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 43764400 of 10420 papers

TitleStatusHype
DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical ImagesCode1
GIT: A Generative Image-to-text Transformer for Vision and LanguageCode2
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature DistillationCode2
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessCode6
CA-UDA: Class-Aware Unsupervised Domain Adaptation with Optimal Assignment and Pseudo-Label Refinement0
BagFlip: A Certified Defense against Data PoisoningCode0
Fast Vision Transformers with HiLo AttentionCode2
TransBoost: Improving the Best ImageNet Performance using Deep TransductionCode0
Trainable Weight Averaging: A General Approach for Subspace TrainingCode1
Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial LabelsCode1
Matryoshka Representation LearningCode2
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision TransformersCode1
On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition0
Inception TransformerCode2
A Comparative Study of Gastric Histopathology Sub-size Image Classification: from Linear Regression to Visual Transformer0
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning SystemsCode0
A CNN with Noise Inclined Module and Denoise Framework for Hyperspectral Image ClassificationCode0
Concurrent Neural Tree and Data Preprocessing AutoML for Image Classification0
DPSNN: A Differentially Private Spiking Neural Network with Temporal Enhanced Pooling0
Privacy-Preserving Image Classification Using Vision Transformer0
An interpretation of the final fully connected layer0
Deep Learning-based automated classification of Chinese Speech Sound Disorders0
Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments0
Accurate and Resource-Efficient Lipreading with Efficientnetv2 and Transformers0
Discriminative Feature Learning through Feature Distance LossCode0
Show:102550
← PrevPage 176 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