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 16011650 of 10419 papers

TitleStatusHype
Robust Semantic Interpretability: Revisiting Concept Activation VectorsCode1
LeViT: a Vision Transformer in ConvNet's Clothing for Faster InferenceCode1
Network Quantization with Element-wise Gradient ScalingCode1
Anytime Dense Prediction with Confidence AdaptivityCode1
Remote Sensing Image Classification with the SEN12MS DatasetCode1
SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image ClassificationCode1
On the Robustness of Vision Transformers to Adversarial ExamplesCode1
Going deeper with Image TransformersCode1
MT3: Meta Test-Time Training for Self-Supervised Test-Time AdaptionCode1
Learning Representational Invariances for Data-Efficient Action RecognitionCode1
Model-Contrastive Federated LearningCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
Rethinking Spatial Dimensions of Vision TransformersCode1
ViViT: A Video Vision TransformerCode1
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image EncodingCode1
CvT: Introducing Convolutions to Vision TransformersCode1
[Re] Rigging the Lottery: Making All Tickets WinnersCode1
Rethinking Neural Operations for Diverse TasksCode1
TransCenter: Transformers with Dense Representations for Multiple-Object TrackingCode1
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image ClassificationCode1
IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object TrackingCode1
Distilling Object Detectors via Decoupled FeaturesCode1
MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement LearningCode1
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy LabelsCode1
Diverse Branch Block: Building a Convolution as an Inception-like UnitCode1
AutoMix: Unveiling the Power of Mixup for Stronger ClassifiersCode1
Scaling Local Self-Attention for Parameter Efficient Visual BackbonesCode1
BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture SearchCode1
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual RecognitionCode1
Incorporating Convolution Designs into Visual TransformersCode1
DeepViT: Towards Deeper Vision TransformerCode1
Local Patch AutoAugment with Multi-Agent CollaborationCode1
Robust Models Are More Interpretable Because Attributions Look NormalCode1
Scalable Vision Transformers with Hierarchical PoolingCode1
Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image ClassificationCode1
Danish Fungi 2020 -- Not Just Another Image Recognition DatasetCode1
3D Human Pose Estimation with Spatial and Temporal TransformersCode1
Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark DatasetCode1
TrivialAugment: Tuning-free Yet State-of-the-Art Data AugmentationCode1
MSMatch: Semi-Supervised Multispectral Scene Classification with Few LabelsCode1
The Low-Rank Simplicity Bias in Deep NetworksCode1
Consistency-based Active Learning for Object DetectionCode1
Triplet-Watershed for Hyperspectral Image ClassificationCode1
Gradient Projection Memory for Continual LearningCode1
Deep Reinforcement Learning for Band Selection in Hyperspectral Image ClassificationCode1
UPANets: Learning from the Universal Pixel Attention NetworksCode1
TransFG: A Transformer Architecture for Fine-grained RecognitionCode1
Membership Inference Attacks on Machine Learning: A SurveyCode1
Revisiting ResNets: Improved Training and Scaling StrategiesCode1
Information Maximization Clustering via Multi-View Self-LabellingCode1
Show:102550
← PrevPage 33 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