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 5301–5350 of 10420 papers

TitleStatusHype
Improving Axial-Attention Network Classification via Cross-Channel Weight SharingCode0
Stochastic Anderson Mixing for Nonconvex Stochastic Optimization—0
Automated Seed Quality Testing System using GAN & Active LearningCode0
TyXe: Pyro-based Bayesian neural nets for PytorchCode1
Perturbated Gradients Updating within Unit Space for Deep LearningCode0
Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)Code1
ResNet strikes back: An improved training procedure in timmCode1
Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder—0
Transferability Estimation for Semantic Segmentation Task—0
UNCERTAINTY QUANTIFICATION USING VARIATIONAL INFERENCE FOR BIOMEDICAL IMAGE SEGMENTATION—0
LMSA: Low-relation Mutil-head Self-Attention Mechanism in Visual Transformer—0
Revisiting Linear Decision Boundaries for Few-Shot Learning with Transformer Hypernetworks—0
Regularizing Image Classification Neural Networks with Partial Differential Equations—0
MDFL: A UNIFIED FRAMEWORK WITH META-DROPOUT FOR FEW-SHOT LEARNING—0
Are Vision Transformers Robust to Patch-wise Perturbations?—0
A precortical module for robust CNNs to light variations—0
Representation Disentanglement in Generative Models with Contrastive Learning—0
m-mix: Generating hard negatives via multiple samples mixing for contrastive learning—0
An Investigation on Hardware-Aware Vision Transformer Scaling—0
A Dot Product Attention Free Transformer—0
Adaptive Region Pooling for Fine-Grained Representation Learning—0
Improving the Accuracy of Learning Example Weights for Imbalance Classification—0
Self-supervised Models are Good Teaching Assistants for Vision Transformers—0
Invariance-Guided Feature Evolution for Few-Shot Learning—0
Self-Supervised Prime-Dual Networks for Few-Shot Image Classification—0
iFlood: A Stable and Effective Regularizer—0
Use of small auxiliary networks and scarce data to improve the adversarial robustness of deep learning models—0
Contrastively Enforcing Distinctiveness for Multi-Label Classification—0
Sample-specific and Context-aware Augmentation for Long Tail Image Classification—0
Meta-OLE: Meta-learned Orthogonal Low-Rank Embedding—0
AAVAE: Augmentation-Augmented Variational Autoencoders—0
WaveMix: Multi-Resolution Token Mixing for ImagesCode1
EXPLAINABLE AI-BASED DYNAMIC FILTER PRUNING OF CONVOLUTIONAL NEURAL NETWORKS—0
Local-Global Shifting Vision Transformers—0
Clustered Task-Aware Meta-Learning by Learning from Learning PathsCode0
Evaluating Language-biased image classification based on semantic compositionality—0
Sparse Attention with Learning to Hash—0
Causally Focused Convolutional Networks Through Minimal Human Guidance—0
Learning to Schedule Learning rate with Graph Neural Networks—0
Mistake-driven Image Classification with FastGAN and SpinalNet—0
Bit-aware Randomized Response for Local Differential Privacy in Federated Learning—0
A Class of Short-term Recurrence Anderson Mixing Methods and Their Applications—0
Best Practices in Pool-based Active Learning for Image Classification—0
Interventional Black-Box Explanations—0
Informative Robust Causal Representation for Generalizable Deep Learning—0
SVMnet: Non-parametric image classification based on convolutional SVM ensembles for small training sets—0
Noisy Adversarial Training—0
Rethinking Client Reweighting for Selfish Federated Learning—0
Task Conditioned Stochastic Subsampling—0
Ontology-Driven Semantic Alignment of Artificial Neurons and Visual Concepts—0
Show:102550
← PrevPage 107 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
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified