Prototypical parts networks combine the power of deep learning with the explainability of case-based reasoning to make accurate, interpretable decisions. They follow the this looks like that reasoning, representing each prototypical part with patches from training images. However, a single image patch comprises multiple visual features, such as color, shape, and texture, making it difficult for users to identify which feature is important to the model. To reduce this ambiguity, we introduce the Lucid Prototypical Parts Network (LucidPPN), a novel prototypical parts network that separates color prototypes from other visual features. Our method employs two reasoning branches: one for non-color visual features, processing grayscale images, and another focusing solely on color information. This separation allows us to clarify whether the model's decisions are based on color, shape, or texture. Additionally, LucidPPN identifies prototypical parts corresponding to semantic parts of classified objects, making comparisons between data classes more intuitive, e.g., when two bird species might differ primarily in belly color. Our experiments demonstrate that the two branches are complementary and together achieve results comparable to baseline methods. More importantly, LucidPPN generates less ambiguous prototypical parts, enhancing user understanding.

While the capabilities of generative foundational models have advanced rapidly in recent years, methods to prevent harmful and unsafe behaviors remain underdeveloped. Among the pressing challenges in AI safety, machine unlearning (MU) has become increasingly critical to meet upcoming safety regulations. Most existing MU approaches focus on altering the most significant parameters of the model. However, these methods often require fine-tuning substantial portions of the model, resulting in high computational costs and training instabilities, which are typically mitigated by access to the original training dataset. In this work, we address these limitations by leveraging Singular Value Decomposition (SVD) to create a compact, low-dimensional projection that enables the selective forgetting of specific data points. We propose Singular Value Decomposition for Efficient Machine Unlearning (SEMU), a novel approach designed to optimize MU in two key aspects. First, SEMU minimizes the number of model parameters that need to be modified, effectively removing unwanted knowledge while making only minimal changes to the model's weights. Second, SEMU eliminates the dependency on the original training dataset, preserving the model's previously acquired knowledge without additional data requirements. Extensive experiments demonstrate that SEMU achieves competitive performance while significantly improving efficiency in terms of both data usage and the number of modified parameters.

Active Visual Exploration (AVE) optimizes the utilization of robotic resources in real-world scenarios by sequentially selecting the most informative observations. However, modern methods require a high computational budget due to processing the same observations multiple times through the autoencoder transformers. As a remedy, we introduce a novel approach to AVE called TOken REcycling (TORE). It divides the encoder into extractor and aggregator components. The extractor processes each observation sepa-rately, enabling the reuse of tokens passed to the aggrega-tor. Moreover, to further reduce the computations, we de-crease the decoder to only one block. Through extensive experiments, we demonstrate that TORE outperforms state-of-the-art methods while reducing computational overhead by up to 90%.

Prototypical parts-based networks are becoming increasingly popular due to their faithful self-explanations. However, their similarity maps are calculated in the penultimate network layer. Therefore, the receptive field of the prototype activation region often depends on parts of the image outside this region, which can lead to misleading interpretations. We name this undesired behavior a spatial explanation misalignment and introduce an interpretability benchmark with a set of dedicated metrics for quantifying this phenomenon. In addition, we propose a method for misalignment compensation and apply it to existing state-of-the-art models. We show the expressiveness of our benchmark and the effectiveness of the proposed compensation methodology through extensive empirical studies.

In this work, we introduce ProtoNCD, a novel approach to novel class discovery (NCD) that leverages prototypical parts for enhanced interpretability.ProtoNCD extends the ProtoPool methodology to the NCD setting, employing techniques such as knowledge distillation and specialized prototypical parts initialization.Through comprehensive experiments on the CUB-200-2011 dataset, we demonstrate the efficacy of ProtoNCD and its pivotal role in explaining how the reasoning of known classes influences predictions for those newly discovered.

Lung cancer is a leading cause of cancer-related deaths, and early diagnosis is crucial for its effective treatment. That is why computer-aided tools have been developed to support particular steps of CT scan analysis, including lung segmentation, suspicious region detection, and patient-level diagnosis. However, none of the previous approaches addressed this process comprehensively. To fill this gap, we introduce CompLung, a comprehensive tool for lung cancer diagnosis that performs all of the above-listed steps in an end-to-end manner. We have trained the CompLung architecture using the publicly available LIDC-IDRI dataset extended with lung segmentation masks obtained from our internal radiologists, which we make publicly available to boost the research on this emerging topic. Finally, we conduct extensive experiments and demonstrate the superior performance and interpretability of CompLung compared to existing methods for lung cancer diagnosis.

Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those predictions to obtain a bag label. The most common MIL model is when we consider a bag as positive if at least one of its instances has a positive label. However, this reasoning does not hold in many real-life scenarios, where the positive bag label is often a consequence of a certain percentage of positive instances. To address this issue, we introduce a dedicated instance-based method called ProMIL, based on deep neural networks and Bernstein polynomial estimation. An important advantage of ProMIL is that it can automatically detect the optimal percentage level for decision-making. We show that ProMIL outperforms standard instance-based MIL in real-world medical applications. We make the code available.

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 challenges for interpretability, as the rationale behind model predictions may change over time, leading to interpretability concept drift. We address this problem by proposing Interpretable Class-InCremental LEarning (ICICLE), an exemplar-free approach that adopts a prototypical part-based approach. It consists of three crucial novelties: interpretability regularization that distills previously learned concepts while preserving user-friendly positive reasoning; proximity-based prototype initialization strategy dedicated to the fine-grained setting; and task-recency bias compensation devoted to prototypical parts. Our experimental results demonstrate that ICICLE reduces the interpretability concept drift and outperforms the existing exemplar-free methods of common class-incremental learning when applied to concept-based models.

In this work, we propose the novel Prototypical Graph Regression Self-explainable Trees (ProGReST) model, which combines prototype learning, soft decision trees, and Graph Neural Networks. In contrast to other works, our model can be used to address various challenging tasks, including compound property prediction. In ProGReST, the rationale is obtained along with prediction due to the model's built-in interpretability. Additionally, we introduce a new graph prototype projection to accelerate model training. Finally, we evaluate PRoGReST on a wide range of chemical datasets for molecular property prediction and perform in-depth analysis with chemical experts to evaluate obtained interpretations. Our method achieves competitive results against state-of- the-art methods.

We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set. To achieve accuracy comparable to baseline methods, we adapt the mechanism of prototypical parts and introduce a diversity loss function that increases the variety of prototypes within each class. We show that ProtoSeg discovers semantic concepts, in contrast to standard segmentation models. Experiments conducted on Pascal VOC and Cityscapes datasets confirm the precision and transparency of the presented method.

Preliminary microbiological diagnosis usually relies on microscopic examination and, due to the routine culture and bacteriological examination, lasts up to 11 days. Hence, many deep learning methods based on microscopic images were recently introduced to replace the time-consuming bacteriological examination. They shorten the diagnosis by 1-2 days but still require iterative culture to obtain monoculture samples. In this work, we present a feasibility study for further shortening the diagnosis time by analyzing polyculture images. It is possible with multi-MIL, a novel multi-label classification method based on multiple instance learning. To evaluate our approach, we introduce a dataset containing microscopic images for all combinations of four considered bacteria species. We obtain ROC AUC above 0.9, proving the feasibility of the method and opening the path for future experiments with a larger number of species.

Abstract The rapid development of histopathology scanners allowed the digital transformation of pathology. Current devices fastly and accurately digitize histology slides on many magnifications, resulting in whole slide images (WSI). However, direct application of supervised deep learning methods to WSI highest magnification is impossible due to hardware limitations. That is why WSI classification is usually analyzed using standard Multiple Instance Learning (MIL) approaches, that do not explain their predictions, which is crucial for medical applications. In this work, we fill this gap by introducing ProtoMIL, a novel self-explainable MIL method inspired by the case-based reasoning process that operates on visual prototypes. Thanks to incorporating prototypical features into objects description, ProtoMIL unprecedentedly joins the model accuracy and fine-grained interpretability, as confirmed by the experiments conducted on five recognized whole-slide image datasets.

In this work, we automatically distinguish between different clones of the same bacteria species (Klebsiella pneumoniae) based only on microscopic images. It is a challenging task, previously seemed unreachable due to the high clones' similarity. For this purpose, we apply a multi-step algorithm with attention-based deep multiple instance learning, which returns parts of the image crucial to the prediction. Except for obtaining high accuracy, we introduce extensive explainability based on persistence homology, increasing the understandability and trust in the model. Our work opens a plethora of research pathways towards cheaper and faster epidemiological management.

In this work, we introduce an extension to ProtoPNet called ProtoPShare which shares prototypical parts between classes. To obtain prototype sharing we prune prototypical parts using a novel data-dependent similarity. Our approach substantially reduces the number of prototypes needed to preserve baseline accuracy and finds prototypical similarities between classes. We show the effectiveness of ProtoPShare on the CUB-200-2011 and the Stanford Cars datasets and confirm the semantic consistency of its prototypical parts in user-study.

Not all supervised learning problems are described by a pair of a fixed-size input tensor and a label. In some cases, especially in medical image analysis, a label corresponds to a bag of instances (e.g. image patches), and to classify such bag, aggregation of information from all of the instances is needed. There have been several attempts to create a model working with a bag of instances, however, they are assuming that there are no dependencies within the bag and the label is connected to at least one instance. In this work, we introduce Self-Attention Attention-based MIL Pooling (SA-AbMILP) aggregation operation to account for the dependencies between instances. We conduct several experiments on MNIST, histological, microbiological, and retinal databases to show that SA-AbMILP performs better than other models. Additionally, we investigate kernel variations of Self-Attention and their influence on the results.