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 751760 of 10419 papers

TitleStatusHype
A Closer Look at Self-Supervised Lightweight Vision TransformersCode1
Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic SegmentationCode1
Addressing Failure Detection by Learning Model ConfidenceCode1
BinaryViT: Pushing Binary Vision Transformers Towards Convolutional ModelsCode1
Addressing Failure Prediction by Learning Model ConfidenceCode1
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODECode1
Understanding the Role of the Projector in Knowledge DistillationCode1
DPMLBench: Holistic Evaluation of Differentially Private Machine LearningCode1
An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic ProcessorCode1
Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz NetworksCode1
Show:102550
← PrevPage 76 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
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