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 80768100 of 10420 papers

TitleStatusHype
TopoAct: Visually Exploring the Shape of Activations in Deep LearningCode0
Towards Partial Supervision for Generic Object Counting in Natural ScenesCode0
Meta-Learning Initializations for Image SegmentationCode0
Parting with Illusions about Deep Active Learning0
Discriminative Robust Deep Dictionary Learning for Hyperspectral Image Classification0
Label Consistent Transform Learning for Hyperspectral Image Classification0
Wide-Area Land Cover Mapping with Sentinel-1 Imagery using Deep Learning Semantic Segmentation Models0
Row-Sparse Discriminative Deep Dictionary Learning for Hyperspectral Image Classification0
Associative Alignment for Few-shot Image ClassificationCode0
Feature Losses for Adversarial Robustness0
Arithmetic addition of two integers by deep image classification networks: experiments to quantify their autonomous reasoning abilityCode0
Appending Adversarial Frames for Universal Video Attack0
SpineNet: Learning Scale-Permuted Backbone for Recognition and LocalizationCode0
Deep Adaptive Wavelet NetworkCode0
Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning0
Selective Synthetic Augmentation with Quality Assurance0
Naive Gabor Networks for Hyperspectral Image Classification0
Meta-Learning without MemorizationCode0
Learning Disentangled Representations via Mutual Information EstimationCode0
Principal Component Properties of Adversarial Samples0
Dynamic Convolution: Attention over Convolution KernelsCode0
An Empirical Study on the Relation between Network Interpretability and Adversarial RobustnessCode0
Improved Few-Shot Visual Classification0
Sampling-Free Learning of Bayesian Quantized Neural Networks0
ClusterFit: Improving Generalization of Visual RepresentationsCode0
Show:102550
← PrevPage 324 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