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 91769200 of 10420 papers

TitleStatusHype
Improving robustness to corruptions with multiplicative weight perturbationsCode0
MultiGrain: a unified image embedding for classes and instancesCode0
Representation Learning by Detecting Incorrect Location EmbeddingsCode0
CECT: Controllable Ensemble CNN and Transformer for COVID-19 Image ClassificationCode0
Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase SamplingCode0
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical EnergyCode0
Allowing humans to interactively guide machines where to look does not always improve human-AI team's classification accuracyCode0
MGIC: Multigrid-in-Channels Neural Network ArchitecturesCode0
Multigrid Neural ArchitecturesCode0
A Bayesian Approach to OOD Robustness in Image ClassificationCode0
Multi-Head Multi-Loss Model CalibrationCode0
Perceptual Quality-preserving Black-Box Attack against Deep Learning Image ClassifiersCode0
Dilated Residual NetworksCode0
Percival: Making In-Browser Perceptual Ad Blocking Practical With Deep LearningCode0
Rethinking deep active learning: Using unlabeled data at model trainingCode0
Improving the Efficiency of Human-in-the-Loop Systems: Adding Artificial to Human ExpertsCode0
Improving the Gating Mechanism of Recurrent Neural NetworksCode0
Performance Evaluation of Low-Cost Machine Vision Cameras for Image-Based Grasp VerificationCode0
Improving the repeatability of deep learning models with Monte Carlo dropoutCode0
Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative EvaluationCode0
Improving the trustworthiness of image classification models by utilizing bounding-box annotationsCode0
Multi-Label Classification of Thoracic Diseases using Dense Convolutional Network on Chest RadiographsCode0
Improving Transferability of Adversarial Examples with Input DiversityCode0
Performance of GAN-based augmentation for deep learning COVID-19 image classificationCode0
DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and L_0 RegularizationCode0
Show:102550
← PrevPage 368 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
10RevCol-HTop 1 Accuracy90Unverified