paper-with-me

Papers

Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows

2023-09-21 · NeurIPS 2023 11

Achieving a balance between image quality (precision) and diversity (recall) is a significant challenge in the domain of generative models. Current state-of-the-art models primarily rely on optimizing heuristics, such as the Fr\'echet Inception Distance. While recent developments have introduced principled methods for evaluating precision and recall, they have yet to be successfully integrated into the training of generative models. Our main contribution is a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows, which explicitly optimizes a user-defined trade-off between precision and recall. More precisely, we show that achieving a specified precision-recall trade-off corresponds to minimizing a unique $f$-divergence from a family we call the \mbox{\em PR-divergences}. Conversely, any $f$-divergence can be written as a linear combination of PR-divergences and corresponds to a weighted precision-recall trade-off. Through comprehensive evaluations, we show that our approach improves the performance of existing state-of-the-art models like BigGAN in terms of either precision or recall when tested on datasets such as ImageNet.Submission Number: 14072

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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…
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 $x$…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Six Ways To Communicate To Someone At Expedia Via Phone And Email's. To communicate or get human at Expedia, the quickest option is typically to call their customer service at +1-888-829-0881 or +1(805) 330 (4056). You can also use the live chat…
((Reservation@Faqs))How do I cancel a reservation on Expedia? How do I cancel a reservation on Expedia? +1^888^829^0881° oR +1^888^829^0881 – Need to cancel your Expedia reservation quickly and without hassle? This step-by-step guide…
Adam 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…
Non-Local Block A Non-Local Block is an image block module used in neural networks that wraps a non-local operation. We can define a…

Similar Papers 제목 키워드 기반

Training Normalizing Flows with the Precision-Recall Divergence

2023-02-01 · Alexandre Verine, Benjamin Negrevergne, Muni Sreenivas Pydi, Yann Chevaleyre

Generative models can have distinct mode of failures like mode dropping and low quality samples, which cannot be captured by a single scalar metric. To address this, recent works propose evaluating generative models usin…

Assessing Generative Models via Precision and Recall

2018-05-31 · NeurIPS 2018 12 · Mehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic, Olivier Bousquet 외

Recent advances in generative modeling have led to an increased interest in the study of statistical divergences as means of model comparison. Commonly used evaluation methods, such as the Frechet Inception Distance (FID…

Precision-Recall Curves Using Information Divergence Frontiers

2019-05-26 · Josip Djolonga, Mario Lucic, Marco Cuturi, Olivier Bachem 외

Despite the tremendous progress in the estimation of generative models, the development of tools for diagnosing their failures and assessing their performance has advanced at a much slower pace. Recent developments have …

Image GenerationInformation RetrievalRetrieval

Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation

2025-05-19 · Sungmin Cha, Kyunghyun Cho

Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented--enabling smaller st…

Knowledge DistillationLanguage ModelingLanguage Modelling

How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models

2021-02-17 · Ahmed M. Alaa, Boris van Breugel, Evgeny Saveliev, Mihaela van der Schaar

Devising domain- and model-agnostic evaluation metrics for generative models is an important and as yet unresolved problem. Most existing metrics, which were tailored solely to the image synthesis setup, exhibit a limite…

Binary ClassificationDiversityImage Generation