Robust classification
94 papers with code • 2 benchmarks • 6 datasets
Benchmarks
These leaderboards are used to track progress in Robust classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Robust classification models and implementations
CIFAR-10
MNIST-C
ModelNet40-C
DeepWeeds
N-ImageNet
WHYSHIFT
Most implemented papers
Towards Deep Learning Models Resistant to Adversarial Attacks
MadryLab/mnist_challenge
•
•
ICLR 2018
Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal.
Certified Adversarial Robustness via Randomized Smoothing
We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm.
SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines
MegviiDetection/video_analyst
•
•
Following these guidelines, we design our Fully Convolutional Siamese tracker++ (SiamFC++) by introducing both classification and target state estimation branch(G1), classification score without ambiguity(G2), tracking without prior knowledge(G3), and estimation quality score(G4).
Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
Our approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an adversarial generative model.
Unlabeled Data Improves Adversarial Robustness
yaircarmon/semisup-adv
•
•
NeurIPS 2019
We demonstrate, theoretically and empirically, that adversarial robustness can significantly benefit from semisupervised learning.
Denoised Smoothing: A Provable Defense for Pretrained Classifiers
microsoft/blackbox-smoothing
•
•
NeurIPS 2020
We present a method for provably defending any pretrained image classifier against $\ell_p$ adversarial attacks.
SWAD: Domain Generalization by Seeking Flat Minima
Domain generalization (DG) methods aim to achieve generalizability to an unseen target domain by using only training data from the source domains.
MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities
areylng/MemSeg
•
•
By comparing the similarities and differences between input samples and memory samples in the memory pool to give effective guesses about abnormal regions; In the inference phase, MemSeg directly determines the abnormal regions of the input image in an end-to-end manner.
Robust Classification with Convolutional Prototype Learning
YangHM/Convolutional-Prototype-Learning
•
•
CVPR 2018
To improve the robustness, we propose a novel learning framework called convolutional prototype learning (CPL).
Towards the first adversarially robust neural network model on MNIST
bethgelab/AnalysisBySynthesis
•
•
ICLR 2019
Despite much effort, deep neural networks remain highly susceptible to tiny input perturbations and even for MNIST, one of the most common toy datasets in computer vision, no neural network model exists for which adversarial perturbations are large and make semantic sense to humans.
