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 221230 of 10419 papers

TitleStatusHype
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic SegmentationCode2
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and TransportationCode2
DAT++: Spatially Dynamic Vision Transformer with Deformable AttentionCode2
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsCode2
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision ApplicationsCode2
Omnivore: A Single Model for Many Visual ModalitiesCode2
ConvMAE: Masked Convolution Meets Masked AutoencodersCode2
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View CompletionCode2
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic SegmentationCode2
Continual Forgetting for Pre-trained Vision ModelsCode2
Show:102550
← PrevPage 23 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