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 526550 of 10419 papers

TitleStatusHype
Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image ClassificationCode1
Co2L: Contrastive Continual LearningCode1
CLR: Channel-wise Lightweight Reprogramming for Continual LearningCode1
Domain Prompt Learning for Efficiently Adapting CLIP to Unseen DomainsCode1
A deep active learning system for species identification and counting in camera trap imagesCode1
Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNetsCode1
Clusterability as an Alternative to Anchor Points When Learning with Noisy LabelsCode1
CoAtNet: Marrying Convolution and Attention for All Data SizesCode1
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge DistillationCode1
Curriculum Temperature for Knowledge DistillationCode1
Differentiable Top-k Classification LearningCode1
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image CollectionsCode1
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed DataCode1
CLIP4IDC: CLIP for Image Difference CaptioningCode1
Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image ClassificationCode1
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object NavigationCode1
Understanding the Role of the Projector in Knowledge DistillationCode1
Addressing Failure Prediction by Learning Model ConfidenceCode1
Clean-Label Backdoor Attacks on Video Recognition ModelsCode1
Addressing Failure Detection by Learning Model ConfidenceCode1
A Closer Look at Self-Supervised Lightweight Vision TransformersCode1
CLCNet: Rethinking of Ensemble Modeling with Classification Confidence NetworkCode1
CleanNet: Transfer Learning for Scalable Image Classifier Training with Label NoiseCode1
Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity EstimationCode1
Class-Difficulty Based Methods for Long-Tailed Visual RecognitionCode1
Show:102550
← PrevPage 22 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