← Learning Types
Deep Learning › Learning Types ›

Adversarial Learning

2063 directly classified papers

Papers per year

Papers

WCP: Worst-Case Perturbations for Semi-Supervised Deep Learning CVPR 2020
Defending Against Universal Attacks Through Selective Feature Regeneration CVPR 2020
A Self-supervised Approach for Adversarial Robustness CVPR 2020
All in One Bad Weather Removal Using Architectural Search CVPR 2020
Adversarial Texture Optimization From RGB-D Scans CVPR 2020
Efficient Adversarial Training With Transferable Adversarial Examples CVPR 2020
Unpaired Image Super-Resolution Using Pseudo-Supervision CVPR 2020
Adversarial Examples Improve Image Recognition CVPR 2020
On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks CVPR 2020
Boosting the Transferability of Adversarial Samples via Attention CVPR 2020
Alleviation of Gradient Exploding in GANs: Fake Can Be Real CVPR 2020
Multi-Task Learning with Generative Adversarial Training for Multi-Passage Machine Reading Comprehension AAAI 2020
WinoGrande: An Adversarial Winograd Schema Challenge at Scale AAAI 2020
Attentive User-Engaged Adversarial Neural Network for Community Question Answering AAAI 2020
Adversarial Disentanglement with Grouped Observations AAAI 2020
FD-GAN: Generative Adversarial Networks with Fusion-Discriminator for Single Image Dehazing AAAI 2020
Adversarial Attack on Deep Product Quantization Network for Image Retrieval AAAI 2020
SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications AAAI 2020
REST: Performance Improvement of a Black Box Model via RL-Based Spatial Transformation AAAI 2020
Hierarchical Knowledge Squeezed Adversarial Network Compression AAAI 2020
Learning Transferable Adversarial Examples via Ghost Networks AAAI 2020
Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature AAAI 2020
Multi-Spectral Salient Object Detection by Adversarial Domain Adaptation AAAI 2020
Heuristic Black-Box Adversarial Attacks on Video Recognition Models AAAI 2020
Adversarial Learning of Privacy-Preserving and Task-Oriented Representations AAAI 2020