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 801825 of 10419 papers

TitleStatusHype
Dynamic Perceiver for Efficient Visual RecognitionCode1
Dynamic Routing Between CapsulesCode1
Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label CorrectionCode1
Early-Learning Regularization Prevents Memorization of Noisy LabelsCode1
CoCa: Contrastive Captioners are Image-Text Foundation ModelsCode1
EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled RegularizationCode1
CODE-CL: Conceptor-Based Gradient Projection for Deep Continual LearningCode1
TransCenter: Transformers with Dense Representations for Multiple-Object TrackingCode1
EEEA-Net: An Early Exit Evolutionary Neural Architecture SearchCode1
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODECode1
A Robust Feature Downsampling Module for Remote Sensing Visual TasksCode1
Efficient Adaptation of Large Vision Transformer via Adapter Re-ComposingCode1
Can An Image Classifier Suffice For Action Recognition?Code1
Efficient Classification of Very Large Images with Tiny ObjectsCode1
Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz NetworksCode1
CoAtNet: Marrying Convolution and Attention for All Data SizesCode1
CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAsCode1
3D U^2-Net: A 3D Universal U-Net for Multi-Domain Medical Image SegmentationCode1
All you need is a good initCode1
CNN Filter DB: An Empirical Investigation of Trained Convolutional FiltersCode1
Co^2L: Contrastive Continual LearningCode1
Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image ClassificationCode1
Adaptive and Background-Aware Vision Transformer for Real-Time UAV TrackingCode1
CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep LearningCode1
Co2L: Contrastive Continual LearningCode1
Show:102550
← PrevPage 33 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
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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified