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 5551–5600 of 10420 papers

TitleStatusHype
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
ZoDIAC: Zoneout Dropout Injection Attention CalculationCode0
Continual Learning with Transformers for Image Classification—0
Unsupervised Domain Adaptation Using Feature Disentanglement And GCNs For Medical Image Classification—0
Improved Text Classification via Test-Time Augmentation—0
Multi-view Feature Augmentation with Adaptive Class Activation Mapping—0
Representative Teacher Keys for Knowledge Distillation Model Compression Based on Attention Mechanism for Image Classification—0
Inverted Semantic-Index for Image Retrieval—0
p-Meta: Towards On-device Deep Model Adaptation—0
Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers—0
Evolution of Activation Functions for Deep Learning-Based Image Classification—0
Self Supervised Learning for Few Shot Hyperspectral Image Classification—0
FEATHERS: Federated Architecture and Hyperparameter Search—0
FLVoogd: Robust And Privacy Preserving Federated Learning—0
A novel adversarial learning strategy for medical image classification—0
Open-source FPGA-ML codesign for the MLPerf Tiny BenchmarkCode0
Revisiting Orthogonality Regularization: A Study for Convolutional Neural Networks in Image ClassificationCode0
A Model-Agnostic SAT-based Approach for Symbolic Explanation Enumeration—0
Single-phase deep learning in cortico-cortical networksCode0
Few-Shot Non-Parametric Learning with Deep Latent Variable Model—0
ROSE: A RObust and SEcure DNN Watermarking—0
Coupling Visual Semantics of Artificial Neural Networks and Human Brain Function via Synchronized Activations—0
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming—0
Revisiting lp-constrained Softmax Loss: A Comprehensive StudyCode0
Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and Rényi MeasuresCode0
Deep reinforced active learning for multi-class image classification—0
Remote Sensing Image Classification using Transfer Learning and Attention Based Deep Neural Network—0
When Does Re-initialization Work?—0
Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning—0
Out-of-distribution Detection by Cross-class Vicinity Distribution of In-distribution DataCode0
Terrain Classification using Transfer Learning on Hyperspectral Images: A Comparative study—0
0/1 Deep Neural Networks via Block Coordinate Descent—0
Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarking—0
Transform-Invariant Convolutional Neural Networks for Image Classification and Search—0
Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters—0
A Comparative Study of Confidence Calibration in Deep Learning: From Computer Vision to Medical Imaging—0
Detecting Adversarial Examples in Batches -- a geometrical approachCode0
The Importance of Background Information for Out of Distribution Generalization—0
Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation—0
Active Data Discovery: Mining Unknown Data using Submodular Information Measures—0
Open-Set Recognition with Gradient-Based Representations—0
Using adversarial images to improve outcomes of federated learning for non-IID data—0
Efficient Adaptive Ensembling for Image Classification—0
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification—0
Self-Supervised Implicit Attention: Guided Attention by The Model Itself—0
Masked Siamese ConvNets—0
Recent Advances in Scene Image Representation and Classification—0
Self-Supervised Pretraining for Differentially Private LearningCode0
A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks—0
Specifying and Testing k-Safety Properties for Machine-Learning ModelsCode0
Show:102550
← PrevPage 112 of 209Next →
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