相关论文: Automatic Concept Extraction for Concept Bottlenec…

Large, publicly available clinical datasets have emerged as a novel resource for understanding disease heterogeneity and to explore personalization of therapy. These datasets are derived from data not originally collected for research…

We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning. GCB maps graphs into a subspace, concept bottleneck, where each concept is a meaningful phrase, and predictions are made…

Unsupervised Concept Extraction aims to extract concepts from a single image; however, existing methods suffer from the inability to extract composable intrinsic concepts. To address this, this paper introduces a new task called…

Concept bottleneck models (CBM) aim to improve model interpretability by predicting human level "concepts" in a bottleneck within a deep learning model architecture. However, how the predicted concepts are used in predicting the target…

We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis? State-of-the-art models today do not typically support the…

Concept Bottleneck Models (CBMs) introduce interpretability to black-box deep learning models by predicting labels through human-understandable concepts. However, unlike humans, who identify objects at different levels of abstraction using…

In this work, we introduce InfoDisent, a hybrid approach to explainability based on the information bottleneck principle. InfoDisent enables the disentanglement of information in the final layer of any pretrained model into atomic concepts,…

Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept prediction and class prediction based on the predicted concepts. CBM…

Given the accelerating progress of vision and language modeling, accurate evaluation of machine-generated image captions remains critical. In order to evaluate captions more closely to human preferences, metrics need to discriminate between…

Concept Bottleneck Models (CBMs) provide inherent interpretability by first mapping input samples to high-level semantic concepts, followed by a combination of these concepts for the final classification. However, the annotation of…

This paper presents CountEx, a discriminative visual counting framework designed to address a key limitation of existing prompt-based methods: the inability to explicitly exclude visually similar distractors. While current approaches allow…

Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all…

The development of artificial intelligence systems for colonoscopy analysis often necessitates expert-annotated image datasets. However, limitations in dataset size and diversity impede model performance and generalisation. Image-text…

The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-making process of CLIP an essential research topic. Due to…

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced…

Explanations for Convolutional Neural Networks (CNNs) based on relevance of input pixels might be too unspecific to evaluate which and how input features impact model decisions. Especially in complex real-world domains like biology, the…

Concept bottleneck models (CBMs), which predict human-interpretable concepts (e.g., nucleus shapes in cell images) before predicting the final output (e.g., cell type), provide insights into the decision-making processes of the model.…

(Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from…

The maturity of deep learning techniques has led in recent years to a breakthrough in object recognition in visual media. While for some specific benchmarks, neural techniques seem to match if not outperform human judgement, challenges are…

Ensuring fairness in image classification prevents models from perpetuating and amplifying bias. Concept bottleneck models (CBMs) map images to high-level, human-interpretable concepts before making predictions via a sparse, one-layer…