English
Related papers

Related papers: DExT: Detector Explanation Toolkit

200 papers

This paper presents Deep Integrated Explanations (DIX) - a universal method for explaining vision models. DIX generates explanation maps by integrating information from the intermediate representations of the model, coupled with their…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Oren Barkan , Yehonatan Elisha , Jonathan Weill , Yuval Asher , Amit Eshel , Noam Koenigstein

We propose Black Box Explanations through Transparent Approximations (BETA), a novel model agnostic framework for explaining the behavior of any black-box classifier by simultaneously optimizing for fidelity to the original model and…

Artificial Intelligence · Computer Science 2017-07-06 Himabindu Lakkaraju , Ece Kamar , Rich Caruana , Jure Leskovec

Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object of interest is partially occluded. We present a novel, black-box algorithm for computing explanations that uses a principled…

Machine Learning · Computer Science 2021-09-08 Hana Chockler , Daniel Kroening , Youcheng Sun

Modern Artificial Intelligence (AI) enabled Intrusion Detection Systems (IDS) are complex black boxes. This means that a security analyst will have little to no explanation or clarification on why an IDS model made a particular prediction.…

Cryptography and Security · Computer Science 2022-07-18 Jesse Ables , Thomas Kirby , William Anderson , Sudip Mittal , Shahram Rahimi , Ioana Banicescu , Maria Seale

Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given…

Computer Vision and Pattern Recognition · Computer Science 2023-11-06 Yifan Pu , Weicong Liang , Yiduo Hao , Yuhui Yuan , Yukang Yang , Chao Zhang , Han Hu , Gao Huang

We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. Utilizing the proposed similarity metric that accounts for both localization and categorization aspects of object detection allows our…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Vitali Petsiuk , Rajiv Jain , Varun Manjunatha , Vlad I. Morariu , Ashutosh Mehra , Vicente Ordonez , Kate Saenko

Understanding and explaining the behavior of machine learning models is essential for building transparent and trustworthy AI systems. We introduce DEXTER, a data-free framework that employs diffusion models and large language models to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Simone Carnemolla , Matteo Pennisi , Sarinda Samarasinghe , Giovanni Bellitto , Simone Palazzo , Daniela Giordano , Mubarak Shah , Concetto Spampinato

Accurately distinguishing each object is a fundamental goal of Multi-object tracking (MOT) algorithms. However, achieving this goal still remains challenging, primarily due to: (i) For crowded scenes with occluded objects, the high overlap…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Jiapeng Wu , Yichen Liu

Black box systems for automated decision making, often based on machine learning over (big) data, map a user's features into a class or a score without exposing the reasons why. This is problematic not only for lack of transparency, but…

Artificial Intelligence · Computer Science 2018-06-27 Dino Pedreschi , Fosca Giannotti , Riccardo Guidotti , Anna Monreale , Luca Pappalardo , Salvatore Ruggieri , Franco Turini

As artificial intelligence and machine learning algorithms make further inroads into society, calls are increasing from multiple stakeholders for these algorithms to explain their outputs. At the same time, these stakeholders, whether they…

In this paper, we propose a method for ensembling the outputs of multiple object detectors for improving detection performance and precision of bounding boxes on image data. We further extend it to video data by proposing a two-stage…

Computer Vision and Pattern Recognition · Computer Science 2021-02-10 Kateryna Chumachenko , Jenni Raitoharju , Alexandros Iosifidis , Moncef Gabbouj

We present an efficient 3D object detection framework based on a single RGB image in the scenario of autonomous driving. Our efforts are put on extracting the underlying 3D information in a 2D image and determining the accurate 3D bounding…

Computer Vision and Pattern Recognition · Computer Science 2019-03-28 Buyu Li , Wanli Ouyang , Lu Sheng , Xingyu Zeng , Xiaogang Wang

A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently. A qualified open-world object detector can not only identify objects of known categories, but also…

Computer Vision and Pattern Recognition · Computer Science 2022-02-17 Shuo Yang , Peize Sun , Yi Jiang , Xiaobo Xia , Ruiheng Zhang , Zehuan Yuan , Changhu Wang , Ping Luo , Min Xu

Explainable Artificial Intelligence (XAI) has in recent years become a well-suited framework to generate human understandable explanations of "black-box" models. In this paper, a novel XAI visual explanation algorithm known as the…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Satya M. Muddamsetty , Mohammad N. S. Jahromi , Andreea E. Ciontos , Laura M. Fenoy , Thomas B. Moeslund

Explainability techniques for data-driven predictive models based on artificial intelligence and machine learning algorithms allow us to better understand the operation of such systems and help to hold them accountable. New transparency…

Machine Learning · Computer Science 2022-09-09 Kacper Sokol , Alexander Hepburn , Raul Santos-Rodriguez , Peter Flach

In the realm of human-machine interaction, artificial intelligence has become a powerful tool for accelerating data modeling tasks. Object detection methods have achieved outstanding results and are widely used in critical domains like…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Alain Andres , Aitor Martinez-Seras , Ibai Laña , Javier Del Ser

An emerging solution for explaining Transformer-based models is to use vector-based analysis on how the representations are formed. However, providing a faithful vector-based explanation for a multi-layer model could be challenging in three…

Computation and Language · Computer Science 2023-06-06 Ali Modarressi , Mohsen Fayyaz , Ehsan Aghazadeh , Yadollah Yaghoobzadeh , Mohammad Taher Pilehvar

Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Aishwarya Kamath , Mannat Singh , Yann LeCun , Gabriel Synnaeve , Ishan Misra , Nicolas Carion

Detection Transformer (DETR) and its variants show strong performance on object detection, a key task for autonomous systems. However, a critical limitation of these models is that their confidence scores only reflect semantic uncertainty,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yutong Yang , Katarina Popović , Julian Wiederer , Markus Braun , Vasileios Belagiannis , Bin Yang

Popular transformer detectors have achieved promising performance through query-based learning using attention mechanisms. However, the roles of existing decoder query types (e.g., content query and positional query) are still…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Guiping Cao , Xiangyuan Lan , Wenjian Huang , Jianguo Zhang , Dongmei Jiang , Yaowei Wang