相关论文: CRAFT: Concept Recursive Activation FacTorization …

Rigorousness and clarity are both essential for interpretations of DNNs to engender human trust. Path methods are commonly employed to generate rigorous attributions that satisfy three axioms. However, the meaning of attributions remains…

Due to the proliferation of short-form content and the rapid adoption of AI, opportunities for deep, reflective thinking have significantly diminished, undermining users' critical thinking and reducing engagement with the reasoning behind…

Imitation learning enables robots to acquire complex manipulation skills from human demonstrations, but current methods rely solely on low-level sensorimotor data while ignoring the rich semantic knowledge humans naturally possess about…

Feature attribution (FA), or the assignment of class-relevance to different locations in an image, is important for many classification problems but is particularly crucial within the neuroscience domain, where accurate mechanistic models…

The advances in deep learning have enabled machine learning methods to outperform human beings in various areas, but it remains a great challenge for a well-trained model to quickly adapt to a new task. One promising solution to realize…

We introduce a psychologically grounded and artist-informed framework for modeling visual creativity across four domains: Inner, Outer, Imaginative, and Moral Worlds. Drawing on interviews with practicing artists and theories from…

Bias discovery is critical for black-box generative models, especiall text-to-image (TTI) models. Existing works predominantly focus on output-level demographic distributions, which do not necessarily guarantee concept representations to be…

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data. The task is addressed as a feature-clustering problem and recent studies augment instance…

While SHAP (SHapley Additive exPlanations) and other feature attribution methods are commonly employed to explain model predictions, their application within information retrieval (IR), particularly for complex outputs such as ranked lists,…

Understanding the decision processes of deep vision models is essential for their safe and trustworthy deployment in real-world settings. Existing explainability approaches, such as saliency maps or concept-based analyses, often suffer from…

Attribution methods reveal which input features a neural network uses for a prediction, adding transparency to their decisions. A common problem is that these attributions seem unspecific, highlighting both important and irrelevant…

Deep Neural Networks have often been called the black box because of the complex, deep architecture and non-transparency presented by the inner layers. There is a lack of trust to use Artificial Intelligence in critical and high-precision…

To learn semantic attributes, existing methods typically train one discriminative model for each word in a vocabulary of nameable properties. However, this "one model per word" assumption is problematic: while a word might have a precise…

The first layer of a deep CNN backbone applies filters to an image to extract the basic features available to later layers. During training, some filters may go inactive, mean ing all weights in the filter approach zero. An inactive fil ter…

Image classification models have achieved satisfactory performance on many datasets, sometimes even better than human. However, The model attention is unclear since the lack of interpretability. This paper investigates the fidelity and…

Generative image models have emerged as a promising technology to produce realistic images. Despite potential benefits, concerns grow about its misuse, particularly in generating deceptive images that could raise significant ethical, legal,…

The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. While a large number of…

Humans use abstract concepts for understanding instead of hard features. Recent interpretability research has focused on human-centered concept explanations of neural networks. Concept Activation Vectors (CAVs) estimate a model's…