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 92769300 of 10420 papers

TitleStatusHype
Tandem Blocks in Deep Convolutional Neural Networks0
Rotation Equivariance and Invariance in Convolutional Neural NetworksCode0
Multiaccuracy: Black-Box Post-Processing for Fairness in ClassificationCode0
Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization0
Learning multiple non-mutually-exclusive tasks for improved classification of inherently ordered labels0
Multi-function Convolutional Neural Networks for Improving Image Classification Performance0
Deep Learning under Privileged Information Using Heteroscedastic DropoutCode0
Learning From Less Data: Diversified Subset Selection and Active Learning in Image Classification Tasks0
CapsNet comparative performance evaluation for image classification0
Improving the Resolution of CNN Feature Maps Efficiently with MultisamplingCode1
Fast Dynamic Routing Based on Weighted Kernel Density EstimationCode0
Adversarial Examples in Remote Sensing0
Object-Level Representation Learning for Few-Shot Image Classification0
Accelerating CNN inference on FPGAs: A Survey0
Calibrating Deep Convolutional Gaussian ProcessesCode0
Transductive Label Augmentation for Improved Deep Network Learning0
AutoAugment: Learning Augmentation Policies from DataCode3
Do Better ImageNet Models Transfer Better?0
Non-convex non-local flows for saliency detection0
Transfer Learning for Illustration ClassificationCode0
Hyperspectral image classification via a random patches networkCode0
Unsupervised Domain Adaptation using Regularized Hyper-graph Matching0
"Why Should I Trust Interactive Learners?" Explaining Interactive Queries of Classifiers to Users0
Masking: A New Perspective of Noisy SupervisionCode0
Improving CNN classifiers by estimating test-time priors0
Show:102550
← PrevPage 372 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
10RevCol-HTop 1 Accuracy90Unverified