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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 7201–7250 of 10420 papers

TitleStatusHype
Classification with 2-D Convolutional Neural Networks for breast cancer diagnosisCode0
C2G-Net: Exploiting Morphological Properties for Image Classification—0
Discretization-Aware Architecture SearchCode1
Deep Reinforcement Learning and its Neuroscientific Implications—0
SpinalNet: Deep Neural Network with Gradual InputCode1
GOLD-NAS: Gradual, One-Level, DifferentiableCode1
Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches—0
Bespoke vs. Prêt-à-Porter Lottery Tickets: Exploiting Mask Similarity for Trainable Sub-Network Finding—0
Deep Learning for Apple Diseases: Classification and Identification—0
Learning the Prediction Distribution for Semi-Supervised Learning with Normalising FlowsCode0
Adaptive Risk Minimization: Learning to Adapt to Domain ShiftCode1
Weakly Supervised Domain Adaptation for Built-up Region Segmentation in Aerial and Satellite ImageryCode0
Self-Challenging Improves Cross-Domain GeneralizationCode1
On Connections between Regularizations for Improving DNN Robustness—0
Self-Supervised GAN CompressionCode0
Towards Robust Deep Learning with Ensemble Networks and Noisy Layers—0
Self-supervised Neural Architecture Search—0
CacheNet: A Model Caching Framework for Deep Learning Inference on the Edge—0
Selecting Regions of Interest in Large Multi-Scale Images for Cancer Pathology—0
Interactive Knowledge Distillation—0
Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring—0
Surrogate-assisted Particle Swarm Optimisation for Evolving Variable-length Transferable Blocks for Image Classification—0
A Novel BGCapsule Network for Text Classification—0
Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?Code0
Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture—0
Rethinking Channel Dimensions for Efficient Model DesignCode1
A deep primal-dual proximal network for image restoration—0
Learning ordered pooling weights in image classificationCode0
Image Analysis Based on Nonnegative/Binary Matrix Factorization—0
Robust and Accurate Authorship Attribution via Program Normalization—0
Estimation with Uncertainty via Conditional Generative Adversarial Networks—0
Robustifying the Deployment of tinyML Models for Autonomous mini-vehicles—0
Measuring Robustness to Natural Distribution Shifts in Image ClassificationCode1
HACT-Net: A Hierarchical Cell-to-Tissue Graph Neural Network for Histopathological Image Classification—0
SeqVAT: Virtual Adversarial Training for Semi-Supervised Sequence Labeling—0
Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions—0
Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution—0
Ontology-guided Semantic Composition for Zero-Shot LearningCode1
Early-Learning Regularization Prevents Memorization of Noisy LabelsCode1
Training highly effective connectivities within neural networks with randomly initialized, fixed weightsCode0
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over ModulesCode1
Improving robustness against common corruptions by covariate shift adaptationCode1
Theory-Inspired Path-Regularized Differential Network Architecture SearchCode1
Explainable 3D Convolutional Neural Networks by Learning Temporal Transformations—0
Conditional Classification: A Solution for Computational Energy Reduction—0
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network ArchitecturesCode1
Heteroskedastic and Imbalanced Deep Learning with Adaptive RegularizationCode1
Harnessing Adversarial Distances to Discover High-Confidence ErrorsCode0
Matrix Shuffle-Exchange Networks for Hard 2D TasksCode0
Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image Classification—0
Show:102550
← PrevPage 145 of 209Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10RevCol-HTop 1 Accuracy90—Unverified