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 32513300 of 10419 papers

TitleStatusHype
DropBlock: A regularization method for convolutional networksCode0
Calibrate to InterpretCode0
Calibrating Deep Convolutional Gaussian ProcessesCode0
Modeling Extent-of-Texture Information for Ground Terrain RecognitionCode0
Improving Pairwise Ranking for Multi-label Image ClassificationCode0
Dropout is NOT All You Need to Prevent Gradient LeakageCode0
Improving Pre-Trained Weights Through Meta-Heuristics Fine-TuningCode0
Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNetsCode0
Improving Neural Architecture Search Image Classifiers via Ensemble LearningCode0
Improving Memory Efficiency for Training KANs via Meta LearningCode0
Batch Model Consolidation: A Multi-Task Model Consolidation FrameworkCode0
Modularity Trumps Invariance for Compositional RobustnessCode0
Improving model calibration with accuracy versus uncertainty optimizationCode0
Improving Nonlinear Projection Heads using Pretrained Autoencoder EmbeddingsCode0
Improving robustness to corruptions with multiplicative weight perturbationsCode0
Improving k-Means Clustering Performance with Disentangled Internal RepresentationsCode0
Deep Neural Network Compression for Image Classification and Object DetectionCode0
Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative LearningCode0
Deep neural network based on F-neurons and its learningCode0
A multiple-instance densely-connected ConvNet for aerial scene classificationCode0
Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck ModelsCode0
Improving Generalization of Batch Whitening by Convolutional Unit OptimizationCode0
SynerMix: Synergistic Mixup Solution for Enhanced Intra-Class Cohesion and Inter-Class Separability in Image ClassificationCode0
Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-TimeCode0
Deep Multi-View Spatial-Temporal Network for Taxi Demand PredictionCode0
BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image ClassificationCode0
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
Improving Fairness in Image Classification via SketchingCode0
Improving Confident-Classifiers For Out-of-distribution DetectionCode0
3D Wavelet Convolutions with Extended Receptive Fields for Hyperspectral Image ClassificationCode0
Improving Calibration by Relating Focal Loss, Temperature Scaling, and PropernessCode0
An In-Depth Analysis of Adversarial Discriminative Domain Adaptation for Digit ClassificationCode0
Adaptive Meta-Learning for Identification of Rover-Terrain DynamicsCode0
Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example)Code0
Improving Deep Neural Network Random Initialization Through Neuronal RewiringCode0
Deep Multimodality Model for Multi-task Multi-view LearningCode0
A Multimodal Approach For Endoscopic VCE Image Classification Using BiomedCLIP-PubMedBERTCode0
Deep Modeling and Optimization of Medical Image ClassificationCode0
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language ModelsCode0
Deep Metric Learning-Based Feature Embedding for Hyperspectral Image ClassificationCode0
Understanding and Robustifying Differentiable Architecture SearchCode0
Improving (α, f)-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distanceCode0
Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output CodesCode0
Deep Manifold Embedding for Hyperspectral Image ClassificationCode0
Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to ATARI gamesCode0
Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image ClassificationCode0
Image Data Augmentation Approaches: A Comprehensive Survey and Future directionsCode0
Dynamic Channel Selection in Self-Supervised LearningCode0
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function OptimizationCode0
Deeply-Supervised NetsCode0
Show:102550
← PrevPage 66 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