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 54015450 of 10420 papers

TitleStatusHype
Evaluation of Deep Neural Network Domain Adaptation Techniques for Image RecognitionCode1
Multi-Semantic Image Recognition Model and Evaluating Index for explaining the deep learning models0
DeepPSL: End-to-end perception and reasoning0
A Strong Baseline for the VIPriors Data-Efficient Image Classification Challenge0
Accelerated PDEs for Construction and Theoretical Analysis of an SGD Extension0
ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning0
Audio-to-Image Cross-Modal Generation0
Compressive Visual RepresentationsCode1
Federated Deep Learning with Bayesian Privacy0
Cluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent PriorsCode0
Training on Test Data with Bayesian Adaptation for Covariate Shift0
Predicting Driver Self-Reported Stress by Analyzing the Road Scene0
Disentangled Feature Representation for Few-shot Image ClassificationCode1
Frequency Disentangled Residual Network0
FedProc: Prototypical Contrastive Federated Learning on Non-IID dataCode1
Classification of COVID-19 from CXR Images in a 15-class Scenario: an Attempt to Avoid Bias in the System0
Distribution-sensitive Information Retention for Accurate Binary Neural Network0
BiTr-Unet: a CNN-Transformer Combined Network for MRI Brain Tumor SegmentationCode1
From images in the wild to video-informed image classification0
Frequency Pooling: Shift-Equivalent and Anti-Aliasing Downsampling0
A Multi-stage Transfer Learning Framework for Diabetic Retinopathy Grading on Small Data0
FooBaR: Fault Fooling Backdoor Attack on Neural Network TrainingCode0
Partial sensitivity analysis in differential privacyCode0
Multi-Domain Few-Shot Learning and Dataset for Agricultural Applications0
Balanced-MixUp for Highly Imbalanced Medical Image ClassificationCode1
GhostShiftAddNet: More Features from Energy-Efficient OperationsCode0
Explaining Convolutional Neural Networks by Tagging Filters0
Audio-Visual Speech Recognition is Worth 32328 Voxels0
Class incremental learning for video action classification0
Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification0
Splitfed learning without client-side synchronization: Analyzing client-side split network portion size to overall performance0
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
The Unreasonable Effectiveness of the Final Batch Normalization Layer0
PP-LCNet: A Lightweight CPU Convolutional Neural NetworkCode1
Decision Tree Learning with Spatial Modal Logics0
Transformer-Unet: Raw Image Processing with Unet0
Topological Structure and Semantic Information Transfer Network for Cross-Scene Hyperspectral Image ClassificationCode1
Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs0
Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning0
Partner-Assisted Learning for Few-Shot Image Classification0
Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGDCode0
A trainable monogenic ConvNet layer robust in front of large contrast changes in image classificationCode0
AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance0
Robust Contrastive Active Learning with Feature-guided Query Strategies0
Task Guided Compositional Representation Learning for ZDA0
PAT: Pseudo-Adversarial Training For Detecting Adversarial Videos0
Fine-Grained Few Shot Learning with Foreground Object Transformation0
Check Your Other Door! Creating Backdoor Attacks in the Frequency Domain0
BioLCNet: Reward-modulated Locally Connected Spiking Neural NetworksCode0
Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?Code1
Show:102550
← PrevPage 109 of 209Next →

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