paper-with-me

홈 › Papers

Position: Do Not Explain Vision Models Without Context

2024-04-28 · Paulina Tomaszewska, Przemysław Biecek

Does the stethoscope in the picture make the adjacent person a doctor or a patient? This, of course, depends on the contextual relationship of the two objects. If it's obvious, why don't explanation methods for vision models use contextual information? In this paper, we (1) review the most popular methods of explaining computer vision models by pointing out that they do not take into account context information, (2) show examples of failures of popular XAI methods, (3) provide examples of real-world use cases where spatial context plays a significant role, (4) propose new research directions that may lead to better use of context information in explaining computer vision models, (5) argue that a change in approach to explanations is needed from 'where' to 'how'.

📄 PDF Abstract BibTeX arXiv:2404.18316

Code (0)

등록된 구현이 없습니다.

Tasks

Position

Similar Papers 제목 키워드 기반

Tonguescape: Exploring Language Models Understanding of Vowel Articulation

2025-01-29 · Haruki Sakajo, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

Vowels are primarily characterized by tongue position. Humans have discovered these features of vowel articulation through their own experience and explicit objective observation such as using MRI. With this knowledge an…

In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax

2023-11-13 · Aaron Mueller, Albert Webson, Jackson Petty, Tal Linzen

In-context learning (ICL) is now a common method for teaching large language models (LLMs) new tasks: given labeled examples in the input context, the LLM learns to perform the task without weight updates. Do models guid…

In-Context LearningOut-of-Distribution Generalization

Attention Mechanism, Transformers, BERT, and GPT: Tutorial and Survey

2020-11-17 · Benyamin Ghojogh, Ali Ghodsi

This is a tutorial and survey paper on the attention mechanism, transformers, BERT, and GPT. We first explain attention mechanism, sequence-to-sequence model without and with attention, self-attention, and attention in d…

DecoderDeep AttentionNatural Language InferenceSurvey+1

Grounding Explainability Within the Context of Global South in XAI

2022-05-13 · Deepa Singh, Michal Slupczynski, Ajit G. Pillai, Vinoth Pandian Sermuga Pandian

In this position paper, we propose building a broader and deeper understanding around Explainability in AI by 'grounding' it in social contexts, the socio-technical systems operate in. We situate our understanding of gro…

Explainable Artificial Intelligence (XAI)Position

Interpretable Compositional Convolutional Neural Networks

2021-07-09 · Wen Shen, Zhihua Wei, Shikun Huang, BinBin Zhang 외

The reasonable definition of semantic interpretability presents the core challenge in explainable AI. This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable composit…