paper-with-me

홈 › Papers

Counterexample-Guided Data Augmentation

2018-05-17 · Tommaso Dreossi, Shromona Ghosh, Xiangyu Yue, Kurt Keutzer, Alberto Sangiovanni-Vincentelli, Sanjit A. Seshia

We present a novel framework for augmenting data sets for machine learning based on counterexamples. Counterexamples are misclassified examples that have important properties for retraining and improving the model. Key components of our framework include a counterexample generator, which produces data items that are misclassified by the model and error tables, a novel data structure that stores information pertaining to misclassifications. Error tables can be used to explain the model's vulnerabilities and are used to efficiently generate counterexamples for augmentation. We show the efficacy of the proposed framework by comparing it to classical augmentation techniques on a case study of object detection in autonomous driving based on deep neural networks.

📄 PDF Abstract BibTeX arXiv:1805.06962

Code (2)

dreossi/analyzeNN 공식 구현
BerkeleyLearnVerify/VerifAI tf

Tasks

Autonomous DrivingData Augmentationobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Counterexample Guided Learning in the Large using Reasoning Agents

2026-06-09 · Hongyi Liu, Frederic Sala, Thomas Reps, Adithya Murali arxiv

LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-specific, and difficult to control. We approach this challenge by asking…

Program Synthesis

A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks

2023-01-26 · David Boetius, Stefan Leue, Tobias Sutter

Counterexample-guided repair aims at creating neural networks with mathematical safety guarantees, facilitating the application of neural networks in safety-critical domains. However, whether counterexample-guided repair…

Open-Ended Question Answering

Are There Good Mistakes? A Theoretical Analysis of CEGIS

2014-07-21 · Susmit Jha, Sanjit A. Seshia

Counterexample-guided inductive synthesis CEGIS is used to synthesize programs from a candidate space of programs. The technique is guaranteed to terminate and synthesize the correct program if the space of candidate pro…

Logic Guided Genetic Algorithms

2020-10-21 · Dhananjay Ashok, Joseph Scott, Sebastian Wetzel, Maysum Panju 외

We present a novel Auxiliary Truth enhanced Genetic Algorithm (GA) that uses logical or mathematical constraints as a means of data augmentation as well as to compute loss (in conjunction with the traditional MSE), with …

Data AugmentationSymbolic Regression

QBF Solving by Counterexample-guided Expansion

2016-11-04 · Roderick Bloem, Nicolas Braud-Santoni, Vedad Hadzic

We introduce a novel generalization of Counterexample-Guided Inductive Synthesis (CEGIS) and instantiate it to yield a novel, competitive algorithm for solving Quantified Boolean Formulas (QBF). Current QBF solvers based…