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 14761500 of 10419 papers

TitleStatusHype
Just rotate it! Uncertainty estimation in closed-source models via multiple queries0
Decentralized Federated Learning Over Imperfect Communication Channels0
3DSS-Mamba: 3D-Spectral-Spatial Mamba for Hyperspectral Image Classification0
Multimodal Adaptive Inference for Document Image Classification with Anytime Early ExitingCode0
Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image ClassificationCode2
Verification technology for finger vein biometric0
An Invisible Backdoor Attack Based On Semantic Feature0
SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch NormalizationCode2
Reproducibility Study of CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image ClassificationCode1
Towards SAR Automatic Target Recognition MultiCategory SAR Image Classification Based on Light Weight Vision Transformer0
Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models0
Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning0
Reduced storage direct tensor ring decomposition for convolutional neural networks compressionCode0
Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification0
Many-Shot In-Context Learning in Multimodal Foundation ModelsCode2
ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image DatasetCode0
Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and PrivacyCode1
Improving Label Error Detection and Elimination with Uncertainty Quantification0
Tackling Distribution Shifts in Task-Oriented Communication with Information BottleneckCode0
The Pitfalls and Promise of Conformal Inference Under Adversarial AttacksCode0
Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modelingCode1
The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks0
FolkTalent: Enhancing Classification and Tagging of Indian Folk Paintings0
Achieving Fairness Through Channel Pruning for Dermatological Disease DiagnosisCode1
Who's in and who's out? A case study of multimodal CLIP-filtering in DataCompCode0
Show:102550
← PrevPage 60 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