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 50265050 of 10420 papers

TitleStatusHype
Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey0
SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation0
Scaling Up Influence FunctionsCode1
A Survey of Deep Learning for Low-Shot Object Detection0
Interpretable Image Classification with Differentiable Prototypes AssignmentCode1
Hard Sample Aware Noise Robust Learning for Histopathology Image ClassificationCode1
Ablation study of self-supervised learning for image classificationCode0
Novel Class Discovery in Semantic SegmentationCode1
Make A Long Image Short: Adaptive Token Length for Vision Transformers0
A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled SamplesCode1
Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?Code1
Probabilistic Tracking with Deep Factors0
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
Vision Pair Learning: An Efficient Training Framework for Image Classification0
Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention0
MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionCode1
Sample Prior Guided Robust Model Learning to Suppress Noisy LabelsCode1
FIBA: Frequency-Injection based Backdoor Attack in Medical Image AnalysisCode1
Generating and Modifying Natural Language Explanations0
DFTS2: Simulating Deep Feature Transmission Over Packet Loss ChannelsCode0
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed ClassificationCode1
Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search0
Shallow Network Based on Depthwise Over-Parameterized Convolution for Hyperspectral Image Classification0
Semi-supervised music emotion recognition using noisy student training and harmonic pitch class profilesCode1
CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded SystemsCode0
Show:102550
← PrevPage 202 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