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 81268150 of 10420 papers

TitleStatusHype
Leveraging Model Interpretability and Stability to increase Model RobustnessCode0
Gated Linear NetworksCode0
Meta-learning algorithms for Few-Shot Computer VisionCode0
Hidden Trigger Backdoor AttacksCode1
RandAugment: Practical automated data augmentation with a reduced search spaceCode2
XNOR-Net++: Improved Binary Neural Networks0
Fusion of Convolutional Neural Network and Statistical Features for Texture classification0
Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional NetworkCode1
Test-Time Training with Self-Supervision for Generalization under Distribution ShiftsCode0
Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image ClassificationCode0
Genetic Programming and Gradient Descent: A Memetic Approach to Binary Image ClassificationCode0
Noisy Batch Active Learning with Deterministic AnnealingCode0
Impact of Low-bitwidth Quantization on the Adversarial Robustness for Embedded Neural Networks0
Interpreting Undesirable Pixels for Image Classification on Black-Box Models0
Urban Sound Tagging using Convolutional Neural NetworksCode0
Adaptive Binary-Ternary Quantization0
Two-stage Image Classification Supervised by a Single Teacher Single Student ModelCode0
Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network0
Balanced Binary Neural Networks with Gated ResidualCode0
A Base Model Selection Methodology for Efficient Fine-Tuning0
Improved Training Speed, Accuracy, and Data Utilization via Loss Function Optimization0
Adapting to Label Shift with Bias-Corrected Calibration0
COMBINED FLEXIBLE ACTIVATION FUNCTIONS FOR DEEP NEURAL NETWORKS0
Improving Confident-Classifiers For Out-of-distribution DetectionCode0
MANIFOLD FORESTS: CLOSING THE GAP ON NEURAL NETWORKS0
Show:102550
← PrevPage 326 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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified