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 13261350 of 10419 papers

TitleStatusHype
FC-KAN: Function Combinations in Kolmogorov-Arnold NetworksCode1
"BNN - BN = ?": Training Binary Neural Networks without Batch NormalizationCode1
Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction DetectionCode1
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean LabelCode1
FedBABU: Towards Enhanced Representation for Federated Image ClassificationCode1
FedDefender: Backdoor Attack Defense in Federated LearningCode1
Federated Learning via Input-Output Collaborative DistillationCode1
Federated Semi-supervised Medical Image Classification via Inter-client Relation MatchingCode1
BAGAN: Data Augmentation with Balancing GANCode1
Boosting Active Learning via Improving Test PerformanceCode1
COVID-CXNet: Detecting COVID-19 in Frontal Chest X-ray Images using Deep LearningCode1
Bag of Tricks for Image Classification with Convolutional Neural NetworksCode1
FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image ClassificationCode1
Domain Prompt Learning for Efficiently Adapting CLIP to Unseen DomainsCode1
Boosting Co-teaching with Compression Regularization for Label NoiseCode1
Balanced Contrastive Learning for Long-Tailed Visual RecognitionCode1
Balanced Energy Regularization Loss for Out-of-distribution DetectionCode1
FFT-based Dynamic Token Mixer for VisionCode1
FIBA: Frequency-Injection based Backdoor Attack in Medical Image AnalysisCode1
FILIP: Fine-grained Interactive Language-Image Pre-TrainingCode1
Balanced-MixUp for Highly Imbalanced Medical Image ClassificationCode1
Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual FeaturesCode1
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained EnvironmentsCode1
Fine-grained Recognition with Learnable Semantic Data AugmentationCode1
Active Learning for Convolutional Neural Networks: A Core-Set ApproachCode1
Show:102550
← PrevPage 54 of 417Next →

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