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 53765400 of 10420 papers

TitleStatusHype
Sequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization Methods0
To Smooth or not to Smooth? On Compatibility between Label Smoothing and Knowledge Distillation0
On the Convergence of Nonconvex Continual Learning with Adaptive Learning Rate0
When in Doubt, Summon the Titans: A Framework for Efficient Inference with Large Models0
Towards Unknown-aware Learning with Virtual Outlier Synthesis0
Dataset Bias Prediction for Few-Shot Image Classification0
Image BERT Pre-training with Online Tokenizer0
How to Adapt Your Large-Scale Vision-and-Language Model0
HFSP: A Hardware-friendly Soft Pruning Framework for Vision Transformers0
Cross Domain Ensemble Distillation for Domain Generalization0
Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing0
Towards Generic Interface for Human-Neural Network Knowledge Exchange0
Does deep learning model calibration improve performance in class-imbalanced medical image classification?0
Combining Human Predictions with Model Probabilities via Confusion Matrices and CalibrationCode1
Second-Order Neural ODE OptimizerCode1
Robust Temporal Ensembling for Learning with Noisy Labels0
Chest X-Rays Image Classification from beta-Variational Autoencoders Latent Features0
Segmentation of Roads in Satellite Images using specially modified U-Net CNNs0
UFO-ViT: High Performance Linear Vision Transformer without SoftmaxCode0
Improvising the Learning of Neural Networks on Hyperspherical ManifoldCode0
Multi-loss ensemble deep learning for chest X-ray classification0
Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition0
Which Design Decisions in AI-enabled Mobile Applications Contribute to Greener AI?0
A Contrastive Learning Approach to Auroral Identification and Classification0
Evaluation of Deep Neural Network Domain Adaptation Techniques for Image RecognitionCode1
Show:102550
← PrevPage 216 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified