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 27512775 of 10420 papers

TitleStatusHype
A CNN with Noise Inclined Module and Denoise Framework for Hyperspectral Image ClassificationCode0
Improving Pre-Trained Weights Through Meta-Heuristics Fine-TuningCode0
Improving Pairwise Ranking for Multi-label Image ClassificationCode0
Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and RetrainingCode0
Bounded logit attention: Learning to explain image classifiersCode0
Improving Nonlinear Projection Heads using Pretrained Autoencoder EmbeddingsCode0
A Deeper Look into Convolutions via Eigenvalue-based PruningCode0
Improving Neural Architecture Search Image Classifiers via Ensemble LearningCode0
Improving Random-Sampling Neural Architecture Search by Evolving the Proxy Search SpaceCode0
Born Again Neural NetworksCode0
Improving Memory Efficiency for Training KANs via Meta LearningCode0
Bootstrapping the Relationship Between Images and Their Clean and Noisy LabelsCode0
Boosting with Lexicographic Programming: Addressing Class Imbalance without Cost TuningCode0
3D CNN with Localized Residual Connections for Hyperspectral Image ClassificationCode0
Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative LearningCode0
Improving model calibration with accuracy versus uncertainty optimizationCode0
Improving Generalization of Batch Whitening by Convolutional Unit OptimizationCode0
A Gradient Boosting Approach for Training Convolutional and Deep Neural NetworksCode0
Improving Generalization and Convergence by Enhancing Implicit RegularizationCode0
SynerMix: Synergistic Mixup Solution for Enhanced Intra-Class Cohesion and Inter-Class Separability in Image ClassificationCode0
An empirical study on the effects of different types of noise in image classification tasksCode0
Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep FeaturesCode0
Attention Augmented Convolutional NetworksCode0
Improving Fairness in Image Classification via SketchingCode0
Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output CodesCode0
Show:102550
← PrevPage 111 of 417Next →

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