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 17511800 of 10419 papers

TitleStatusHype
A Novel lightweight Convolutional Neural Network, ExquisiteNetV2Code1
Regularizing Neural Networks via Adversarial Model PerturbationCode1
Relational Surrogate Loss LearningCode1
Relative Positional Encoding for Transformers with Linear ComplexityCode1
Evaluating the Adversarial Robustness of Adaptive Test-time DefensesCode1
Towards a More Rigorous Science of Blindspot Discovery in Image Classification ModelsCode1
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation AnchoringCode1
Going Deeper with ConvolutionsCode1
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network CalibrationCode1
Reproducible scaling laws for contrastive language-image learningCode1
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
Res2Net: A New Multi-scale Backbone ArchitectureCode1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
Evidential Turing ProcessesCode1
Evolutionary Neural AutoML for Deep LearningCode1
Age Estimation Using Expectation of Label Distribution LearningCode1
Class Adaptive Network CalibrationCode1
Evolving Normalization-Activation LayersCode1
EXACT: How to Train Your AccuracyCode1
Class-Aware Contrastive Semi-Supervised LearningCode1
Class-Aware Patch Embedding Adaptation for Few-Shot Image ClassificationCode1
Class-Balanced Active Learning for Image ClassificationCode1
Class-Balanced Distillation for Long-Tailed Visual RecognitionCode1
Class-Balanced Loss Based on Effective Number of SamplesCode1
Class-Difficulty Based Methods for Long-Tailed Visual RecognitionCode1
Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity EstimationCode1
An Overview of Deep Learning Architectures in Few-Shot Learning DomainCode1
Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?Code1
CoAtNet: Marrying Convolution and Attention for All Data SizesCode1
Explainable Deep Learning Methods in Medical Image Classification: A SurveyCode1
EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use caseCode1
Explaining and Harnessing Adversarial ExamplesCode1
CoCa: Contrastive Captioners are Image-Text Foundation ModelsCode1
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image ClassificationCode1
Explaining in Style: Training a GAN to explain a classifier in StyleSpaceCode1
Explaining Latent Representations with a Corpus of ExamplesCode1
Explaining Predictions of Non-Linear Classifiers in NLPCode1
Rethinking Transfer Learning for Medical Image ClassificationCode1
Generative Classifiers as a Basis for Trustworthy Image ClassificationCode1
Discovering and Mitigating Visual Biases through Keyword ExplanationCode1
Generative Hierarchical Features from Synthesizing ImagesCode1
Co2L: Contrastive Continual LearningCode1
Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image ClassificationCode1
Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?Code1
Adversarial AutoMixupCode1
Revisiting Sparse Convolutional Model for Visual RecognitionCode1
NoisyNN: Exploring the Impact of Information Entropy Change in Learning SystemsCode1
Co^2L: Contrastive Continual LearningCode1
Exploring Vision Transformers for Fine-grained ClassificationCode1
Generative Adversarial Minority Oversampling for Spectral-Spatial Hyperspectral Image ClassificationCode1
Show:102550
← PrevPage 36 of 209Next →

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