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 42814290 of 10420 papers

TitleStatusHype
Differentiable Top-k Classification LearningCode1
Masked Frequency Modeling for Self-Supervised Visual Pre-TrainingCode1
Self-Supervised Implicit Attention: Guided Attention by The Model Itself0
Masked Siamese ConvNets0
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification0
Recent Advances in Scene Image Representation and Classification0
Self-Supervised Pretraining for Differentially Private LearningCode0
Peripheral Vision TransformerCode1
Evaluating histopathology transfer learning with ChampKitCode1
A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks0
Show:102550
← PrevPage 429 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