首页/论文/2102.06307

arXiv 2102.063072021-02cs.LGcs.CV

What does LIME really see in images?

Université Côte d’Azur（蔚蓝海岸大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；LJAD（LJAD（暂缺通用中文名，保留原文））；Polytech Nice（尼斯综合理工学院）

Damien Garreau, Dina Mardaoui

备注：: 30 pages, 13 figures, accepted to ICML 2021

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

The performance of modern algorithms on certain computer vision tasks such as object recognition is now close to that of humans. This success was achieved at the price of complicated architectures depending on millions of parameters and it has become quite challenging to understand how particular predictions are made. Interpretability methods propose to give us this understanding. In this paper, we study LIME, perhaps one of the most popular. On the theoretical side, we show that when the number of generated examples is large, LIME explanations are concentrated around a limit explanation for which we give an explicit expression. We further this study for elementary shape detectors and linear models. As a consequence of this analysis, we uncover a connection between LIME and integrated gradients, another explanation method. More precisely, the LIME explanations are similar to the sum of integrated gradients over the superpixels used in the preprocessing step of LIME.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

s-LIME: Reconciling Locality and Fidelity in Linear Explanations

Univ. Rennes（雷恩大学）；Ensai（国立统计与信息分析学院）；CNRS（法国国家科学研究中心）；CREST（经济与统计研究中心）；Inria（法国国家信息与自动化研究所）；Irisa（雷恩信息与随机系统研究所）；Insa（国立应用科学学院）

The benefit of locality is one of the major premises of LIME, one of the most prominent methods to explain black-box machine learning models. This emphasis relies on the postulate that the more locally we look at the vicinity of an instance, the simpler the black-box model becomes, and the more accurately we can mimic it with a linear surrogate. As logical as this seems, our findings suggest that, with the current design of LIME, the surrogate model may degenerate when the explanation is too local, namely, when the bandwidth parameter $σ$ tends to zero. Based on this observation, the contribut…

2022-08-02cs.LG

GLIME：通用、稳定且局部的 LIME 解释

GLIME: General, Stable and Local LIME Explanation

Tsinghua University（清华大学）

针对 LIME 存在的不稳定和低局部保真度问题，提出 GLIME 框架，通过等价公式化、局部无偏采样分布实现更快收敛、更高稳定性与保真度，且解释独立于参考选择。

2023-11-27cs.AIcs.CVcs.HC

What Really is Deep Learning Doing?

Deep learning has achieved a great success in many areas, from computer vision to natural language processing, to game playing, and much more. Yet, what deep learning is really doing is still an open question. There are a lot of works in this direction. For example, [5] tried to explain deep learning by group renormalization, and [6] tried to explain deep learning from the view of functional approximation. In order to address this very crucial question, here we see deep learning from perspective of mechanical learning and learning machine (see [1], [2]). From this particular angle, we can see …

2017-11-06cs.LGcs.NE

使用基于LIME的可解释人工智能进行水下声纳图像分类与分析

Underwater SONAR Image Classification and Analysis using LIME-based Explainable Artificial Intelligence

SRM Institute of Science and Technology（SRM科技学院）；Faculty of Engineering and Technology（工程与技术学院）

本文利用VGG16等CNN架构和迁移学习对水下SONAR图像进行分类，并引入LIME及SP-LIME等XAI技术提供透明解释，提升了模型在高安全领域的可信度。

2024-09-23cs.AIcs.CVcs.HC

机器真的能看见图像中的物体吗？基于句法距离和视觉自指实例的研究

Can Machines Really See Objects in Images? A Study Based on Syntactic Distance and Visual Self-Referential Instances

通过句法距离定义视觉任务，发现当前视觉模型在全局语义任务中存在结构性的能力边界，表现为准确率在临界点后崩溃至随机猜测。

2026-06-28cs.AIcs.CVcs.LG

ALIME: Autoencoder Based Approach for Local Interpretability

Machine learning and especially deep learning have garneredtremendous popularity in recent years due to their increased performanceover other methods. The availability of large amount of data has aidedin the progress of deep learning. Nevertheless, deep learning models areopaque and often seen as black boxes. Thus, there is an inherent need tomake the models interpretable, especially so in the medical domain. Inthis work, we propose a locally interpretable method, which is inspiredby one of the recent tools that has gained a lot of interest, called localinterpretable model-agnostic explanation…

2019-09-04cs.LGstat.ML

更多相关论文收起更多论文

Does Joint Training Really Help Cascaded Speech Translation?

RWTH Aachen University（亚琛工业大学）

Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results. However, fundamental challenges such as error propagation from the automatic speech recognition system still remain. To mitigate these problems, recently, people turn their attention to direct data and propose various joint training methods. In this work, we seek to answer the question of whether joint training really helps cascaded speech translation. We review recent papers on the topic and also investigate a joint training criterion b…

2022-11-24cs.CLcs.LGeess.AS

多智能体辩论何时以及为何失败，它真的表现不佳吗？

When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?

The Chinese University of Hong Kong（香港中文大学）；RIKEN Center for Advanced Intelligence Project（日本理化学研究院高级智能项目中心）；Hong Kong Baptist University（香港 Baptist大学）；The University of Tokyo（东京大学）

研究多智能体辩论（MAD）失败原因及表现，分析竞争型和寻求共识型MAD范式问题，提出协作协议ColMAD，经实验验证其在错误检测等任务上比之前协议高出10个百分点，且优于单智能体方法，凸显协议设计对MAD潜力实现的关键作用。

2026-07-15cs.LG

What Do We Really Need? Degenerating U-Net on Retinal Vessel Segmentation

International Max Planck Research School for Physics of Light（国际马克斯·普朗克光物理研究学院）；Erlangen Graduate School in Advanced Optical Technologies（埃尔朗根高级光学技术研究生院）

Retinal vessel segmentation is an essential step for fundus image analysis. With the recent advances of deep learning technologies, many convolutional neural networks have been applied in this field, including the successful U-Net. In this work, we firstly modify the U-Net with functional blocks aiming to pursue higher performance. The absence of the expected performance boost then lead us to dig into the opposite direction of shrinking the U-Net and exploring the extreme conditions such that its segmentation performance is maintained. Experiment series to simplify the network structure, reduc…

2019-11-06cs.CVcs.LGeess.IV

Unmasking Clever Hans Predictors and Assessing What Machines Really Learn

Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫研究所海因里希赫兹研究所）；Technische Universität Berlin（柏林工业大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Korea University（高丽大学）；Max Planck Institut für Informatik（马克斯·普朗克计算机科学研究所）

Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly "intelligent" behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade games. This showcases a spectrum of problem-solving behaviors ranging from naive and short-sighted, to well-informed and strategic. We observe that standard performance evaluation metrics can be oblivious to distinguishing these diverse problem solving behaviors. Furthermore, we propose our semi-…

2019-02-26cs.AIcs.CVcs.LG

LLM对齐真的需要多样性吗？对道德推理适应RLVR方法的实证研究

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning

Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Microsoft Research（微软研究院）；University of Michigan（密歇根大学）；Shanghai Jiao Tong University（上海交通大学）；CUHKSZ（香港中文大学（深圳））；THU（清华大学）

本文通过实证研究发现，LLM对齐任务并不需要多样性算法，标准奖励最大化RLVR方法在道德推理中同样有效。

2026-03-11cs.AIcs.CLcs.LG