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 371380 of 10419 papers

TitleStatusHype
Token Cropr: Faster ViTs for Quite a Few TasksCode1
On the Performance Analysis of Momentum Method: A Frequency Domain PerspectiveCode1
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image CollectionsCode1
Vision Mamba Distillation for Low-resolution Fine-grained Image ClassificationCode1
Spectral-Spatial Transformer with Active Transfer Learning for Hyperspectral Image ClassificationCode1
FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image ClassificationCode1
CODE-CL: Conceptor-Based Gradient Projection for Deep Continual LearningCode1
MetaLA: Unified Optimal Linear Approximation to Softmax Attention MapCode1
Vision Eagle Attention: a new lens for advancing image classificationCode1
HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image ClassificationCode1
Show:102550
← PrevPage 38 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