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 34013410 of 10420 papers

TitleStatusHype
CC-Loss: Channel Correlation Loss For Image Classification0
Efficient and Flexible Method for Reducing Moderate-size Deep Neural Networks with Condensation0
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run0
Efficient and Reliable Overlay Networks for Decentralized Federated Learning0
Efficient Annotation for Medical Image Analysis: A One-Pass Selective Annotation Approach0
Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management0
Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look0
A non-discriminatory approach to ethical deep learning0
DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification0
Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques0
Show:102550
← PrevPage 341 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