paper-with-me

홈 › Papers

Believe The HiPe: Hierarchical Perturbation for Fast, Robust, and Model-Agnostic Saliency Mapping

2021-02-22 · Jessica Cooper, Ognjen Arandjelović, David J Harrison

Understanding the predictions made by Artificial Intelligence (AI) systems is becoming more and more important as deep learning models are used for increasingly complex and high-stakes tasks. Saliency mapping -- a popular visual attribution method -- is one important tool for this, but existing formulations are limited by either computational cost or architectural constraints. We therefore propose Hierarchical Perturbation, a very fast and completely model-agnostic method for interpreting model predictions with robust saliency maps. Using standard benchmarks and datasets, we show that our saliency maps are of competitive or superior quality to those generated by existing model-agnostic methods -- and are over 20 times faster to compute.

📄 PDF Abstract BibTeX arXiv:2103.05108

Code (1)

jessicamarycooper/Hierarchical-Perturbation 공식 구현 pytorch

Similar Papers 제목 키워드 기반

HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents

2026-02-18 · Jiangweizhi Peng, Yuanxin Liu, Ruida Zhou, Charles Fleming 외 arxiv

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before r…

Hierarchical Reinforcement Learning

HiPerformer: A High-Performance Global-Local Segmentation Model with Modular Hierarchical Fusion Strategy

2025-09-24 · Dayu Tan, Zhenpeng Xu, Yansen Su, Xin Peng 외 arxiv

Both local details and global context are crucial in medical image segmentation, and effectively integrating them is essential for achieving high accuracy. However, existing mainstream methods based on CNN-Transformer hy…

Medical Image Segmentation

Enhancing the Self-Universality for Transferable Targeted Attacks

2022-09-08 · CVPR 2023 1 · Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

In this paper, we propose a novel transfer-based targeted attack method that optimizes the adversarial perturbations without any extra training efforts for auxiliary networks on training data. Our new attack method is pr…

Hierarchical Explanations for Video Action Recognition

2023-01-01 · Sadaf Gulshad, Teng Long, Nanne van Noord

To interpret deep neural networks, one main approach is to dissect the visual input and find the prototypical parts responsible for the classification. However, existing methods often ignore the hierarchical relationship…

Action ClassificationAction RecognitionExplainable artificial intelligenceTemporal Action Localization

Extracting and Validating Explanatory Word Archipelagoes using Dual Entropy

2020-02-22 · Yukio Ohsawa, Teruaki Hayashi

The logical connectivity of text is represented by the connectivity of words that form archipelagoes. Here, each archipelago is a sequence of islands of the occurrences of a certain word. An island here means the local s…