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 8801–8850 of 10420 papers

TitleStatusHype
On instabilities of deep learning in image reconstruction - Does AI come at a cost?Code0
Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image Classification—0
MultiGrain: a unified image embedding for classes and instancesCode0
Robust Multi-instance Learning with Stable Instances—0
Learning to see across Domains and Modalities—0
Towards a Robust Deep Neural Network in Texts: A Survey—0
Bag of Freebies for Training Object Detection Neural NetworksCode3
Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifold—0
Deep learning and face recognition: the state of the art—0
Learning From Noisy Labels By Regularized Estimation Of Annotator ConfusionCode1
Meta-CurvatureCode0
FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary—0
CHIP: Channel-wise Disentangled Interpretation of Deep Convolutional Neural NetworksCode0
Robustness Of Saak Transform Against Adversarial Attacks—0
Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks—0
Centroid-based deep metric learning for speaker recognition—0
Widely Linear Kernels for Complex-Valued Kernel Activation Functions—0
Disguised-Nets: Image Disguising for Privacy-preserving Outsourced Deep Learning—0
Meta-Amortized Variational Inference and LearningCode0
Learning Decision Trees Recurrently Through Communication—0
Precise Proximal Femur Fracture Classification for Interactive Training and Surgical Planning—0
Towards Pedestrian Detection Using RetinaNet in ECCV 2018 Wider Pedestrian Detection ChallengeCode0
Parameter-Efficient Transfer Learning for NLPCode1
Adaptive Gradient for Adversarial Perturbations Generation—0
Deep Learning Solutions for TanDEM-X-based Forest Classification—0
ColorNet: Investigating the importance of color spaces for image classificationCode0
The Efficacy of SHIELD under Different Threat Models—0
Self-Supervised Visual Representations for Cross-Modal Retrieval—0
Higher-order Count Sketch: Dimensionality Reduction That Retains Efficient Tensor Operations—0
Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networksCode0
Probabilistic Discriminative Learning with Layered Graphical ModelsCode0
Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference—0
Semantic Redundancies in Image-Classification Datasets: The 10% You Don't Need—0
Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach—0
Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 ClassificationCode0
A Push-Pull Layer Improves Robustness of Convolutional Neural Networks—0
MgNet: A Unified Framework of Multigrid and Convolutional Neural Network—0
Glyce: Glyph-vectors for Chinese Character RepresentationsCode0
Compressed Domain Image Classification Using a Dynamic-Rate Neural Network—0
CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks—0
Convolutional Neural Networks with Layer ReuseCode0
Stochastic Linear Bandits with Hidden Low Rank Structure—0
ADMM-SOFTMAX : An ADMM Approach for Multinomial Logistic RegressionCode0
Fixup Initialization: Residual Learning Without NormalizationCode0
Evaluation of Transfer Learning for Classification of: (1) Diabetic Retinopathy by Digital Fundus Photography and (2) Diabetic Macular Edema, Choroidal Neovascularization and Drusen by Optical Coherence Tomography—0
Equivariant Transformer NetworksCode0
Deep Multimodality Model for Multi-task Multi-view LearningCode0
Is Pretraining Necessary for Hyperspectral Image Classification?—0
Decoupled Greedy Learning of CNNsCode0
Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classification—0
Show:102550
← PrevPage 177 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