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 30013025 of 10420 papers

TitleStatusHype
Deformable Kernels: Adapting Effective Receptive Fields for Object DeformationCode0
Improving Generalization of Batch Whitening by Convolutional Unit OptimizationCode0
Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck ModelsCode0
Improving model calibration with accuracy versus uncertainty optimizationCode0
Improving Fairness in Image Classification via SketchingCode0
Benchmarking Robust Self-Supervised Learning Across Diverse Downstream TasksCode0
Analysis of Confident-Classifiers for Out-of-distribution DetectionCode0
Benchmarking Perturbation-based Saliency Maps for Explaining Atari AgentsCode0
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output CodesCode0
Improving Deep Neural Network Random Initialization Through Neuronal RewiringCode0
Defense Against Model Stealing Based on Account-Aware Distribution DiscrepancyCode0
Defense against Adversarial Attacks Using High-Level Representation Guided DenoiserCode0
Representation Learning by Detecting Incorrect Location EmbeddingsCode0
Improving Confident-Classifiers For Out-of-distribution DetectionCode0
Improving Generalization and Convergence by Enhancing Implicit RegularizationCode0
Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel ClassificationCode0
Dimensionality-Driven Learning with Noisy LabelsCode0
Improving (α, f)-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distanceCode0
Benchmarking Large Language Models for Image Classification of Marine MammalsCode0
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language ModelsCode0
Improving Calibration by Relating Focal Loss, Temperature Scaling, and PropernessCode0
Defending Against Physically Realizable Attacks on Image ClassificationCode0
BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of AttentionCode0
Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example)Code0
Show:102550
← PrevPage 121 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
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