paper-with-me

Interpretability Techniques for Deep Learning

2개 벤치마크 · 논문 25편 · 이 태스크의 논문 보기 →

Benchmarks

CausalGym

결과 7개

CelebA

결과 7개

Most implemented

Axiomatic Attribution for Deep Networks

2017-03-04 · 구현 40개

Papers

Time series saliency maps: explaining models across multiple domains

2025-05-19 · Christodoulos Kechris, Jonathan Dan, David Atienza

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 s…

Explainable Artificial Intelligence (XAI)Interpretability Techniques for Deep LearningPhotoplethysmography (PPG) heart rate estimationSeizure Detection+2

Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability

2025-03-26 · CVPR 2025 1 · Yingdong Shi, Changming Li, Yifan Wang, Yongxiang Zhao 외

Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and …

Age/UnbiasedDecision MakingImage GenerationInterpretability Techniques for Deep Learning+1

IBO: Inpainting-Based Occlusion to Enhance Explainable Artificial Intelligence Evaluation in Histopathology

2024-08-29 · Pardis Afshar, Sajjad Hashembeiki, Pouya Khani, Emad Fatemizadeh 외

Histopathological image analysis is crucial for accurate cancer diagnosis and treatment planning. While deep learning models, especially convolutional neural networks, have advanced this field, their "black-box" nature r…

ClassificationDenoisingExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)+1

Explainable Deep Learning: A Visual Analytics Approach with Transition Matrices

2024-03-29 · Mathematics 2024 3 · Pavlo Radiuk, Olexander Barmak, Eduard Manziuk, Iurii Krak

The non-transparency of artificial intelligence (AI) systems, particularly in deep learning (DL), poses significant challenges to their comprehensibility and trustworthiness. This study aims to enhance the explainability…

Deep LearningExplainable Artificial Intelligence (XAI)Image GenerationInterpretability Techniques for Deep Learning+3

CausalGym: Benchmarking causal interpretability methods on linguistic tasks

2024-02-19 · Aryaman Arora, Dan Jurafsky, Christopher Potts

Language models (LMs) have proven to be powerful tools for psycholinguistic research, but most prior work has focused on purely behavioural measures (e.g., surprisal comparisons). At the same time, research in model inte…

BenchmarkingInterpretability Techniques for Deep Learning

Less is More: Fewer Interpretable Region via Submodular Subset Selection

2024-02-14 · Ruoyu Chen, Hua Zhang, Siyuan Liang, Jingzhi Li 외

Image attribution algorithms aim to identify important regions that are highly relevant to model decisions. Although existing attribution solutions can effectively assign importance to target elements, they still face th…

Error UnderstandingImage AttributionInterpretability Techniques for Deep Learning

전체 25편 보기 →