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 21212130 of 10420 papers

TitleStatusHype
Unsupervised Learning of Object Keypoints for Perception and ControlCode1
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive ProcessesCode1
A Partially Reversible U-Net for Memory-Efficient Volumetric Image SegmentationCode1
Presence-Only Geographical Priors for Fine-Grained Image ClassificationCode1
When Does Label Smoothing Help?Code1
Combating Label Noise in Deep Learning Using AbstentionCode1
Derivative Manipulation for General Example WeightingCode1
Shredder: Learning Noise Distributions to Protect Inference PrivacyCode1
ProbAct: A Probabilistic Activation Function for Deep Neural NetworksCode1
DIANet: Dense-and-Implicit Attention NetworkCode1
Show:102550
← PrevPage 213 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