paper-with-me

Papers

PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs

2021-08-31 · Vidhya Kamakshi, Uday Gupta, Narayanan C Krishnan

Deep CNNs, though have achieved the state of the art performance in image classification tasks, remain a black-box to a human using them. There is a growing interest in explaining the working of these deep models to improve their trustworthiness. In this paper, we introduce a Posthoc Architecture-agnostic Concept Extractor (PACE) that automatically extracts smaller sub-regions of the image called concepts relevant to the black-box prediction. PACE tightly integrates the faithfulness of the explanatory framework to the black-box model. To the best of our knowledge, this is the first work that extracts class-specific discriminative concepts in a posthoc manner automatically. The PACE framework is used to generate explanations for two different CNN architectures trained for classifying the AWA2 and Imagenet-Birds datasets. Extensive human subject experiments are conducted to validate the human interpretability and consistency of the explanations extracted by PACE. The results from these experiments suggest that over 72% of the concepts extracted by PACE are human interpretable.

📄 PDF Abstract BibTeX arXiv:2108.13828

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Interpreting CFD Surrogates through Sparse Autoencoders

2025-07-21 · Yeping Hu, Shusen Liu arxiv

Learning-based surrogate models have become a practical alternative to high-fidelity CFD solvers, but their latent representations remain opaque and hinder adoption in safety-critical or regulation-bound settings. This w…

Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery

2024-07-19 · Sukrut Rao, Sweta Mahajan, Moritz Böhle, Bernt Schiele

Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept space and then linearly combining concept…

Posthoc Interpretation via Quantization

2023-03-22 · Francesco Paissan, Cem Subakan, Mirco Ravanelli

In this paper, we introduce a new approach, called Posthoc Interpretation via Quantization (PIQ), for interpreting decisions made by trained classifiers. Our method utilizes vector quantization to transform the represent…

Image SegmentationQuantizationSemantic Segmentation

MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks

2020-11-03 · Ashish Kumar, Karan Sehgal, Prerna Garg, Vidhya Kamakshi 외

Deep convolutional networks have been quite successful at various image classification tasks. The current methods to explain the predictions of a pre-trained model rely on gradient information, often resulting in salienc…

ClassificationGeneral Classificationimage-classificationImage Classification

Concept Whitening for Interpretable Image Recognition

2020-02-05 · Zhi Chen, Yijie Bei, Cynthia Rudin

What does a neural network encode about a concept as we traverse through the layers? Interpretability in machine learning is undoubtedly important, but the calculations of neural networks are very challenging to understa…