Related papers: Learning Interpretable Concept Groups in CNNs
Understanding how cities visually differ from each others is interesting for planners, residents, and historians. We investigate the interpretation of deep features learned by convolutional neural networks (CNNs) for city recognition. Given…
Humans can recognize an image as an instance of a general concept, beyond simply identifying its objects and their relationships. In this paper, we investigate 1. The extent to which VLMs have this concept abstraction capacity, and 2.…
Continual learning enables incremental learning of new tasks without forgetting those previously learned, resulting in positive knowledge transfer that can enhance performance on both new and old tasks. However, continual learning poses new…
Deep reinforcement learning (DRL), through learning policies or values represented by neural networks, has successfully addressed many complex control problems. However, the neural networks introduced by DRL lack interpretability and…
In recent years convolutional neural networks (CNN) have shown striking progress in various tasks. However, despite the high performance, the training and prediction process remains to be a black box, leaving it a mystery to extract what…
An approach to improve network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We find pretrained models to be highly unclusterable and thus train models to be more…
We present an analysis into the inner workings of Convolutional Neural Networks (CNNs) for processing text. CNNs used for computer vision can be interpreted by projecting filters into image space, but for discrete sequence inputs CNNs…
In-Context Learning (ICL) empowers Large Language Models (LLMs) with the ability to learn from a few examples provided in the prompt, enabling downstream generalization without the requirement for gradient updates. Despite encouragingly…
Convolutional Neural Network (CNN) has been successful in image recognition tasks, and recent works shed lights on how CNN separates different classes with the learned inter-class knowledge through visualization. In this work, we instead…
We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and…
Deep neural networks have been widely used in text classification. However, it is hard to interpret the neural models due to the complicate mechanisms. In this work, we study the interpretability of a variant of the typical text…
We introduce collaborative learning in which multiple classifier heads of the same network are simultaneously trained on the same training data to improve generalization and robustness to label noise with no extra inference cost. It…
Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose a method for augmenting…
Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less…
This paper learns a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside a pre-trained CNN. Considering that each filter in a conv-layer of a pre-trained CNN usually represents a mixture of…
This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., explaining knowledge representations hidden in middle conv-layers of the CNN.…
Deep neural networks have achieved remarkable success in computer vision; however, their black-box nature in decision-making limits interpretability and trust, particularly in safety-critical applications. Interpretability is crucial in…
The perceptual-based grouping process produces a hierarchical and compositional image representation that helps both human and machine vision systems recognize heterogeneous visual concepts. Examples can be found in the classical…
Retinal vessel segmentation from retinal images is an essential task for developing the computer-aided diagnosis system for retinal diseases. Efforts have been made on high-performance deep learning-based approaches to segment the retinal…
The opaque nature of Large Language Models (LLMs) has led to significant research efforts aimed at enhancing their interpretability, primarily through post-hoc methods. More recent in-hoc approaches, such as Concept Bottleneck Models…