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 55765600 of 10420 papers

TitleStatusHype
Deep Neural Networks and PIDE discretizations0
A Low Rank Promoting Prior for Unsupervised Contrastive Learning0
Using Metamorphic Relations to Verify and Enhance Artcode Classification0
GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learning0
Unifying Nonlocal Blocks for Neural NetworksCode1
Generic Neural Architecture Search via RegressionCode1
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision TransformerCode1
Rapid Elastic Architecture Search under Specialized Classes and Resource Constraints0
Domain Generalization via Gradient SurgeryCode1
Toward Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition SystemsCode1
Inference via Sparse Coding in a Hierarchical Vision ModelCode0
From augmented microscopy to the topological transformer: a new approach in cell image analysis for Alzheimer's research0
Vision Transformer with Progressive SamplingCode1
SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis0
Hybrid Classical-Quantum Deep Learning Models for Autonomous Vehicle Traffic Image Classification Under Adversarial Attack0
Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain AdaptationCode0
Self-Supervised Feature Learning of 1D Convolutional Neural Networks with Contrastive Loss for Eating Detection Using an In-Ear MicrophoneCode0
Group Fisher Pruning for Practical Network CompressionCode1
Projective Skip-Connections for Segmentation Along a Subset of Dimensions in Retinal OCT0
Detectron2 Object Detection & Manipulating Images using CartoonizationCode4
Multimodal Item Categorization Fully Based on Transformer0
Adaptable image quality assessment using meta-reinforcement learning of task amenability0
Delving into Deep Image Prior for Adversarial Defense: A Novel Reconstruction-based Defense Framework0
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode1
DPT: Deformable Patch-based Transformer for Visual RecognitionCode1
Show:102550
← PrevPage 224 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
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