让深度模型像人一样看图说话，指出判断依据和位置。
Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models
- 用空间感知概念瓶颈层将黑箱特征转为可解释概念图。
- 在分类任务中性能超越原始模型和非空间方法。
- 生成高质量定位热图，适合模型调试与交互式分析。
现代深度神经网络已在多种任务上达到人类水平性能，但缺乏像人类一样通过展示位置和说明概念来解释决策的能力。本文提出统一框架，将任意视觉神经网络转化为空间与概念可解释的模型。引入无需人工标注的空间感知概念瓶颈层，将预训练主干网络的“黑箱”特征投影为可解释的概念图，并通过在此瓶颈层上训练分类器，获得自解释模型，能说明哪些概念影响了预测结果，并生成其在输入图像中的空间定位热图。该方法称为空间感知且无标签概念瓶颈模型（SALF-CBM）。实验表明：(1) SALF-CBM在多个分类任务中优于非空间概念瓶颈方法及原始主干模型；(2) 在零样本分割任务中生成的定位热图质量高于广泛使用的基于热图的方法；(3) 支持模型探索与调试，用户可查询特定图像区域，通过局部编辑概念图来修正模型决策。
原文摘要 · Abstract (English)
Modern deep neural networks have now reached human-level performance across a variety of tasks. However, unlike humans they lack the ability to explain their decisions by showing where and telling what concepts guided them. In this work, we present a unified framework for transforming any vision neural network into a spatially and conceptually interpretable model. We introduce a spatially-aware concept bottleneck layer that projects "black-box" features of pre-trained backbone models into interpretable concept maps, without requiring human labels. By training a classification layer over this bottleneck, we obtain a self-explaining model that articulates which concepts most influenced its prediction, along with heatmaps that ground them in the input image. Accordingly, we name this method "Spatially-Aware and Label-Free Concept Bottleneck Model" (SALF-CBM). Our results show that the proposed SALF-CBM: (1) Outperforms non-spatial CBM methods, as well as the original backbone, on a variety of classification tasks; (2) Produces high-quality spatial explanations, outperforming widely used heatmap-based methods on a zero-shot segmentation task; (3) Facilitates model exploration and debugging, enabling users to query specific image regions and refine the model's decisions by locally editing its concept maps.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。