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 301350 of 10419 papers

TitleStatusHype
FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceCode2
Transferability of Adversarial Examples to Attack Cloud-based Image Classifier ServiceCode2
LayoutLM: Pre-training of Text and Layout for Document Image UnderstandingCode2
Big Transfer (BiT): General Visual Representation LearningCode2
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksCode2
RandAugment: Practical automated data augmentation with a reduced search spaceCode2
Fixing the train-test resolution discrepancyCode2
Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation LearningCode2
ProxylessNAS: Direct Neural Architecture Search on Target Task and HardwareCode2
GPipe: Efficient Training of Giant Neural Networks using Pipeline ParallelismCode2
Context Encoding for Semantic SegmentationCode2
Learning Efficient Convolutional Networks through Network SlimmingCode2
Random Erasing Data AugmentationCode2
Revisiting Unreasonable Effectiveness of Data in Deep Learning EraCode2
Pruning Filters for Efficient ConvNetsCode2
Some Improvements on Deep Convolutional Neural Network Based Image ClassificationCode2
Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and PhysicsCode1
SeqPE: Transformer with Sequential Position EncodingCode1
InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck MambaCode1
SAFE: Finding Sparse and Flat Minima to Improve PruningCode1
Eigenspectrum Analysis of Neural Networks without Aspect Ratio BiasCode1
OD3: Optimization-free Dataset Distillation for Object DetectionCode1
Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic SegmentationCode1
Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image ClassificationCode1
Domain Adaptation for Multi-label Image Classification: a Discriminator-free ApproachCode1
AGI-Elo: How Far Are We From Mastering A Task?Code1
Spectral-Spatial Self-Supervised Learning for Few-Shot Hyperspectral Image ClassificationCode1
ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale StagesCode1
CheXWorld: Exploring Image World Modeling for Radiograph Representation LearningCode1
Bayesian continual learning and forgetting in neural networksCode1
Towards Accurate and Interpretable Neuroblastoma Diagnosis via Contrastive Multi-scale Pathological Image AnalysisCode1
LEMUR Neural Network Dataset: Towards Seamless AutoMLCode1
Pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural NetworksCode1
NoProp: Training Neural Networks without Back-propagation or Forward-propagationCode1
On Large Multimodal Models as Open-World Image ClassifiersCode1
LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer TextCode1
Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal RepresentationsCode1
Interpretable Image Classification via Non-parametric Part Prototype LearningCode1
Fair Federated Medical Image Classification Against Quality Shift via Inter-Client Progressive State MatchingCode1
M^3amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing ClassificationCode1
XFMamba: Cross-Fusion Mamba for Multi-View Medical Image ClassificationCode1
Delving into Out-of-Distribution Detection with Medical Vision-Language ModelsCode1
Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance LearningCode1
Gradient-Guided Annealing for Domain GeneralizationCode1
ProAPO: Progressively Automatic Prompt Optimization for Visual ClassificationCode1
QPM: Discrete Optimization for Globally Interpretable Image ClassificationCode1
MaxSup: Overcoming Representation Collapse in Label SmoothingCode1
A synergistic CNN-transformer network with pooling attention fusion for hyperspectral image classificationCode1
GAIA: A Global, Multi-modal, Multi-scale Vision-Language Dataset for Remote Sensing Image AnalysisCode1
MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI ClassificationCode1
Show:102550
← PrevPage 7 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