English
Related papers

Related papers: When are Post-hoc Conceptual Explanations Identifi…

200 papers

In modern machine learning, the trend of harnessing self-supervised learning to derive high-quality representations without label dependency has garnered significant attention. However, the absence of label information, coupled with the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Yan Cui , Shuhong Liu , Liuzhuozheng Li , Zhiyuan Yuan

Humans connect language and vision to perceive the world. How to build a similar connection for computers? One possible way is via visual concepts, which are text terms that relate to visually discriminative entities. We propose an…

Computer Vision and Pattern Recognition · Computer Science 2015-09-25 Chen Sun , Chuang Gan , Ram Nevatia

Recent years have witnessed increasing interests in prompt-based learning in which models can be trained on only a few annotated instances, making them suitable in low-resource settings. When using prompt-based learning for text…

Computation and Language · Computer Science 2023-05-11 Hongjing Li , Hanqi Yan , Yanran Li , Li Qian , Yulan He , Lin Gui

Large multimodal models such as Stable Diffusion can generate, detect, and classify new visual concepts after fine-tuning just a single word embedding. Do models learn similar words for the same concepts (i.e. <orange-cat> = orange + cat)?…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Brandon Trabucco , Max Gurinas , Kyle Doherty , Ruslan Salakhutdinov

The opaque reasoning of Graph Neural Networks induces a lack of human trust. Existing graph network explainers attempt to address this issue by providing post-hoc explanations, however, they fail to make the model itself more interpretable.…

To interpret the meanings of colors in visualizations of categorical information, people must determine how distinct colors correspond to different concepts. This process is easier when assignments between colors and concepts in…

Human-Computer Interaction · Computer Science 2019-10-08 Ragini Rathore , Zachary Leggon , Laurent Lessard , Karen B. Schloss

Concept-based explainable AI is promising as a tool to improve the understanding of complex models at the premises of a given user, viz.\ as a tool for personalized explainability. An important class of concept-based explainability methods…

Understanding how the human brain represents visual concepts, and in which brain regions these representations are encoded, remains a long-standing challenge. Decades of work have advanced our understanding of visual representations, yet…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Navve Wasserman , Matias Cosarinsky , Yuval Golbari , Aude Oliva , Antonio Torralba , Tamar Rott Shaham , Michal Irani

We consider the problem of finding plausible knowledge that is missing from a given ontology, as a generalisation of the well-studied taxonomy expansion task. One line of work treats this task as a Natural Language Inference (NLI) problem,…

Computation and Language · Computer Science 2024-03-27 Na Li , Thomas Bailleux , Zied Bouraoui , Steven Schockaert

Post-hoc interpretability approaches have been proven to be powerful tools to generate explanations for the predictions made by a trained black-box model. However, they create the risk of having explanations that are a result of some…

Machine Learning · Computer Science 2021-04-14 Thibault Laugel , Marie-Jeanne Lesot , Christophe Marsala , Xavier Renard , Marcin Detyniecki

Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing complementary visual explanations that could localize the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Cristiano Patrício , Luís F. Teixeira , João C. Neves

By now there is substantial evidence that deep learning models learn certain human-interpretable features as part of their internal representations of data. As having the right (or wrong) concepts is critical to trustworthy machine learning…

Machine Learning · Computer Science 2023-12-29 Nicholas Konz , Charles Godfrey , Madelyn Shapiro , Jonathan Tu , Henry Kvinge , Davis Brown

Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, whose explanation quality can be…

Machine Learning · Computer Science 2020-11-10 Gregory Plumb , Maruan Al-Shedivat , Angel Alexander Cabrera , Adam Perer , Eric Xing , Ameet Talwalkar

Providing textual concept-based explanations for neurons in deep neural networks (DNNs) is of importance in understanding how a DNN model works. Prior works have associated concepts with neurons based on examples of concepts or a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Nhat Hoang-Xuan , Minh Vu , My T. Thai

Modular object-centric representations are essential for *human-like reasoning* but are challenging to obtain under spatial ambiguities, *e.g. due to occlusions and view ambiguities*. However, addressing challenges presents both theoretical…

Machine Learning · Computer Science 2025-06-10 Avinash Kori , Francesca Toni , Ben Glocker

Traditional deep learning interpretability methods which are suitable for model users cannot explain network behaviors at the global level and are inflexible at providing fine-grained explanations. As a solution, concept-based explanations…

Human-Computer Interaction · Computer Science 2022-10-26 Jinbin Huang , Aditi Mishra , Bum Chul Kwon , Chris Bryan

Traditional approaches for learning on categorical data underexploit the dependencies between columns (\aka fields) in a dataset because they rely on the embedding of data points driven alone by the classification/regression loss. In…

Machine Learning · Computer Science 2023-07-19 Zhibin Li , Piotr Koniusz , Lu Zhang , Daniel Edward Pagendam , Peyman Moghadam

Most existing interpretable methods explain a black-box model in a post-hoc manner, which uses simpler models or data analysis techniques to interpret the predictions after the model is learned. However, they (a) may derive contradictory…

Machine Learning · Computer Science 2020-01-22 Mengzhuo Guo , Qingpeng Zhang , Xiuwu Liao , Daniel Dajun Zeng

Emotion cause identification aims at identifying the potential causes that lead to a certain emotion expression in text. Several techniques including rule based methods and traditional machine learning methods have been proposed to address…

Computation and Language · Computer Science 2019-06-05 Zixiang Ding , Huihui He , Mengran Zhang , Rui Xia

Explaining black-box Artificial Intelligence (AI) models is a cornerstone for trustworthy AI and a prerequisite for its use in safety critical applications such that AI models can reliably assist humans in critical decisions. However,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-10 Poulami Sinhamahapatra , Lena Heidemann , Maureen Monnet , Karsten Roscher
‹ Prev 1 8 9 10 Next ›