English
Related papers

Related papers: DANCE: Enhancing saliency maps using decoys

200 papers

In high-stakes applications of machine learning models, interpretability methods provide guarantees that models are right for the right reasons. In medical imaging, saliency maps have become the standard tool for determining whether a…

Computer Vision and Pattern Recognition · Computer Science 2019-12-05 Jacob Pfau , Albert T. Young , Maria L. Wei , Michael J. Keiser

Human vision is naturally more attracted by some regions within their field of view than others. This intrinsic selectivity mechanism, so-called visual attention, is influenced by both high- and low-level factors; such as the global…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Mohamed Amine Kerkouri , Marouane Tliba , Aladine Chetouani , Rachid Harba

Despite the tremendous achievements of deep convolutional neural networks (CNNs) in many computer vision tasks, understanding how they actually work remains a significant challenge. In this paper, we propose a novel two-step understanding…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Heyi Li , Yunke Tian , Klaus Mueller , Xin Chen

It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the…

Machine Learning · Computer Science 2024-07-22 Arshia Soltani Moakhar , Eugenia Iofinova , Elias Frantar , Dan Alistarh

Saliency map estimation in computer vision aims to estimate the locations where people gaze in images. Since people tend to look at objects in images, the parameters of the model pretrained on ImageNet for image classification are useful…

Computer Vision and Pattern Recognition · Computer Science 2018-07-30 Taiki Oyama , Takao Yamanaka

We propose a novel unsupervised game-theoretic salient object detection algorithm that does not require labeled training data. First, saliency detection problem is formulated as a non-cooperative game, hereinafter referred to as Saliency…

Computer Vision and Pattern Recognition · Computer Science 2018-08-01 Yu Zeng , Huchuan Lu , Ali Borji , Mengyang Feng

Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically…

Image and Video Processing · Electrical Eng. & Systems 2021-06-29 Zixuan Liu , Ehsan Adeli , Kilian M. Pohl , Qingyu Zhao

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…

Computer Vision and Pattern Recognition · Computer Science 2020-01-06 Dasom Seo , Kanghan Oh , Il-Seok Oh

Saliency methods are widely used to visualize which input features are deemed relevant to a model's prediction. However, their visual plausibility can obscure critical limitations. In this work, we propose a diagnostic test for class…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Dane Williamson , Yangfeng Ji , Matthew Dwyer

We propose a framework inspired by biological vision systems to produce saliency maps of digital images. Well-known computational models for receptive fields of areas in the visual cortex that are specialized for color and orientation…

Computer Vision and Pattern Recognition · Computer Science 2022-05-04 Reza Hojjaty Saeedy , Richard A. Messner

Existing retrieval-augmented approaches for Dense Video Captioning (DVC) often fail to achieve accurate temporal segmentation aligned with true event boundaries, as they rely on heuristic strategies that overlook ground truth event…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Seung hee Choi , MinJu Jeon , Hyunwoo Oh , Jihwan Lee , Dong-Jin Kim

Saliency maps are a popular approach for explaining classifications of (convolutional) neural networks. However, it remains an open question as to how best to evaluate salience maps, with three families of evaluation methods commonly being…

Human-Computer Interaction · Computer Science 2025-04-25 Felix Kares , Timo Speith , Hanwei Zhang , Markus Langer

The role of long- and short-term dynamics towards salient object detection in videos is under-researched. We present a Transformer-based approach to learn a joint representation of video frames and past saliency information. Our model…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Theodor Wulff , Fares Abawi , Philipp Allgeuer , Stefan Wermter

Traditional saliency map methods, popularized in computer vision, highlight individual points (pixels) of the input that contribute the most to the model's output. However, in time series, they offer limited insights, as semantically…

Machine Learning · Computer Science 2026-05-08 Christodoulos Kechris , Jonathan Dan , David Atienza

Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze the saliency maps of…

Machine Learning · Computer Science 2021-04-23 Bogdan Musat , Razvan Andonie

Salient object detection has seen remarkable progress driven by deep learning techniques. However, most of deep learning based salient object detection methods are black-box in nature and lacking in interpretability. This paper proposes the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-21 Huaxin Xiao , Jiashi Feng , Yunchao Wei , Maojun Zhang

Learning new concepts from a few of samples is a standard challenge in computer vision. The main directions to improve the learning ability of few-shot training models include (i) a robust similarity learning and (ii) generating or…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Hongguang Zhang , Jing Zhang , Piotr Koniusz

We aim at segmenting small organs (e.g., the pancreas) from abdominal CT scans. As the target often occupies a relatively small region in the input image, deep neural networks can be easily confused by the complex and variable background.…

Computer Vision and Pattern Recognition · Computer Science 2018-04-10 Qihang Yu , Lingxi Xie , Yan Wang , Yuyin Zhou , Elliot K. Fishman , Alan L. Yuille

With the growing availability of databases for face presentation attack detection, researchers are increasingly focusing on video-based face anti-spoofing methods that involve hundreds to thousands of images for training the models.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 Usman Muhammad , Mourad Oussalah , Jorma Laaksonen

In this paper we address the problem of unsupervised localization of objects in single images. Compared to previous state-of-the-art method our method is fully unsupervised in the sense that there is no prior instance level or category…

Computer Vision and Pattern Recognition · Computer Science 2018-04-12 Hakan Karaoguz , Patric Jensfelt