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 33513375 of 10420 papers

TitleStatusHype
FV-MgNet: Fully Connected V-cycle MgNet for Interpretable Time Series Forecasting0
Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms0
Deep Dependency Networks for Multi-Label Classification0
Weight Prediction Boosts the Convergence of AdamW0
Structured mutation inspired by evolutionary theory enriches population performance and diversity0
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and VideoCode4
NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese NetworksCode0
Does Deep Active Learning Work in the Wild?0
Training with Mixed-Precision Floating-Point Assignments0
UPop: Unified and Progressive Pruning for Compressing Vision-Language TransformersCode1
Inference Time Evidences of Adversarial Attacks for Forensic on Transformers0
Reverse engineering adversarial attacks with fingerprints from adversarial examples0
Rethinking Soft Label in Label Distribution Learning Perspective0
Transfer Learning and Class Decomposition for Detecting the Cognitive Decline of Alzheimer Disease0
NP-Match: Towards a New Probabilistic Model for Semi-Supervised LearningCode1
Massively Scaling Heteroscedastic Classifiers0
Lateralized Learning for Multi-Class Visual Classification Tasks0
DAFD: Domain Adaptation via Feature Disentanglement for Image Classification0
Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser ModelsCode0
NeSyFOLD: Neurosymbolic Framework for Interpretable Image ClassificationCode0
Identifying Adversarially Attackable and Robust SamplesCode0
Language-Driven Anchors for Zero-Shot Adversarial RobustnessCode0
SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual RecognitionCode2
The Influences of Color and Shape Features in Visual Contrastive Learning0
PhaVIP: Phage VIrion Protein classification based on chaos game representation and Vision TransformerCode1
Show:102550
← PrevPage 135 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