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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4901–4925 of 10420 papers

TitleStatusHype
Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representations—0
A ConvNet for the 2020sCode5
Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks—0
Invariance encoding in sliced-Wasserstein space for image classification with limited training dataCode0
ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce ConnectionsCode0
Glance and Focus Networks for Dynamic Visual RecognitionCode1
Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo ReplayCode1
A Sneak Attack on Segmentation of Medical Images Using Deep Neural Network Classifiers—0
BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split ComputingCode1
Detecting Twenty-thousand Classes using Image-level SupervisionCode3
Negative Evidence Matters in Interpretable Histology Image ClassificationCode0
Nonlocal Kernel Network (NKN): a Stable and Resolution-Independent Deep Neural Network—0
Deep Learning Based Classification System For Recognizing Local Spinach—0
Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window AttentionCode1
Synthesizer Based Efficient Self-Attention for Vision Tasks—0
Problem-dependent attention and effort in neural networks with applications to image resolution and model selection—0
Towards Understanding Quality Challenges of the Federated Learning for Neural Networks: A First Look from the Lens of RobustnessCode0
Multi-Representation Adaptation Network for Cross-domain Image ClassificationCode2
Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple SourcesCode2
AI visualization in Nanoscale Microscopy—0
Attention Mechanism Meets with Hybrid Dense Network for Hyperspectral Image Classification—0
Gaussian-Hermite Moment Invariants of General Multi-Channel Functions—0
Vision Transformer with Deformable AttentionCode2
An analysis of over-sampling labeled data in semi-supervised learning with FixMatchCode0
Building Human-like Communicative Intelligence: A Grounded Perspective—0
Show:102550
← PrevPage 197 of 417Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10RevCol-HTop 1 Accuracy90—Unverified