A crucial aspect of understanding the complex nature of Deep Neural Networks
(DNNs) is the ability to explain learned concepts within their latent
representations. While various methods exist to connect neurons to textual
descriptions of human-understandable concepts, evaluating the quality of these
explanation methods presents a major challenge in the field due to a lack of
unified, general-purpose quantitative evaluation. In this work, we introduce
CoSy (Concept Synthesis) -- a novel, architecture-agnostic framework to
evaluate the quality of textual explanations for latent neurons. Given textual
explanations, our proposed framework leverages a generative model conditioned
on textual input to create data points representing the textual explanation.
Then, the neuron's response to these explanation data points is compared with
the response to control data points, providing a quality estimate of the given
explanation. We ensure the reliability of our proposed framework in a series of
meta-evaluation experiments and demonstrate practical value through insights
from benchmarking various concept-based textual explanation methods for
Computer Vision tasks, showing that tested explanation methods significantly
differ in quality.

在这项工作中，我们介绍了 CoSy（概念合成）- 一种新颖的、与架构无关的框架来评估潜在神经元的文本解释的质量。通过给出的文本解释，我们提出的框架利用以文本输入为条件的生成模型创建表示文本解释的数据点。然后，将神经元对这些解释数据点的响应与对控制数据点的响应进行比较，从而提供给定解释的质量估计。我们通过一系列元评估实验确保了我们提出的框架的可靠性，并通过对计算机视觉任务的各种基于概念的文本解释方法进行基准测试产生了实际价值，结果表明测试的解释方法在质量上存在显著差异。

CoSy: 评估神经元的文本解释

CoSy: Evaluating Textual Explanations of Neurons

Recently introduced Contrastive Language-Image Pre-Training (CLIP) bridges
images and text by embedding them into a joint latent space. This opens the
door to ample literature that aims to manipulate an input image by providing a
textual explanation. However, due to the discrepancy between image and text
embeddings in the joint space, using text embeddings as the optimization target
often introduces undesired artifacts in the resulting images. Disentanglement,
interpretability, and controllability are also hard to guarantee for
manipulation. To alleviate these problems, we propose to define corpus
subspaces spanned by relevant prompts to capture specific image
characteristics. We introduce CLIP Projection-Augmentation Embedding (PAE) as
an optimization target to improve the performance of text-guided image
manipulation. Our method is a simple and general paradigm that can be easily
computed and adapted, and smoothly incorporated into any CLIP-based image
manipulation algorithm. To demonstrate the effectiveness of our method, we
conduct several theoretical and empirical studies. As a case study, we utilize
the method for text-guided semantic face editing. We quantitatively and
qualitatively demonstrate that PAE facilitates a more disentangled,
interpretable, and controllable image manipulation with state-of-the-art
quality and accuracy.

使用 CLIP Projection-Augmentation Embedding（PAE）作为优化目标，以改善文本引导的图像操作的性能。

CLIP-PAE: 投影增强嵌入以提取相关特征，以实现可分解、可解释和可控的文本引导图像操纵

CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Image Manipulation