paper-with-me

Papers

Uncertainty based Class Activation Maps for Visual Question Answering

2020-01-23 · Badri N. Patro, Mayank Lunayach, Vinay P. Namboodiri

Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates that also provide visual attention maps. Particularly, we solve for visual question answering task. We incorporate modern probabilistic deep learning methods that we further improve by using the gradients for these estimates. These have two-fold benefits: a) improvement in obtaining the certainty estimates that correlate better with misclassified samples and b) improved attention maps that provide state-of-the-art results in terms of correlation with human attention regions. The improved attention maps result in consistent improvement for various methods for visual question answering. Therefore, the proposed technique can be thought of as a recipe for obtaining improved certainty estimates and explanations for deep learning models. We provide detailed empirical analysis for the visual question answering task on all standard benchmarks and comparison with state of the art methods.

📄 PDF Abstract BibTeX arXiv:2002.10309

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningProbabilistic Deep LearningQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

U-CAM: Visual Explanation using Uncertainty based Class Activation Maps

2019-08-17 · ICCV 2019 10 · Badri N. Patro, Mayank Lunayach, Shivansh Patel, Vinay P. Namboodiri

Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates that also provide visual attention maps. Particularly, we solve f…

Deep LearningProbabilistic Deep LearningQuestion AnsweringVisual Question Answering+1

Visualizing Uncertainty: Spatial Maps of Missing and Conflicting Evidence in Deep Learning

2026-06-14 · Dong Hyun Jeong, Feng Chen, Jin-Hee Cho, Lance M. Kaplan 외 arxiv

Understanding when and why deep neural networks are uncertain is crucial for deploying reliable machine learning systems in safety-critical domains. While existing uncertainty quantification methods provide scalar measur…

GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

2021-09-02 · Oren Barkan, Omri Armstrong, Amir Hertz, Avi Caciularu 외

We present Gradient Activation Maps (GAM) - a machinery for explaining predictions made by visual similarity and classification models. By gleaning localized gradient and activation information from multiple network laye…

Classification

Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization

2021-10-12 · ICCV 2021 10 · Jinheng Xie, Cheng Luo, Xiangping Zhu, Ziqi Jin 외

We present a two-stage learning framework for weakly supervised object localization (WSOL). While most previous efforts rely on high-level feature based CAMs (Class Activation Maps), this paper proposes to localize objec…

ObjectObject LocalizationWeakly-Supervised Object Localization

Combinational Class Activation Maps for Weakly Supervised Object Localization

2019-10-12 · Seunghan Yang, Yoonhyung Kim, Youngeun Kim, Changick Kim

Weakly supervised object localization has recently attracted attention since it aims to identify both class labels and locations of objects by using image-level labels. Most previous methods utilize the activation map co…

ObjectObject LocalizationWeakly-Supervised Object Localization