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 6001–6050 of 10420 papers

TitleStatusHype
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksCode2
This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep NetworksCode1
Soft-Attention Improves Skin Cancer Classification PerformanceCode1
RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image RecognitionCode1
MLP-Mixer: An all-MLP Architecture for VisionCode1
LFI-CAM: Learning Feature Importance for Better Visual ExplanationCode1
Synthetic Data for Model Selection—0
Subspace Representation Learning for Few-shot Image Classification—0
GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated LearningCode1
Adversarial Example Detection for DNN Models: A Review and Experimental ComparisonCode1
Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization—0
Submodular Mutual Information for Targeted Data Subset Selection—0
Faster Meta Update Strategy for Noise-Robust Deep LearningCode1
Black-box adversarial attacks using Evolution Strategies—0
Deep Image Destruction: Vulnerability of Deep Image-to-Image Models against Adversarial Attacks—0
Unsupervised data augmentation for object detection—0
GM-MLIC: Graph Matching based Multi-Label Image Classification—0
GeoWINE: Geolocation based Wiki, Image,News and Event RetrievalCode1
Ensembling with Deep Generative ViewsCode1
Emerging Properties in Self-Supervised Vision TransformersCode1
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual RepresentationsCode0
Hardware Architecture of Embedded Inference Accelerator and Analysis of Algorithms for Depthwise and Large-Kernel Convolutions—0
Locality Constrained Analysis Dictionary Learning via K-SVD Algorithm—0
Decoupled Dynamic Filter NetworksCode1
GasHis-Transformer: A Multi-scale Visual Transformer Approach for Gastric Histopathological Image Detection—0
Deep Neural Networks Based Weight Approximation and Computation Reuse for 2-D Image Classification—0
EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature FusionCode1
Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support SamplesCode1
Filter Distribution Templates in Convolutional Networks for Image Classification Tasks—0
Twins: Revisiting the Design of Spatial Attention in Vision TransformersCode1
FastAdaBelief: Improving Convergence Rate for Belief-based Adaptive Optimizers by Exploiting Strong Convexity—0
Boosting Co-teaching with Compression Regularization for Label NoiseCode1
Deep Domain Generalization with Feature-norm Network—0
Open-vocabulary Object Detection via Vision and Language Knowledge DistillationCode1
Explaining in Style: Training a GAN to explain a classifier in StyleSpaceCode1
Watershed of Artificial Intelligence: Human Intelligence, Machine Intelligence, and Biological Intelligence—0
Rethinking BiSeNet For Real-time Semantic SegmentationCode1
ConTNet: Why not use convolution and transformer at the same time?Code1
SGNet: A Super-class Guided Network for Image Classification and Object DetectionCode0
Towards Good Practices for Efficiently Annotating Large-Scale Image Classification DatasetsCode1
Visformer: The Vision-friendly TransformerCode1
Less is more: Selecting informative and diverse subsets with balancing constraints—0
Vision Transformers with Patch DiversificationCode1
HAO: Hardware-aware neural Architecture Optimization for Efficient Inference—0
Mutual Contrastive Learning for Visual Representation LearningCode1
Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Models—0
Multimodal Contrastive Training for Visual Representation Learning—0
Wise-SrNet: A Novel Architecture for Enhancing Image Classification by Learning Spatial Resolution of Feature MapsCode1
3D/2D regularized CNN feature hierarchy for Hyperspectral image classification—0
ASPCNet: A Deep Adaptive Spatial Pattern Capsule Network for Hyperspectral Image Classification—0
Show:102550
← PrevPage 121 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
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