相关论文: SIDE: Sparse Information Disentanglement for Expla…

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,…

It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the…

The ability for a human to understand an Artificial Intelligence (AI) model's decision-making process is critical in enabling stakeholders to visualize model behavior, perform model debugging, promote trust in AI models, and assist in…

Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to…

Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…

Explainable AI aims to overcome the black-box nature of complex ML models like neural networks by generating explanations for their predictions. Explanations often take the form of a heatmap identifying input features (e.g. pixels) that are…

Deep learning models have achieved remarkable success in different areas of machine learning over the past decade; however, the size and complexity of these models make them difficult to understand. In an effort to make them more…

Prototypical part learning is emerging as a promising approach for making semantic segmentation interpretable. The model selects real patches seen during training as prototypes and constructs the dense prediction map based on the similarity…

For many use-cases, it is often important to explain the prediction of a black-box model by identifying the most influential training data samples. Existing approaches lack customization for user intent and often provide a homogeneous set…

Explainable AI aims to render model behavior understandable by humans, which can be seen as an intermediate step in extracting causal relations from correlative patterns. Due to the high risk of possible fatal decisions in image-based…

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

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…

We propose ProtoArgNet, a novel interpretable deep neural architecture for image classification in the spirit of prototypical-part-learning as found, e.g., in ProtoPNet. While earlier approaches associate every class with multiple…

Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in…

Single image depth estimation (SIDE) plays a crucial role in 3D computer vision. In this paper, we propose a two-stage robust SIDE framework that can perform blind SIDE for both indoor and outdoor scenes. At the first stage, the scene…

We present a deformable prototypical part network (Deformable ProtoPNet), an interpretable image classifier that integrates the power of deep learning and the interpretability of case-based reasoning. This model classifies input images by…

As AI systems grow more capable, it becomes increasingly important that their decisions remain understandable and aligned with human expectations. A key challenge is the limited interpretability of deep models. Post-hoc methods like GradCAM…