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 50515075 of 10420 papers

TitleStatusHype
Evolutionary Neural Architecture Search for Image Restoration0
CLOG-CD: Curriculum Learning based on Oscillating Granularity of Class Decomposed Medical Image Classification0
Evolutionary Multi-objective Optimisation in Neurotrajectory Prediction0
Evolutionary Cell Aided Design for Neural Network Architectures0
EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion0
Applying adversarial networks to increase the data efficiency and reliability of Self-Driving Cars0
Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning0
Evidential Federated Learning for Skin Lesion Image Classification0
Evidence-empowered Transfer Learning for Alzheimer's Disease0
CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization0
Applications of the Streaming Networks0
Event-Based Control for Online Training of Neural Networks0
Evaluation, Tuning and Interpretation of Neural Networks for Meteorological Applications0
Evaluation of Transfer Learning for Classification of: (1) Diabetic Retinopathy by Digital Fundus Photography and (2) Diabetic Macular Edema, Choroidal Neovascularization and Drusen by Optical Coherence Tomography0
CLIP-QDA: An Explainable Concept Bottleneck Model0
Applications of Sequential Learning for Medical Image Classification0
Adversarial Examples Versus Cloud-based Detectors: A Black-box Empirical Study0
A Comprehensive Survey on Hardware-Aware Neural Architecture Search0
A 3-stage Spectral-spatial Method for Hyperspectral Image Classification0
PreMix: Addressing Label Scarcity in Whole Slide Image Classification with Pre-trained Multiple Instance Learning Aggregators0
Fidelity of Interpretability Methods and Perturbation Artifacts in Neural Networks0
Applications and Effect Evaluation of Generative Adversarial Networks in Semi-Supervised Learning0
Evaluation of Deep Learning on an Abstract Image Classification Dataset0
Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval0
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement0
Show:102550
← PrevPage 203 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