paper-with-me

홈 › Papers

Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks

2019-08-07 · Jörg Wagner, Jan Mathias Köhler, Tobias Gindele, Leon Hetzel, Jakob Thaddäus Wiedemer, Sven Behnke

To verify and validate networks, it is essential to gain insight into their decisions, limitations as well as possible shortcomings of training data. In this work, we propose a post-hoc, optimization based visual explanation method, which highlights the evidence in the input image for a specific prediction. Our approach is based on a novel technique to defend against adversarial evidence (i.e. faulty evidence due to artefacts) by filtering gradients during optimization. The defense does not depend on human-tuned parameters. It enables explanations which are both fine-grained and preserve the characteristics of images, such as edges and colors. The explanations are interpretable, suited for visualizing detailed evidence and can be tested as they are valid model inputs. We qualitatively and quantitatively evaluate our approach on a multitude of models and datasets.

📄 PDF Abstract BibTeX arXiv:1908.02686

Code (0)

등록된 구현이 없습니다.

Tasks

valid

Similar Papers 제목 키워드 기반

Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks

2019-06-01 · CVPR 2019 6 · Jorg Wagner, Jan Mathias Kohler, Tobias Gindele, Leon Hetzel 외

To verify and validate networks, it is essential to gain insight into their decisions, limitations as well as possible shortcomings of training data. In this work, we propose a post-hoc, optimization based visual explana…

valid

CFM: Language-aligned Concept Foundation Model for Vision

2026-01-20 · Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi, Bernt Schiele 외 arxiv

Language-aligned vision foundation models perform strongly across diverse downstream tasks. Yet, their learned representations remain opaque, making interpreting their decision-making difficult. Recent work decompose the…

Image Classification

Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

2025-02-19 · Yucheng Shi, Quanzheng Li, Jin Sun, Xiang Li 외

Large multimodal models (LMMs) have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific objectives and provi…

Fine-Grained Visual RecognitionPneumonia DetectionVisual Reasoning

Interpretable Visual Question Answering Referring to Outside Knowledge

2023-03-08 · He Zhu, Ren Togo, Takahiro Ogawa, Miki Haseyama

We present a novel multimodal interpretable VQA model that can answer the question more accurately and generate diverse explanations. Although researchers have proposed several methods that can generate human-readable an…

DiversityImage CaptioningQuestion AnsweringVisual Question Answering+1

Pairwise Matching of Intermediate Representations for Fine-grained Explainability

2025-03-28 · Lauren Shrack, Timm Haucke, Antoine Salaün, Arjun Subramonian 외

The differences between images belonging to fine-grained categories are often subtle and highly localized, and existing explainability techniques for deep learning models are often too diffuse to provide useful and inter…