paper-with-me

홈 › Papers

Detecting GAN generated errors

2019-12-02 · Xiru Zhu, Fengdi Che, Tianzi Yang, Tzuyang Yu, David Meger, Gregory Dudek

Despite an impressive performance from the latest GAN for generating hyper-realistic images, GAN discriminators have difficulty evaluating the quality of an individual generated sample. This is because the task of evaluating the quality of a generated image differs from deciding if an image is real or fake. A generated image could be perfect except in a single area but still be detected as fake. Instead, we propose a novel approach for detecting where errors occur within a generated image. By collaging real images with generated images, we compute for each pixel, whether it belongs to the real distribution or generated distribution. Furthermore, we leverage attention to model long-range dependency; this allows detection of errors which are reasonable locally but not holistically. For evaluation, we show that our error detection can act as a quality metric for an individual image, unlike FID and IS. We leverage Improved Wasserstein, BigGAN, and StyleGAN to show a ranking based on our metric correlates impressively with FID scores. Our work opens the door for better understanding of GAN and the ability to select the best samples from a GAN model.

📄 PDF Abstract BibTeX arXiv:1912.00527

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Conditional Batch Normalization Conditional Batch Normalization (CBN) is a class-conditional variant of batch normalization. The key idea is to…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
TTUR The Two Time-scale Update Rule (TTUR) is an update rule for generative adversarial networks trained with stochastic gradient descent. TTUR has an individual learning rate for…
GAN Hinge Loss The GAN Hinge Loss is a hinge loss based loss function for [generative adversarial…
Residual Connection 설명 없음
Non-Local Operation A Non-Local Operation is a component for capturing long-range dependencies with deep neural networks. It is a generalization of the classical non-local mean operation in…

Similar Papers 제목 키워드 기반

Detecting Errors through Ensembling Prompts (DEEP): An End-to-End LLM Framework for Detecting Factual Errors

2024-06-18 · Alex Chandler, Devesh Surve, Hui Su

Accurate text summarization is one of the most common and important tasks performed by Large Language Models, where the costs of human review for an entire document may be high, but the costs of errors in summarization m…

HallucinationLanguage ModelingLanguage ModellingLarge Language Model+1

Detecting over/under-translation errors for determining adequacy in human translations

2021-04-01 · Prabhakar Gupta, Ridha Juneja, Anil Nelakanti, Tamojit Chatterjee

We present a novel approach to detecting over and under translations (OT/UT) as part of adequacy error checks in translation evaluation. We do not restrict ourselves to machine translation (MT) outputs and specifically t…

Language ModelingLanguage ModellingMachine TranslationTranslation

Cipher: A Prototype Game-with-a-Purpose for Detecting Errors in Text

2020-05-01 · LREC 2020 5 · Liang Xu, Jon Chamberlain

Errors commonly exist in machine-generated documents and publication materials; however, some correction algorithms do not perform well for complex errors and it is costly to employ humans to do the task. To solve the pr…

FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios

2023-07-25 · I-Chun Chern, Steffi Chern, Shiqi Chen, Weizhe Yuan 외

The emergence of generative pre-trained models has facilitated the synthesis of high-quality text, but it has also posed challenges in identifying factual errors in the generated text. In particular: (1) A wider range of…

Code GenerationFact CheckingMathematical Reasoning

Probabilistic Soundness Guarantees in LLM Reasoning Chains

2025-07-17 · Weiqiu You, Anton Xue, Shreya Havaldar, Delip Rao 외 arxiv

In reasoning chains generated by large language models (LLMs), initial errors often propagate and undermine the reliability of the final conclusion. Current LLM-based error detection methods often fail to detect propagat…