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 99269950 of 10420 papers

TitleStatusHype
Leveraging Model Interpretability and Stability to increase Model RobustnessCode0
Posterior-Guided Neural Architecture SearchCode0
Relation-Aware Global Attention for Person Re-identificationCode0
Progressive Neural Architecture SearchCode0
BagFlip: A Certified Defense against Data PoisoningCode0
A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection in Network Traffic DataCode0
One Step Learning, One Step ReviewCode0
Relation Network for Multi-label Aerial Image ClassificationCode0
A Comparative Study on Efficiencies of Variants of Convolutional Neural Networks based on Image Classification TaskCode0
Leveraging Topological Guidance for Improved Knowledge DistillationCode0
DartsReNet: Exploring new RNN cells in ReNet architecturesCode0
Progressive Transfer LearningCode0
A Discriminative Channel Diversification Network for Image ClassificationCode0
DAP: Detection-Aware Pre-training with Weak SupervisionCode0
DANet: Divergent Activation for Weakly Supervised Object LocalizationCode0
DAC: Data-free Automatic Acceleration of Convolutional NetworksCode0
D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain AlignmentCode0
CycleMix: Mixing Source Domains for Domain Generalization in Style-Dependent DataCode0
LiDAR-Guided Cross-Attention Fusion for Hyperspectral Band Selection and Image ClassificationCode0
LiD-FL: Towards List-Decodable Federated LearningCode0
Bad Global Minima Exist and SGD Can Reach ThemCode0
Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image ClassificationCode0
Lifting Layers: Analysis and ApplicationsCode0
Relative stability toward diffeomorphisms indicates performance in deep netsCode0
TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video ClassificationCode0
Show:102550
← PrevPage 398 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
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