SOTAVerified

Robust classification

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 295 papers

TitleStatusHype
MemSeg: A semi-supervised method for image surface defect detection using differences and commonalitiesCode2
ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet AccuracyCode1
Denoising Masked AutoEncoders Help Robust ClassificationCode1
SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation GuidelinesCode1
Diffusion Models are Certifiably Robust ClassifiersCode1
Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function PerspectiveCode1
SWAD: Domain Generalization by Seeking Flat MinimaCode1
Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial TrainingCode1
Recognizing bird species in diverse soundscapes under weak supervisionCode1
RU-AI: A Large Multimodal Dataset for Machine-Generated Content DetectionCode1
Towards Robust Classification Model by Counterfactual and Invariant Data GenerationCode1
Vision Transformers are Robust LearnersCode1
If your data distribution shifts, use self-learningCode1
Robust Classification with Convolutional Prototype LearningCode1
Ev-TTA: Test-Time Adaptation for Event-Based Object RecognitionCode1
EventCLIP: Adapting CLIP for Event-based Object RecognitionCode1
HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake DetectionCode1
Imbalanced Image Classification with Complement Cross EntropyCode1
Multi-Objective Interpolation Training for Robustness to Label NoiseCode1
Proper Network Interpretability Helps Adversarial Robustness in ClassificationCode1
Robust Classification via a Single Diffusion ModelCode1
RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud ClassifiersCode1
DeepWeeds: A Multiclass Weed Species Image Dataset for Deep LearningCode1
Towards Deep Learning Models Resistant to Adversarial AttacksCode1
Towards Robust Classification with Deep Generative ForestsCode1
AlleNoise: large-scale text classification benchmark dataset with real-world label noiseCode1
An Adversarial Approach for the Robust Classification of Pneumonia from Chest RadiographsCode1
Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based ModelsCode1
Denoised Smoothing: A Provable Defense for Pretrained ClassifiersCode1
Robust-GBDT: GBDT with Nonconvex Loss for Tabular Classification in the Presence of Label Noise and Class ImbalanceCode1
Leaving Reality to Imagination: Robust Classification via Generated DatasetsCode1
Detecting Multi-Oriented Text with Corner-based Region ProposalsCode1
Dual-stage Hyperspectral Image Classification Model with Spectral SupertokenCode1
epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression RecognitionCode1
Group-wise Inhibition based Feature Regularization for Robust ClassificationCode1
Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-offCode1
Certified Adversarial Robustness via Randomized SmoothingCode1
Identifying Spurious Correlations for Robust Text ClassificationCode1
Masksembles for Uncertainty EstimationCode1
Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial RobustnessCode1
N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event CamerasCode1
PepMNet: a hybrid deep learning model for predicting peptide properties using hierarchical graph representationsCode1
Decoding visemes: improving machine lipreading—0
Adversarially Robust Classification based on GLRT—0
Deep Adaptation of Adult-Child Facial Expressions by Fusing Landmark Features—0
Adversarially Optimized Mixup for Robust Classification—0
ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression—0
Deep-RBF Networks Revisited: Robust Classification with Rejection—0
A Hilbert Space of Stationary Ergodic Processes—0
Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attacks—0
Show:102550
← PrevPage 1 of 6Next →

No leaderboard results yet.