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 73267350 of 10420 papers

TitleStatusHype
Fine-Tuning DARTS for Image Classification0
On the training dynamics of deep networks with L_2 regularizationCode0
Multiscale Deep Equilibrium ModelsCode1
Neural Ensemble Search for Uncertainty Estimation and Dataset ShiftCode1
Depth Uncertainty in Neural NetworksCode1
AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant WeightsCode1
Optimal Complexity in Decentralized Training0
Stream-51: Streaming Classification and Novelty Detection from VideosCode1
Topology-aware Differential Privacy for Decentralized Image Classification0
Explicitly Modeled Attention Maps for Image Classification0
Domain Adaptation and Image Classification via Deep Conditional Adaptation Network0
Meta Approach to Data Augmentation Optimization0
Split-Merge Pooling0
DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition0
Bootstrap your own latent: A new approach to self-supervised LearningCode1
CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAsCode1
BI-MAML: Balanced Incremental Approach for Meta Learning0
Attentive Feature Reuse for Multi Task Meta learning0
On Second Order Behaviour in Augmented Neural ODEsCode1
Move-to-Data: A new Continual Learning approach with Deep CNNs, Application for image-class recognition0
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networksCode0
AlgebraNetsCode0
HMIC: Hierarchical Medical Image Classification, A Deep Learning Approach0
Multigrid-in-Channels Architectures for Wide Convolutional Neural Networks0
SegNBDT: Visual Decision Rules for SegmentationCode1
Show:102550
← PrevPage 294 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