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 41314140 of 10420 papers

TitleStatusHype
Vision Transformers: From Semantic Segmentation to Dense PredictionCode3
Balanced Contrastive Learning for Long-Tailed Visual RecognitionCode1
Residual and Attentional Architectures for Vector-Symbols0
Consistent Polyhedral Surrogates for Top-k Classification and Variants0
Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross ModulationCode0
Fully trainable Gaussian derivative convolutional layerCode0
Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision LearningCode1
Multi-manifold Attention for Vision Transformers0
ViT-NeT: Interpretable Vision Transformers with Neural Tree DecoderCode1
Zero-Shot Temporal Action Detection via Vision-Language PromptingCode1
Show:102550
← PrevPage 414 of 1042Next →

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