相关论文: Intrinsic Concept Extraction Based on Compositiona…

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 concepts for…

We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment…

Explaining deep learning models is of vital importance for understanding artificial intelligence systems, improving safety, and evaluating fairness. To better understand and control the CNN model, many methods for…

To increase the trustworthiness of deep neural networks, it is critical to improve the understanding of how they make decisions. This paper introduces a novel unsupervised concept-based model for image classification, named Learnable…

Deep learning has driven significant advances in medical image analysis, yet its adoption in clinical practice remains constrained by the large size and lack of transparency in modern models. Advances in interpretability techniques such as…

Textural Inversion, a prompt learning method, learns a singular text embedding for a new "word" to represent image style and appearance, allowing it to be integrated into natural language sentences to generate novel synthesised images.…

In an era where the volume of data drives the effectiveness of self-supervised learning, the specificity and clarity of data semantics play a crucial role in model training. Addressing this, we introduce HYPerbolic Entailment filtering…

In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the…

Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across visual and semantic modalities. While current approaches…

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse…

Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its…

Image retrieval with hybrid-modality queries, also known as composing text and image for image retrieval (CTI-IR), is a retrieval task where the search intention is expressed in a more complex query format, involving both vision and text…

Concept-based interpretability methods are a popular form of explanation for deep learning models which provide explanations in the form of high-level human interpretable concepts. These methods typically find concept activation vectors…

The customization of text-to-image models has seen significant advancements, yet generating multiple personalized concepts remains a challenging task. Current methods struggle with attribute leakage and layout confusion when handling…

The rapid expansion of large-scale text-to-image diffusion models has raised growing concerns regarding their potential misuse in creating harmful or misleading content. In this paper, we introduce MACE, a finetuning framework for the task…

In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet…

Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learned by these models remain an enigma. In this work, we…

Compressive sensing (CS) works to acquire measurements at sub-Nyquist rate and recover the scene images. Existing CS methods always recover the scene images in pixel level. This causes the smoothness of recovered images and lack of…

We present a novel methodology for integrating high resolution longitudinal data with the dynamic prediction capabilities of survival models. The aim is two-fold: to improve the predictive power while maintaining interpretability of the…

Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually require task-specific training and struggle to generalize across both…