoiseCode0
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural NetworksCode0
Identifying Transients in the Dark Energy Survey using Convolutional Neural NetworksCode0
ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain AdaptationCode0
Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network EnsembleCode0
A Contrastive Knowledge Transfer Framework for Model Compression and Transfer LearningCode0
SGNet: A Super-class Guided Network for Image Classification and Object DetectionCode0
Model Input-Output Configuration Search with Embedded Feature Selection for Sensor Time-series and Image ClassificationCode0
ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object DetectorCode0
Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box SettingsCode0
Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud ClassifiersCode0
Identification of Stone Deterioration Patterns with Large Multimodal ModelsCode0
IDEA: Image Description Enhanced CLIP-AdapterCode0
sharpDARTS: Faster and More Accurate Differentiable Architecture SearchCode0
Identifying Adversarially Attackable and Robust SamplesCode0
Cartoon Face Recognition: A Benchmark DatasetCode0
AugStatic - A Light-Weight Image Augmentation LibraryCode0
I-CEE: Tailoring Explanations of Image Classification Models to User ExpertiseCode0
Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled DataCode0
Data Augmentation in a Hybrid Approach for Aspect-Based Sentiment AnalysisCode0
Comb, Prune, Distill: Towards Unified Pruning for Vision Model CompressionCode0
iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual RecognitionCode0
Identifying Bias in Deep Neural Networks Using Image TransformsCode0
ImageNot: A contrast with ImageNet preserves model rankingsCode0
HyperZZW Operator Connects Slow-Fast Networks for Full Context InteractionCode0
AlgebraNetsCode0
Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGDCode0
Tuned Compositional Feature Replays for Efficient Stream LearningCode0
Hyperspectral Image Classification With Contrastive Graph Convolutional NetworkCode0
Show:102550
← PrevPage 78 of 209Next →

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