English
Related papers

Related papers: Locally Testing Model Detections for Semantic Glob…

200 papers

Deep learning models for natural language processing (NLP) are inherently complex and often viewed as black box in nature. This paper develops an approach for interpreting convolutional neural networks for text classification problems by…

Computation and Language · Computer Science 2021-07-12 Wei Zhao , Rahul Singh , Tarun Joshi , Agus Sudjianto , Vijayan N. Nair

Deep learning models have achieved strong performance in medical image analysis, but their internal decision processes remain difficult to interpret. Concept Bottleneck Models (CBMs) partially address this limitation by structuring…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Getamesay Dagnaw , Xuefei Yin , Muhammad Hassan Maqsood , Yanming Zhu , Alan Wee-Chung Liew

Interpreting the internal activations of neural networks can produce more faithful explanations of their behavior, but is difficult due to the complex structure of activation space. Existing approaches to scalable interpretability use…

Artificial Intelligence · Computer Science 2025-12-18 Vincent Huang , Dami Choi , Daniel D. Johnson , Sarah Schwettmann , Jacob Steinhardt

Autonomous driving (AD) and advanced driver assistance systems (ADAS) increasingly utilize deep neural networks (DNNs) for improved perception or planning. Nevertheless, DNNs are quite brittle when the data distribution during inference…

Computer Vision and Pattern Recognition · Computer Science 2023-03-10 Fabian Woitschek , Georg Schneider

Recently, deep neural networks (DNNs) have achieved great success in semantically challenging NLP tasks, yet it remains unclear whether DNN models can capture compositional meanings, those aspects of meaning that have been long studied in…

Computation and Language · Computer Science 2021-06-03 Hitomi Yanaka , Koji Mineshima , Kentaro Inui

The rise of social networks has not only facilitated communication but also allowed the spread of harmful content. Although significant advances have been made in detecting toxic language in textual data, the exploration of concept-based…

Computation and Language · Computer Science 2025-12-16 Samarth Garg , Divya Singh , Deeksha Varshney , Mamta

As deep neural networks (DNNs) get adopted in an ever-increasing number of applications, explainability has emerged as a crucial desideratum for these models. In many real-world tasks, one of the principal reasons for requiring…

Artificial Intelligence · Computer Science 2020-07-03 Vedant Nanda , Till Speicher , John P. Dickerson , Krishna P. Gummadi , Muhammad Bilal Zafar

Explainable AI (XAI) methods typically focus on identifying essential input features or more abstract concepts for tasks like image or text classification. However, for algorithmic tasks like combinatorial optimization, these concepts may…

Machine Learning · Computer Science 2024-12-30 Elad Shoham , Hadar Cohen , Khalil Wattad , Havana Rika , Dan Vilenchik

Unlike human-engineered systems such as aeroplanes, where each component's role and dependencies are well understood, the inner workings of AI models remain largely opaque, hindering verifiability and undermining trust. This paper…

This paper explains the generalization power of a deep neural network (DNN) from the perspective of interactions. Although there is no universally accepted definition of the concepts encoded by a DNN, the sparsity of interactions in a DNN…

Machine Learning · Computer Science 2024-09-16 Huilin Zhou , Hao Zhang , Huiqi Deng , Dongrui Liu , Wen Shen , Shih-Han Chan , Quanshi Zhang

Motivated by the Gestalt pattern theory, and the Winograd Challenge for language understanding, we design synthetic experiments to investigate a deep learning algorithm's ability to infer simple (at least for human) visual concepts, such as…

Computer Vision and Pattern Recognition · Computer Science 2017-11-02 Zhennan Yan , Xiang Sean Zhou

Models based on deep convolutional neural networks (CNN) have significantly improved the performance of semantic segmentation. However, learning these models requires a large amount of training images with pixel-level labels, which are very…

Computer Vision and Pattern Recognition · Computer Science 2018-02-05 Linwei Ye , Zhi Liu , Yang Wang

The deep neural networks (DNNs) have achieved great success in learning complex patterns with strong predictive power, but they are often thought of as "black box" models without a sufficient level of transparency and interpretability. It…

Machine Learning · Computer Science 2020-11-10 Agus Sudjianto , William Knauth , Rahul Singh , Zebin Yang , Aijun Zhang

Local explanation frameworks aim to rationalize particular decisions made by a black-box prediction model. Existing techniques are often restricted to a specific type of predictor or based on input saliency, which may be undesirably…

Machine Learning · Computer Science 2019-02-12 Brandon Carter , Jonas Mueller , Siddhartha Jain , David Gifford

Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally crucial. Current evaluation methodologies lack transparency, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Katarzyna Filus , Michał Romaszewski , Mateusz Żarski

Safety-critical applications require transparency in artificial intelligence (AI) components, but widely used convolutional neural networks (CNNs) widely used for perception tasks lack inherent interpretability. Hence, insights into what…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 Georgii Mikriukov , Gesina Schwalbe , Christian Hellert , Korinna Bade

In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Matthias Rottmann , Marco Reese

Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherently limited to model such dependencies due to the naive…

Computer Vision and Pattern Recognition · Computer Science 2021-09-01 Xiangtai Li , Li Zhang , Guangliang Cheng , Kuiyuan Yang , Yunhai Tong , Xiatian Zhu , Tao Xiang

The task of graph node classification is often approached by utilizing a local Graph Neural Network (GNN), that learns only local information from the node input features and their adjacency. In this paper, we propose to improve the…

Machine Learning · Computer Science 2024-06-18 Moshe Eliasof , Eran Treister

Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations. Global node encoding allows explicit communication between two distant nodes, thereby neglecting graph…

Computation and Language · Computer Science 2020-06-23 Leonardo F. R. Ribeiro , Yue Zhang , Claire Gardent , Iryna Gurevych