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 42214230 of 10420 papers

TitleStatusHype
DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors0
Deep Supervision with Intermediate Concepts0
Behavior of Mini-Batch Optimization for Training Deep Neural Networks on Large Datasets0
Histograms of Pattern Sets for Image Classification and Object Recognition0
An Algorithm for Routing Vectors in Sequences0
Hilbert Sinkhorn Divergence for Optimal Transport0
Deep Spatial Pyramid: The Devil is Once Again in the Details0
DeepSetNet: Predicting Sets with Deep Neural Networks0
Be Careful What You Backpropagate: A Case For Linear Output Activations & Gradient Boosting0
HindSight: A Graph-Based Vision Model Architecture For Representing Part-Whole Hierarchies0
Show:102550
← PrevPage 423 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
10RevCol-HTop 1 Accuracy90Unverified