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 38313840 of 10420 papers

TitleStatusHype
Data-Efficient Training of CNNs and Transformers with Coresets: A Stability PerspectiveCode0
Data-Efficient Language Shaped Few-shot Image ClassificationCode0
On the Limitations of Temperature Scaling for Distributions with OverlapsCode0
Exploring Alternatives to Softmax FunctionCode0
Cold Case: The Lost MNIST DigitsCode0
A Lightweight Privacy-Preserving Scheme Using Label-based Pixel Block Mixing for Image Classification in Deep LearningCode0
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural NetworksCode0
A Unified View of Masked Image ModelingCode0
Model Input-Output Configuration Search with Embedded Feature Selection for Sensor Time-series and Image ClassificationCode0
IDEA: Image Description Enhanced CLIP-AdapterCode0
Show:102550
← PrevPage 384 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