Robust classification   Edit

38 papers with code • 2 benchmarks • 3 datasets

This task has no description! Would you like to contribute one?

Towards Deep Learning Models Resistant to Adversarial Attacks

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.

5,099

Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labels

4 May 2017

To highlight, RP with a CNN classifier can predict if an MNIST digit is a "one"or "not" with only 0. 25% error, and 0. 46 error across all digits, even when 50% of positive examples are mislabeled and 50% of observed positive labels are mislabeled negative examples.

1,916

SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines

14 Nov 2019

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).

571

Implicit Generation and Modeling with Energy Based Models

Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train.

242

Implicit Generation and Generalization in Energy-Based Models

20 Mar 2019

Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train.

242

Certified Adversarial Robustness via Randomized Smoothing

8 Feb 2019

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.

201

Detecting Multi-Oriented Text with Corner-based Region Proposals

8 Apr 2018

Previous approaches for scene text detection usually rely on manually defined sliding windows.

144

Imbalanced Image Classification with Complement Cross Entropy

4 Sep 2020

Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets.

109

DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning

9 Oct 2018

This work contributes the first large, public, multiclass image dataset of weed species from the Australian rangelands; allowing for the development of robust classification methods to make robotic weed control viable.

106

Robust Classification with Convolutional Prototype Learning

To improve the robustness, we propose a novel learning framework called convolutional prototype learning (CPL).

85