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 31813190 of 10420 papers

TitleStatusHype
ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers0
Does Robustness on ImageNet Transfer to Downstream Tasks?0
Explicitly Modeled Attention Maps for Image Classification0
Does Visual Pretraining Help End-to-End Reasoning?0
Dirichlet-based Histogram Feature Transform for Image Classification0
Blockchain Enabled Trustless API Marketplace0
Blink: Fast and Generic Collectives for Distributed ML0
Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks0
Explanatory Masks for Neural Network Interpretability0
Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs0
Show:102550
← PrevPage 319 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
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