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 94269450 of 10420 papers

TitleStatusHype
Wide Compression: Tensor Ring Nets0
A Twofold Siamese Network for Real-Time Object TrackingCode0
Convolutional Neural Networks combined with Runge-Kutta MethodsCode0
Deep Multi-View Spatial-Temporal Network for Taxi Demand PredictionCode0
Sensitivity and Generalization in Neural Networks: an Empirical Study0
Predicting Natural Hazards with Neuronal Networks0
Learning Image Conditioned Label Space for Multilabel Classification0
Discriminative Label Consistent Domain Adaptation0
Collaboratively Weighting Deep and Classic Representation via L2 Regularization for Image ClassificationCode0
ViS-HuD: Using Visual Saliency to Improve Human Detection with Convolutional Neural Networks0
Unsupervised Band Selection of Hyperspectral Images via Multi-dictionary Sparse Representation0
Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image SegmentationCode0
Weighted Linear Discriminant Analysis based on Class Saliency Information0
Structured Label Inference for Visual UnderstandingCode0
Towards Principled Design of Deep Convolutional Networks: Introducing SimpNetCode0
CapsuleGAN: Generative Adversarial Capsule NetworkCode0
ASP:A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction0
Deep Predictive Coding Network for Object Recognition0
DCFNet: Deep Neural Network with Decomposed Convolutional FiltersCode0
Generative Adversarial Networks and Probabilistic Graph Models for Hyperspectral Image Classification0
Deep Visual Domain Adaptation: A Survey0
Combinets: Creativity via Recombination of Neural Networks0
Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches0
Generating Triples with Adversarial Networks for Scene Graph Construction0
Encoder-Decoder with Atrous Separable Convolution for Semantic Image SegmentationCode1
Show:102550
← PrevPage 378 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
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
10RevCol-HTop 1 Accuracy90Unverified