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 79517975 of 10420 papers

TitleStatusHype
Constrained Linear Data-feature Mapping for Image ClassificationCode0
Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion ReductionCode0
Federated Learning with Bayesian Differential Privacy0
Optimizing Data Usage via Differentiable RewardsCode0
Attack Agnostic Statistical Method for Adversarial Detection0
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation AnchoringCode1
Rethinking Normalization and Elimination Singularity in Neural NetworksCode0
Classification-driven Single Image Dehazing0
EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble TransformationsCode0
Beyond Synthetic Noise: Deep Learning on Controlled Noisy LabelsCode1
AutoShrink: A Topology-aware NAS for Discovering Efficient Neural ArchitectureCode0
Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural NetworksCode0
Regularizing Neural Networks by Stochastically Training Layer EnsemblesCode0
Quantization NetworksCode0
Adversarial Examples Improve Image RecognitionCode0
MSD: Multi-Self-Distillation Learning via Multi-classifiers within Deep Neural Networks0
AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning0
Outside the Box: Abstraction-Based Monitoring of Neural NetworksCode0
MetH: A family of high-resolution and variable-shape image challengesCode0
Deep Learning based HEp-2 Image Classification: A Comprehensive Review0
Inspect Transfer Learning Architecture with Dilated Convolution0
Auto-Precision Scaling for Distributed Deep LearningCode0
Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation ApproachCode0
Rethinking deep active learning: Using unlabeled data at model trainingCode0
IC-Network: Efficient Structure for Convolutional Neural Networks0
Show:102550
← PrevPage 319 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