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 21262150 of 10420 papers

TitleStatusHype
Learning Hierarchical Image Segmentation For Recognition and By RecognitionCode1
Active Domain Adaptation via Clustering Uncertainty-weighted EmbeddingsCode1
Improving Vision Transformers by Revisiting High-frequency ComponentsCode1
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
Language-Guided Transformer for Federated Multi-Label ClassificationCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
ConTNet: Why not use convolution and transformer at the same time?Code1
Language Quantized AutoEncoders: Towards Unsupervised Text-Image AlignmentCode1
LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception TasksCode1
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image ClassificationCode1
CSPNet: A New Backbone that can Enhance Learning Capability of CNNCode1
Improving the Resolution of CNN Feature Maps Efficiently with MultisamplingCode1
Contextual Convolutional Neural NetworksCode1
Improving Visual Prompt Tuning for Self-supervised Vision TransformersCode1
Age Estimation Using Expectation of Label Distribution LearningCode1
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network CalibrationCode1
Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window AttentionCode1
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning ParadigmCode1
Curriculum Temperature for Knowledge DistillationCode1
Astroformer: More Data Might not be all you need for ClassificationCode1
Curriculum By SmoothingCode1
Improving robustness against common corruptions by covariate shift adaptationCode1
Contextual Transformer Networks for Visual RecognitionCode1
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised LearningCode1
Concept Learners for Few-Shot LearningCode1
Show:102550
← PrevPage 86 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