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 42314240 of 10420 papers

TitleStatusHype
Self Supervised Learning for Few Shot Hyperspectral Image Classification0
FEATHERS: Federated Architecture and Hyperparameter Search0
Revisiting Orthogonality Regularization: A Study for Convolutional Neural Networks in Image ClassificationCode0
Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D SpaceCode1
A novel adversarial learning strategy for medical image classification0
Open-source FPGA-ML codesign for the MLPerf Tiny BenchmarkCode0
A Model-Agnostic SAT-based Approach for Symbolic Explanation Enumeration0
Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation ConsistencyCode1
Single-phase deep learning in cortico-cortical networksCode0
Few-Shot Non-Parametric Learning with Deep Latent Variable Model0
Show:102550
← PrevPage 424 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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 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