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 94269450 of 10420 papers

TitleStatusHype
Gibbs Sampling with Low-Power Spiking Digital Neurons0
GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learning0
GIST: Greedy Independent Set Thresholding for Diverse Data Summarization0
Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness0
Glasses Detection Using Convolutional Neural Networks0
Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank0
Global Deconvolutional Networks for Semantic Segmentation0
Global Feature Guided Local Pooling0
Global Interaction Modelling in Vision Transformer via Super Tokens0
Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision0
Global-to-Local Support Spectrums for Language Model Explainability0
Global Weighted Average Pooling Bridges Pixel-level Localization and Image-level Classification0
GLoMo: Unsupervised Learning of Transferable Relational Graphs0
GMM-IL: Image Classification using Incrementally Learnt, Independent Probabilistic Models for Small Sample Sizes0
GM-MLIC: Graph Matching based Multi-Label Image Classification0
GM-Net: Learning Features with More Efficiency0
GmNet: Revisiting Gating Mechanisms From A Frequency View0
GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning0
Goal-driven text descriptions for images0
Goal-Oriented Communication for Edge Learning based on the Information Bottleneck0
Goal-Oriented Source Coding using LDPC Codes for Compressed-Domain Image Classification0
Going Deeper Into Face Detection: A Survey0
Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Models0
GoogLe2Net: Going Transverse with Convolutions0
Google is all you need: Semi-Supervised Transfer Learning Strategy For Light Multimodal Multi-Task Classification Model0
Show:102550
← PrevPage 378 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
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