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 40764100 of 10420 papers

TitleStatusHype
Texture features in medical image analysis: a survey0
Maximal Independent Vertex Set applied to Graph Pooling0
Connection Reduction of DenseNet for Image RecognitionCode0
On the Evaluation of User Privacy in Deep Neural Networks using Timing Side Channel0
giMLPs: Gate with Inhibition Mechanism in MLPsCode0
A Rotation Meanout Network with Invariance for Dermoscopy Image Classification and RetrievalCode0
Information Gain Sampling for Active Learning in Medical Image Classification0
XOOD: Extreme Value Based Out-Of-Distribution Detection For Image ClassificationCode0
Adaptive Edge Offloading for Image Classification Under Rate LimitCode1
A review of Deep learning Techniques for COVID-19 identification on Chest CT images0
Class-Difficulty Based Methods for Long-Tailed Visual RecognitionCode1
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy LabelsCode1
Topological structure of complex predictionsCode1
Pro-tuning: Unified Prompt Tuning for Vision Tasks0
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated ConvolutionsCode2
Neural Architecture Search on Efficient Transformers and Beyond0
CrAM: A Compression-Aware MinimizerCode1
On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification0
Text Classification in Memristor-based Spiking Neural NetworksCode1
Image sensing with multilayer, nonlinear optical neural networksCode1
Multi-layer Representation Learning for Robust OOD Image Classification0
Adaptive sampling for scanning pixel cameras0
ALBench: A Framework for Evaluating Active Learning in Object DetectionCode2
Contrastive Masked Autoencoders are Stronger Vision LearnersCode1
Generalizable multi-task, multi-domain deep segmentation of sparse pediatric imaging datasets via multi-scale contrastive regularization and multi-joint anatomical priors0
Show:102550
← PrevPage 164 of 417Next →

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