English
Related papers

Related papers: Saliency Map Verbalization: Comparing Feature Impo…

200 papers

Recent work uncovered potential flaws in \eg attribution or heatmap based saliency methods. A typical flaw is a confirmations bias, where the scores are compared to human expectation. Since measuring the quality of saliency methods is hard…

Machine Learning · Computer Science 2025-01-27 Leonid Schwenke , Martin Atzmueller

We present a novel method for reliably explaining the predictions of neural networks. We consider an explanation reliable if it identifies input features relevant to the model output by considering the input and the neighboring data points.…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Dohun Lim , Hyeonseok Lee , Sungchan Kim

Poor generalization is one symptom of models that learn to predict target variables using spuriously-correlated image features present only in the training distribution instead of the true image features that denote a class. It is often…

Computer Vision and Pattern Recognition · Computer Science 2021-02-11 Joseph D. Viviano , Becks Simpson , Francis Dutil , Yoshua Bengio , Joseph Paul Cohen

Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps. By contrast, masking-based methods optimize a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Hanwei Zhang , Felipe Torres , Ronan Sicre , Yannis Avrithis , Stephane Ayache

The expansion of explainable artificial intelligence as a field of research has generated numerous methods of visualizing and understanding the black box of a machine learning model. Attribution maps are generally used to highlight the…

Machine Learning · Computer Science 2023-08-02 Ian E. Nielsen , Ravi P. Ramachandran , Nidhal Bouaynaya , Hassan M. Fathallah-Shaykh , Ghulam Rasool

Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying "important" pixels in an input image. However, the development and adoption of these methods…

Machine Learning · Computer Science 2022-06-20 Joon Sik Kim , Gregory Plumb , Ameet Talwalkar

Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects. Neural networks for saliency estimation require ground truth saliency maps for training which are usually achieved via…

Computer Vision and Pattern Recognition · Computer Science 2021-07-21 Carola Figueroa-Flores , David Berga , Joost van der Weijer , Bogdan Raducanu

Identifying the salience (i.e. importance) of discourse units is an important task in language understanding. While events play important roles in text documents, little research exists on analyzing their saliency status. This paper…

Computation and Language · Computer Science 2018-09-10 Zhengzhong Liu , Chenyan Xiong , Teruko Mitamura , Eduard Hovy

Interpretable machine learning and explainable artificial intelligence have become essential in many applications. The trade-off between interpretability and model performance is the traitor to developing intrinsic and model-agnostic…

Machine Learning · Computer Science 2023-09-06 Chiara Balestra , Bin Li , Emmanuel Müller

While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel…

Computation and Language · Computer Science 2022-11-16 Lijie Wang , Yaozong Shen , Shuyuan Peng , Shuai Zhang , Xinyan Xiao , Hao Liu , Hongxuan Tang , Ying Chen , Hua Wu , Haifeng Wang

In this paper, we propose a data-free method of extracting Impressions of each class from the classifier's memory. The Deep Learning regime empowers classifiers to extract distinct patterns (or features) of a given class from training data,…

Computer Vision and Pattern Recognition · Computer Science 2020-08-03 Sravanti Addepalli , Dipesh Tamboli , R. Venkatesh Babu , Biplab Banerjee

Saliency maps are widely used for visual explanations in deep learning, but a fundamental lack of consensus persists regarding their intended purpose and alignment with diverse user queries. This ambiguity hinders the effective evaluation…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Yehonatan Elisha , Seffi Cohen , Oren Barkan , Noam Koenigstein

The field of eXplainable artificial intelligence (XAI) has produced a plethora of methods (e.g., saliency-maps) to gain insight into artificial intelligence (AI) models, and has exploded with the rise of deep learning (DL). However,…

Human-Computer Interaction · Computer Science 2024-04-12 Marvin Pafla , Kate Larson , Mark Hancock

Word-level saliency explanations ("heat maps over words") are often used to communicate feature-attribution in text-based models. Recent studies found that superficial factors such as word length can distort human interpretation of the…

Computation and Language · Computer Science 2023-05-09 Alon Jacovi , Hendrik Schuff , Heike Adel , Ngoc Thang Vu , Yoav Goldberg

Saliency maps can explain how deep neural networks classify images. But are they actually useful for humans? The present systematic review of 68 user studies found that while saliency maps can enhance human performance, null effects or even…

Human-Computer Interaction · Computer Science 2024-08-20 Romy Müller

Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification. In the current paper, we propose an approach which…

Computer Vision and Pattern Recognition · Computer Science 2021-02-04 Carola Figueroa-Flores , Bogdan Raducanu , David Berga , Joost van de Weijer

Existing saliency-guided training approaches improve model generalization by incorporating a loss term that compares the model's class activation map (CAM) for a sample's true-class ({\it i.e.}, correct-label class) against a human…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Jacob Piland , Chris Sweet , Adam Czajka

Determining the relative importance of the elements in a sentence is a key factor for effortless natural language understanding. For human language processing, we can approximate patterns of relative importance by measuring reading…

Computation and Language · Computer Science 2021-06-08 Nora Hollenstein , Lisa Beinborn

Neural image/video captioning models can generate accurate descriptions, but their internal process of mapping regions to words is a black box and therefore difficult to explain. Top-down neural saliency methods can find important regions…

Computer Vision and Pattern Recognition · Computer Science 2017-09-12 Vasili Ramanishka , Abir Das , Jianming Zhang , Kate Saenko

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