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 91019125 of 10420 papers

TitleStatusHype
Discriminative Feature Learning through Feature Distance LossCode0
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language ModelsCode0
MULLER: Multilayer Laplacian Resizer for VisionCode0
Multiaccuracy: Black-Box Post-Processing for Fairness in ClassificationCode0
Discriminative Active LearningCode0
Improving (α, f)-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distanceCode0
Multi-Agent Image Classification via Reinforcement LearningCode0
A Simple Single-Scale Vision Transformer for Object Localization and Instance SegmentationCode0
Improving Calibration by Relating Focal Loss, Temperature Scaling, and PropernessCode0
Multi-aspect Knowledge Distillation with Large Language ModelCode0
Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example)Code0
Multi-Attribute Open Set RecognitionCode0
Improving Confident-Classifiers For Out-of-distribution DetectionCode0
Discriminability-Transferability Trade-Off: An Information-Theoretic PerspectiveCode0
Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing FlowsCode0
A Simple Approach to Adversarial Robustness in Few-shot Image ClassificationCode0
Improving Deep Neural Network Random Initialization Through Neuronal RewiringCode0
All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image ClassificationCode0
Discrete Representations Strengthen Vision Transformer RobustnessCode0
Certified Defenses against Adversarial ExamplesCode0
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge IntelligenceCode0
Improving Fairness in Image Classification via SketchingCode0
PCANet: A Simple Deep Learning Baseline for Image Classification?Code0
S3Pool: Pooling with Stochastic Spatial SamplingCode0
Show:102550
← PrevPage 365 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