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 20912100 of 10420 papers

TitleStatusHype
Universal Adversarial Robustness of Texture and Shape-Biased ModelsCode1
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation AnchoringCode1
Beyond Synthetic Noise: Deep Learning on Controlled Noisy LabelsCode1
General E(2)-Equivariant Steerable CNNsCode1
Self-training with Noisy Student improves ImageNet classificationCode1
Multimodal Model-Agnostic Meta-Learning via Task-Aware ModulationCode1
A deep active learning system for species identification and counting in camera trap imagesCode1
Soft-Label Dataset Distillation and Text Dataset DistillationCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Addressing Failure Prediction by Learning Model ConfidenceCode1
Show:102550
← PrevPage 210 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