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 41514160 of 10420 papers

TitleStatusHype
QSAN: A Near-term Achievable Quantum Self-Attention Network0
Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image ClassificationCode2
Rich Feature Distillation with Feature Affinity Module for Efficient Image Dehazing0
Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationCode0
Adversarial Robustness Assessment of NeuroEvolution Approaches0
LightViT: Towards Light-Weight Convolution-Free Vision TransformersCode1
Image and Model Transformation with Secret Key for Vision Transformer0
RE-Tagger: A light-weight Real-Estate Image Classifier0
UniNet: Unified Architecture Search with Convolution, Transformer, and MLPCode1
Regression Metric Loss: Learning a Semantic Representation Space for Medical ImagesCode1
Show:102550
← PrevPage 416 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified