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 15011550 of 10419 papers

TitleStatusHype
BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained DevicesCode1
BiTr-Unet: a CNN-Transformer Combined Network for MRI Brain Tumor SegmentationCode1
FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image ClassificationCode1
Defending Against Unforeseen Failure Modes with Latent Adversarial TrainingCode1
MaxDropout: Deep Neural Network Regularization Based on Maximum Output ValuesCode1
Maximum Classifier Discrepancy for Unsupervised Domain AdaptationCode1
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
Denoised Smoothing: A Provable Defense for Pretrained ClassifiersCode1
DeiT III: Revenge of the ViTCode1
Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable PrototypesCode1
Forward Learning of Graph Neural NetworksCode1
CEFHRI: A Communication Efficient Federated Learning Framework for Recognizing Industrial Human-Robot InteractionCode1
CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image ClassificationCode1
Measuring Robustness to Natural Distribution Shifts in Image ClassificationCode1
Understanding the Role of the Projector in Knowledge DistillationCode1
Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response JacobiansCode1
FcaNet: Frequency Channel Attention NetworksCode1
CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image ClassificationCode1
A General Regret Bound of Preconditioned Gradient Method for DNN TrainingCode1
Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural NetworksCode1
"BNN - BN = ?": Training Binary Neural Networks without Batch NormalizationCode1
Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image ClassificationCode1
Boosting Active Learning via Improving Test PerformanceCode1
Densely Connected Convolutional NetworksCode1
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
Boosting Convolutional Neural Networks with Middle Spectrum Grouped ConvolutionCode1
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture SearchCode1
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image ClassificationCode1
FCCNs: Fully Complex-valued Convolutional Networks using Complex-valued Color Model and Loss FunctionCode1
MetaDelta: A Meta-Learning System for Few-shot Image ClassificationCode1
An Empirical Investigation of Representation Learning for ImitationCode1
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANNCode1
An Empirical Investigation of the Role of Pre-training in Lifelong LearningCode1
CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image ClassificationCode1
Causal Transportability for Visual RecognitionCode1
FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel RepresentationCode1
FatNet: High Resolution Kernels for Classification Using Fully Convolutional Optical Neural NetworksCode1
FC-KAN: Function Combinations in Kolmogorov-Arnold NetworksCode1
A deep active learning system for species identification and counting in camera trap imagesCode1
Detecting AutoAttack Perturbations in the Frequency DomainCode1
Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image ClassificationCode1
Boosting Multi-Label Image Classification with Complementary Parallel Self-DistillationCode1
Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image ClassificationCode1
Hybrid Supervision Learning for Pathology Whole Slide Image ClassificationCode1
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision TransformersCode1
Boosting the Adversarial Transferability of Surrogate Models with Dark KnowledgeCode1
Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image ClassificationCode1
Category Query Learning for Human-Object Interaction ClassificationCode1
DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding AttacksCode1
Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text AttacksCode1
Show:102550
← PrevPage 31 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
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