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 98769900 of 10420 papers

TitleStatusHype
Learning with Latent LanguageCode0
Low-Cost Self-Ensembles Based on Multi-Branch Transformation and Grouped ConvolutionCode0
BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image ClassificationCode0
On Complex Valued Convolutional Neural NetworksCode0
Data Parameters: A New Family of Parameters for Learning a Differentiable CurriculumCode0
Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep ModelsCode0
A New Cervical Cytology Dataset for Nucleus Detection and Image Classification (Cervix93) and Methods for Cervical Nucleus DetectionCode0
Probing Contextual Diversity for Dense Out-of-Distribution DetectionCode0
Data-Free Generative Replay for Class-Incremental Learning on Imbalanced DataCode0
On dataset transferability in medical image classificationCode0
Data-Free Backbone Fine-Tuning for Pruned Neural NetworksCode0
Learn To Pay AttentionCode0
On-device Online Learning and Semantic Management of TinyML SystemsCode0
Learn to Segment Retinal Lesions and BeyondCode0
Learn What You Need in Personalized Federated LearningCode0
A Comprehensive Overhaul of Feature DistillationCode0
Data-Efficient Training of CNNs and Transformers with Coresets: A Stability PerspectiveCode0
A Comprehensive guide to Bayesian Convolutional Neural Network with Variational InferenceCode0
On Divergence Measures for Bayesian PseudocoresetsCode0
One-bit Supervision for Image ClassificationCode0
Rotation Equivariance and Invariance in Convolutional Neural NetworksCode0
Less Is Better: Unweighted Data Subsampling via Influence FunctionCode0
Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial ExamplesCode0
Rotation equivariant vector field networksCode0
Data-Efficient Language Shaped Few-shot Image ClassificationCode0
Show:102550
← PrevPage 396 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