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 21812190 of 10420 papers

TitleStatusHype
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture DesignCode1
End-to-End Incremental LearningCode1
Invariant Information Clustering for Unsupervised Image Classification and SegmentationCode1
Age Estimation Using Expectation of Label Distribution LearningCode1
This Looks Like That: Deep Learning for Interpretable Image RecognitionCode1
DARTS: Differentiable Architecture SearchCode1
RISE: Randomized Input Sampling for Explanation of Black-box ModelsCode1
Manifold Mixup: Better Representations by Interpolating Hidden StatesCode1
Bayesian Model-Agnostic Meta-LearningCode1
Improving the Resolution of CNN Feature Maps Efficiently with MultisamplingCode1
Show:102550
← PrevPage 219 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