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 93519375 of 10420 papers

TitleStatusHype
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural NetworksCode0
HydraNets: Specialized Dynamic Architectures for Efficient Inference0
Accurate and Efficient Similarity Search for Large Scale Face Recognition0
Generating Image Captions in Arabic using Root-Word Based Recurrent Neural Networks and Deep Neural Networks0
OLÉ: Orthogonal Low-Rank Embedding - A Plug and Play Geometric Loss for Deep LearningCode0
Rotation Equivariance and Invariance in Convolutional Neural NetworksCode0
Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization0
Multiaccuracy: Black-Box Post-Processing for Fairness in ClassificationCode0
Multi-function Convolutional Neural Networks for Improving Image Classification Performance0
Learning multiple non-mutually-exclusive tasks for improved classification of inherently ordered labels0
Deep Learning under Privileged Information Using Heteroscedastic DropoutCode0
Object-Level Representation Learning for Few-Shot Image Classification0
Fast Dynamic Routing Based on Weighted Kernel Density EstimationCode0
CapsNet comparative performance evaluation for image classification0
Adversarial Examples in Remote Sensing0
Learning From Less Data: Diversified Subset Selection and Active Learning in Image Classification Tasks0
Calibrating Deep Convolutional Gaussian ProcessesCode0
Accelerating CNN inference on FPGAs: A Survey0
Transductive Label Augmentation for Improved Deep Network Learning0
Transfer Learning for Illustration ClassificationCode0
Do Better ImageNet Models Transfer Better?0
Non-convex non-local flows for saliency detection0
Hyperspectral image classification via a random patches networkCode0
"Why Should I Trust Interactive Learners?" Explaining Interactive Queries of Classifiers to Users0
Unsupervised Domain Adaptation using Regularized Hyper-graph Matching0
Show:102550
← PrevPage 375 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