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 176200 of 10419 papers

TitleStatusHype
A Simple Framework for Contrastive Learning of Visual RepresentationsCode2
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural NetworksCode2
Focal Modulation NetworksCode2
DAT++: Spatially Dynamic Vision Transformer with Deformable AttentionCode2
A Simple Episodic Linear Probe Improves Visual Recognition in the WildCode2
GalLoP: Learning Global and Local Prompts for Vision-Language ModelsCode2
Generalized Parametric Contrastive LearningCode2
Global Context Vision TransformersCode2
GPipe: Efficient Training of Giant Neural Networks using Pipeline ParallelismCode2
GrootVL: Tree Topology is All You Need in State Space ModelCode2
GroupMamba: Efficient Group-Based Visual State Space ModelCode2
DaViT: Dual Attention Vision TransformersCode2
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated ConvolutionsCode2
Deep PCB To COCO ConvertorCode2
DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image ClassificationCode2
Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image ClassificationCode2
CrypTen: Secure Multi-Party Computation Meets Machine LearningCode2
Big Transfer (BiT): General Visual Representation LearningCode2
LayoutLM: Pre-training of Text and Layout for Document Image UnderstandingCode2
Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple SourcesCode2
Learning Transferable Visual Models From Natural Language SupervisionCode2
LibFewShot: A Comprehensive Library for Few-shot LearningCode2
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality InversionCode2
DAMamba: Vision State Space Model with Dynamic Adaptive ScanCode2
ConvMAE: Masked Convolution Meets Masked AutoencodersCode2
Show:102550
← PrevPage 8 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