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 15511560 of 10420 papers

TitleStatusHype
Implicit Generative Prior for Bayesian Neural NetworksCode0
A Method of Moments Embedding Constraint and its Application to Semi-Supervised LearningCode0
SPLICE -- Streamlining Digital Pathology Image Processing0
SDFD: Building a Versatile Synthetic Face Image Dataset with Diverse Attributes0
Lacunarity Pooling Layers for Plant Image Classification using Texture AnalysisCode0
IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Tasks0
MiMICRI: Towards Domain-centered Counterfactual Explanations of Cardiovascular Image Classification ModelsCode0
Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning0
Rethinking model prototyping through the MedMNIST+ dataset collectionCode1
Vision Transformer-based Adversarial Domain AdaptationCode0
Show:102550
← PrevPage 156 of 1042Next →

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