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 57015725 of 10420 papers

TitleStatusHype
Focal Self-attention for Local-Global Interactions in Vision TransformersCode1
On the Practicality of Deterministic Epistemic UncertaintyCode0
Temporally Sorting Images from Real-World EventsCode0
Understanding Adversarial Examples Through Deep Neural Network's Response Surface and Uncertainty Regions0
One-class Steel Detector Using Patch GAN Discriminator for Visualising Anomalous Feature Map0
Exploring Robust Architectures for Deep Artificial Neural NetworksCode0
Exploring Localization for Self-supervised Fine-grained Contrastive Learning0
Understanding and Improving Early Stopping for Learning with Noisy LabelsCode1
Cells are Actors: Social Network Analysis with Classical ML for SOTA Histology Image ClassificationCode0
Zoo-Tuning: Adaptive Transfer from a Zoo of Models0
Adaptive Sample Selection for Robust Learning under Label NoiseCode0
Benchmarking Knowledge-driven Zero-shot LearningCode1
Co^2L: Contrastive Continual LearningCode1
R-Drop: Regularized Dropout for Neural NetworksCode1
Multi-Compound Transformer for Accurate Biomedical Image SegmentationCode1
Progressive Class-based Expansion Learning For Image Classification0
Hyperspectral Remote Sensing Image Classification Based on Multi-scale Cross Graphic Convolution0
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic SparsityCode1
RAILS: A Robust Adversarial Immune-inspired Learning SystemCode1
Immuno-mimetic Deep Neural Networks (Immuno-Net)0
Can An Image Classifier Suffice For Action Recognition?Code1
Spectral-Spatial Global Graph Reasoning for Hyperspectral Image ClassificationCode1
Image Classification with CondenseNeXt for ARM-Based Computing PlatformsCode0
Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers0
Efficient Document Image Classification Using Region-Based Graph Neural Network0
Show:102550
← PrevPage 229 of 417Next →

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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 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