相关论文: Human-Centered Concept Explanations for Neural Net…

While concept-based explanations improve interpretability over local attributions, they often rely on correlational signals and lack causal validation. We introduce VisionLogic, a novel neural-symbolic framework that produces faithful,…

An essential step in deploying medical imaging models is ensuring alignment with clinical knowledge and interpretability. We focus on mapping clinical concepts into the latent space of generative models to identify Concept Activation…

Interpretability methods for image classification assess model trustworthiness by attempting to expose whether the model is systematically biased or attending to the same cues as a human would. Saliency methods for feature attribution…

Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we…

Deep neural perception and control networks are likely to be a key component of self-driving vehicles. These models need to be explainable - they should provide easy-to-interpret rationales for their behavior - so that passengers, insurance…

The study of causal abstractions bridges two integral components of human intelligence: the ability to determine cause and effect, and the ability to interpret complex patterns into abstract concepts. Formally, causal abstraction frameworks…

Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text;…

A variety of methods exist to explain image classification models. However, whether they provide any benefit to users over simply comparing various inputs and the model's respective predictions remains unclear. We conducted a user study…

Explainable Artificial Intelligence has gained significant attention due to the widespread use of complex deep learning models in high-stake domains such as medicine, finance, and autonomous cars. However, different explanations often…

Fetal standard scan plane detection during 2-D mid-pregnancy examinations is a highly complex task, which requires extensive medical knowledge and years of training. Although deep neural networks (DNN) can assist inexperienced operators in…

Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This…

With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as model interpretation. While…

Converging evidence suggests that the mammalian ventral visual pathway encodes increasingly complex stimulus features in downstream areas. Using deep convolutional neural networks, we can now quantitatively demonstrate that there is indeed…

A concept-based classifier can explain the decision process of a deep learning model by human-understandable concepts in image classification problems. However, sometimes concept-based explanations may cause false positives, which…

Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space. These "visual" explanations are often insufficient, as the model's actual concept remains elusive. Moreover,…

Plant diseases remain a considerable threat to food security and agricultural sustainability. Rapid and early identification of these diseases has become a significant concern motivating several studies to rely on the increasing global…

In this paper, we address the challenging problem of 3D concept grounding (i.e. segmenting and learning visual concepts) by looking at RGBD images and reasoning about paired questions and answers. Existing visual reasoning approaches…

Recent artificial neural networks that process natural language achieve unprecedented performance in tasks requiring sentence-level understanding. As such, they could be interesting models of the integration of linguistic information in the…

Human visual perception carves a scene at its physical joints, decomposing the world into objects, which are selectively attended, tracked, and predicted as we engage our surroundings. Object representations emancipate perception from the…

We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts that closely approximate neuron behavior. Compared to prior work that uses atomic labels as explanations, analyzing neurons…