paper-with-me

Papers

Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks

2018-07-31 · Dasom Seo, Kanghan Oh, Il-Seok Oh

Recently, many methods to interpret and visualize deep neural network predictions have been proposed and significant progress has been made. However, a more class-discriminative and visually pleasing explanation is required. Thus, this paper proposes a region-based approach that estimates feature importance in terms of appropriately segmented regions. By fusing the saliency maps generated from multi-scale segmentations, a more class-discriminative and visually pleasing map is obtained. We incorporate this regional multi-scale concept into a prediction difference method that is model-agnostic. An input image is segmented in several scales using the super-pixel method, and exclusion of a region is simulated by sampling a normal distribution constructed using the boundary prior. The experimental results demonstrate that the regional multi-scale method produces much more class-discriminative and visually pleasing saliency maps.

📄 PDF Abstract BibTeX arXiv:1807.11720

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Importance

Similar Papers 제목 키워드 기반

Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties

2019-11-04 · Xavier Gitiaux, Shane A. Maloney, Anna Jungbluth, Carl Shneider 외

Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific domains this is not adequate and estimatio…

BIG-bench Machine LearningSuper-Resolution

Regional Style and Color Transfer

2024-04-22 · Zhicheng Ding, Panfeng Li, Qikai Yang, Siyang Li 외

This paper presents a novel contribution to the field of regional style transfer. Existing methods often suffer from the drawback of applying style homogeneously across the entire image, leading to stylistic inconsistenc…

Style Transfer

Style Mixer: Semantic-aware Multi-Style Transfer Network

2019-10-29 · Zixuan Huang, Jinghuai Zhang, Jing Liao

Recent neural style transfer frameworks have obtained astonishing visual quality and flexibility in Single-style Transfer (SST), but little attention has been paid to Multi-style Transfer (MST) which refers to simultaneo…

Style Transfer

Local Interpretable Model Agnostic Shap Explanations for machine learning models

2022-10-10 · P. Sai Ram Aditya, Mayukha Pal

With the advancement of technology for artificial intelligence (AI) based solutions and analytics compute engines, machine learning (ML) models are getting more complex day by day. Most of these models are generally used…

Explainable Artificial Intelligence (XAI)

Extreme Image Coding via Multiscale Autoencoders With Generative Adversarial Optimization

2019-04-08 · Chao Huang, Haojie Liu, Tong Chen, Qiu Shen 외

We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the "priors" at different resolution scale to impr…

Generative Adversarial NetworkImage Compression