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 111–120 of 10420 papers

TitleStatusHype
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
ALBench: A Framework for Evaluating Active Learning in Object DetectionCode2
Effective Data Augmentation With Diffusion ModelsCode2
FasterViT: Fast Vision Transformers with Hierarchical AttentionCode2
Fixing the train-test resolution discrepancyCode2
Fixing the train-test resolution discrepancy: FixEfficientNetCode2
FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceCode2
MogaNet: Multi-order Gated Aggregation NetworkCode2
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space DualityCode2
Dilated Neighborhood Attention TransformerCode2
Show:102550
← PrevPage 12 of 1042Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified