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 10111020 of 10420 papers

TitleStatusHype
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image ClassificationCode1
DAM: Dynamic Adapter Merging for Continual Video QA LearningCode1
Disentangled Feature Representation for Few-shot Image ClassificationCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Danish Fungi 2020 -- Not Just Another Image Recognition DatasetCode1
Distilling Visual Priors from Self-Supervised LearningCode1
DARTS: Differentiable Architecture SearchCode1
DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution EnvironmentsCode1
A Second-Order Approach to Learning with Instance-Dependent Label NoiseCode1
Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationCode1
Show:102550
← PrevPage 102 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