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 51015125 of 10420 papers

TitleStatusHype
ResNet Structure Simplification with the Convolutional Kernel Redundancy Measure0
Rethinking Two Consensuses of the Transferability in Deep Learning0
Soft Labels for Rapid Satellite Object Detection0
Test-Time Mixup Augmentation for Data and Class-Specific Uncertainty Estimation in Deep Learning Image Classification0
GMM-IL: Image Classification using Incrementally Learnt, Independent Probabilistic Models for Small Sample Sizes0
Pattern Attention Transformer with Doughnut Kernel0
An Empirical Study on the Efficacy of Deep Active Learning for Image Classification0
Optimizing Explanations by Network Canonization and Hyperparameter Search0
Interpreting Vulnerabilities of Multi-Instance Learning to Adversarial PerturbationsCode0
Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think0
GENNAPE: Towards Generalized Neural Architecture Performance EstimatorsCode0
AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification0
Exploiting Category Names for Few-Shot Classification with Vision-Language Models0
SimCS: Simulation for Domain Incremental Online Continual Segmentation0
Impact of Automatic Image Classification and Blind Deconvolution in Improving Text Detection Performance of the CRAFT Algorithm0
Explaining Deep Convolutional Neural Networks for Image Classification by Evolving Local Interpretable Model-agnostic Explanations0
Establishment of Neural Networks Robust to Label Noise0
Entropy-Driven Mixed-Precision Quantization for Deep Network Design0
SI-GAT: A method based on improved Graph Attention Network for sonar image classification0
Learning to Learn: How to Continuously Teach Humans and Machines0
SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image ClassificationCode0
Context-Adaptive Deep Neural Networks via Bridge-Mode Connectivity0
Forged Image Detection using SOTA Image Classification Deep Learning Methods for Image Forensics with Error Level Analysis0
Semantic-Aware Local-Global Vision Transformer0
A Particle-based Sparse Gaussian Process Optimizer0
Show:102550
← PrevPage 205 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