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 21712180 of 10420 papers

TitleStatusHype
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary CellsCode1
Shallow-Deep Networks: Understanding and Mitigating Network OverthinkingCode1
Complementary-Label Learning for Arbitrary Losses and ModelsCode1
SNIP: Single-shot Network Pruning based on Connection SensitivityCode1
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural NetworksCode1
Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised DetectionCode1
A Less Biased Evaluation of Out-of-distribution Sample DetectorsCode1
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' BlocksCode1
Automatically designing CNN architectures using genetic algorithm for image classificationCode1
MnasNet: Platform-Aware Neural Architecture Search for MobileCode1
Show:102550
← PrevPage 218 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