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
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning ParadigmCode1
Deep Roto-Translation Scattering for Object ClassificationCode1
PØDA: Prompt-driven Zero-shot Domain AdaptationCode1
PODA: Prompt-driven Zero-shot Domain AdaptationCode1
Convolutional Sequence to Sequence LearningCode1
PolyLoss: A Polynomial Expansion Perspective of Classification Loss FunctionsCode1
Positional Contrastive Learning for Volumetric Medical Image SegmentationCode1
Post-hoc Uncertainty Learning using a Dirichlet Meta-ModelCode1
Convolution-enhanced Evolving Attention NetworksCode1
CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision ModelsCode1
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamicsCode1
Pretrained ViTs Yield Versatile Representations For Medical ImagesCode1
PRIME: A few primitives can boost robustness to common corruptionsCode1
PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset SelectionCode1
ProAPO: Progressively Automatic Prompt Optimization for Visual ClassificationCode1
Class Adaptive Network CalibrationCode1
Progressive Neural Compression for Adaptive Image Offloading under Timing ConstraintsCode1
Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative StudyCode1
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
DeiT III: Revenge of the ViTCode1
Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity EstimationCode1
An Overview of Deep Learning Architectures in Few-Shot Learning DomainCode1
Designing Network Design SpacesCode1
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network CalibrationCode1
PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision TransformersCode1
Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image ClassificationCode1
PseudoSeg: Designing Pseudo Labels for Semantic SegmentationCode1
CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare RecordsCode1
Meta-Weight-Net: Learning an Explicit Mapping For Sample WeightingCode1
PVT v2: Improved Baselines with Pyramid Vision TransformerCode1
Pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural NetworksCode1
Pyramid Scene Parsing NetworkCode1
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without ConvolutionsCode1
Age Estimation Using Expectation of Label Distribution LearningCode1
QPM: Discrete Optimization for Globally Interpretable Image ClassificationCode1
Deep Polynomial Neural NetworksCode1
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy LabelsCode1
DeepNoise: Signal and Noise Disentanglement based on Classifying Fluorescent Microscopy Images via Deep LearningCode1
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image ClassificationCode1
Adversarial AutoMixupCode1
RankDNN: Learning to Rank for Few-shot LearningCode1
RapidNet: Multi-Level Dilated Convolution Based Mobile BackboneCode1
Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?Code1
Real-Fake: Effective Training Data Synthesis Through Distribution MatchingCode1
Deep Prototypical Networks with Hybrid Residual Attention for 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