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 6651–6700 of 10420 papers

TitleStatusHype
Generate, Annotate, and Learn: NLP with Synthetic TextCode0
Verifying Quantized Neural Networks using SMT-Based Model Checking—0
Deep neural network loses attention to adversarial images—0
Cross-domain Contrastive Learning for Unsupervised Domain AdaptationCode0
Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems—0
SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation—0
Explainable AI for medical imaging: Explaining pneumothorax diagnoses with Bayesian Teaching—0
Scaling Vision Transformers—0
The Randomness of Input Data Spaces is an A Priori Predictor for Generalization—0
TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block InversionCode0
An Intelligent Hybrid Model for Identity Document Classification—0
MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders—0
Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution TrainingCode0
Frustratingly Easy Uncertainty Estimation for Distribution Shift—0
Reveal of Vision Transformers Robustness against Adversarial Attacks—0
Redundant representations help generalization in wide neural networksCode0
Robust Implicit Networks via Non-Euclidean ContractionsCode0
Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment—0
An End-to-End Breast Tumour Classification Model Using Context-Based Patch Modelling- A BiLSTM Approach for Image Classification—0
GasHisSDB: A New Gastric Histopathology Image Dataset for Computer Aided Diagnosis of Gastric CancerCode0
X-volution: On the unification of convolution and self-attention—0
BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of AttentionCode0
A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer—0
When Vision Transformers Outperform ResNets without Pre-training or Strong Data AugmentationsCode0
SpecRepair: Counter-Example Guided Safety Repair of Deep Neural NetworksCode0
Nonuniform Defocus Removal for Image Classification—0
Stochastic Whitening Batch Normalization—0
TVDIM: Enhancing Image Self-Supervised Pretraining via Noisy Text Data—0
Semantic-Aware Contrastive Learning for Multi-object Medical Image Segmentation—0
Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels—0
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels—0
Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification ModelsCode0
Reconciliation of Statistical and Spatial Sparsity For Robust Image and Image-Set ClassificationCode0
Rethinking Pseudo Labels for Semi-Supervised Object Detection—0
Learning to Learn Semantic Factors in Heterogeneous Image Classification—0
Fidelity Estimation Improves Noisy-Image Classification With Pretrained NetworksCode0
Energy-Efficient and Federated Meta-Learning via Projected Stochastic Gradient Ascent—0
Dual-stream Network for Visual Recognition—0
Bounded logit attention: Learning to explain image classifiersCode0
Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling—0
Scorpion detection and classification systems based on computer vision and deep learning for health security purposes—0
Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin MachineCode0
High Performance Hyperspectral Image Classification using Graphics Processing Units—0
EDDA: Explanation-driven Data Augmentation to Improve Explanation Faithfulness—0
Diffusion-Based Representation Learning—0
FoveaTer: Foveated Transformer for Image Classification—0
AutoSampling: Search for Effective Data Sampling Schedules—0
A systematic review of transfer learning based approaches for diabetic retinopathy detection—0
Encoders and Ensembles for Task-Free Continual Learning—0
Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error—0
Show:102550
← PrevPage 134 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