Search Results for author:
Found 33 papers, 19 papers with code
AI-Driven Rapid Identification of Bacterial and Fungal Pathogens in Blood Smears of Septic Patients
A total of 16, 637 Gram-stained microscopic images were used in the study.
This looks like what? Challenges and Future Research Directions for Part-Prototype Models
The growing interest in eXplainable Artificial Intelligence (XAI) has prompted research into models with built-in interpretability, the most prominent of which are part-prototype models.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
Parameter-Efficient Interventions for Enhanced Model Merging
Model merging combines knowledge from task-specific models into a unified multi-task model to avoid joint training on all task data.
Beyond [cls]: Exploring the true potential of Masked Image Modeling representations
Masked Image Modeling (MIM) has emerged as a popular method for Self-Supervised Learning (SSL) of visual representations.
OMENN: One Matrix to Explain Neural Networks
This matrix is constructed through a series of linear transformations that represent the processing of the input by each successive layer in the neural network.
Revisiting FunnyBirds evaluation framework for prototypical parts networks
In this study, we comprehensively compare metric scores obtained for two types of ProtoPNet visualizations: bounding boxes and similarity maps.
A deep cut into Split Federated Self-supervised Learning
Collaborative self-supervised learning has recently become feasible in highly distributed environments by dividing the network layers between client devices and a central server.
LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
Prototypical parts networks combine the power of deep learning with the explainability of case-based reasoning to make accurate, interpretable decisions.
AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale
Active Visual Exploration (AVE) is a task that involves dynamically selecting observations (glimpses), which is critical to facilitate comprehension and navigation within an environment.
ProPML: Probability Partial Multi-label Learning
Partial Multi-label Learning (PML) is a type of weakly supervised learning where each training instance corresponds to a set of candidate labels, among which only some are true.
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know.
TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration
Active Visual Exploration (AVE) optimizes the utilization of robotic resources in real-world scenarios by sequentially selecting the most informative observations.
Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers
Vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches.
Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations
Prototypical parts-based networks are becoming increasingly popular due to their faithful self-explanations.
ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging
The most common MIL model is when we consider a bag as positive if at least one of its instances has a positive label.
Augmentation-aware Self-supervised Learning with Conditioned Projector
By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches.
ICICLE: Interpretable Class Incremental Continual Learning
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.
Active Visual Exploration Based on Attention-Map Entropy
Active visual exploration addresses the issue of limited sensor capabilities in real-world scenarios, where successive observations are actively chosen based on the environment.
ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts
We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set.
ProPaLL: Probabilistic Partial Label Learning
Partial label learning is a type of weakly supervised learning, where each training instance corresponds to a set of candidate labels, among which only one is true.
Interpretable Image Classification with Differentiable Prototypes Assignment
We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes.
ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification
Multiple Instance Learning (MIL) gains popularity in many real-life machine learning applications due to its weakly supervised nature.
SONG: Self-Organizing Neural Graphs
Recent years have seen a surge in research on deep interpretable neural networks with decision trees as one of the most commonly incorporated tools.
Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations
Motivated by this observation, we introduce a novel visual probing framework for explaining the self-supervised models by leveraging probing tasks employed previously in natural language processing.
Classifying bacteria clones using attention-based deep multiple instance learning interpreted by persistence homology
In this work, we analyze if it is possible to distinguish between different clones of the same bacteria species (Klebsiella pneumoniae) based only on microscopic images.
ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery
In this paper, we introduce ProtoPShare, a self-explained method that incorporates the paradigm of prototypical parts to explain its predictions.
Kernel Self-Attention in Deep Multiple Instance Learning
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.
Deep learning approach to describe and classify fungi microscopic images
Preliminary diagnosis of fungal infections can rely on microscopic examination.
Deep learning approach to description and classification of fungi microscopic images
Diagnosis of fungal infections can rely on microscopic examination, however, in many cases, it does not allow unambiguous identification of the species due to their visual similarity.
Persistence Bag-of-Words for Topological Data Analysis
Persistent homology (PH) is a rigorous mathematical theory that provides a robust descriptor of data in the form of persistence diagrams (PDs).
Processing of missing data by neural networks
We propose a general, theoretically justified mechanism for processing missing data by neural networks.
Cascade context encoder for improved inpainting
For this purpose, we train context encoder for 64x64 pixels images in a standard way and use its resized output to fill in the missing input region of the 128x128 context encoder, both in training and evaluation phase.
Topological descriptors for 3D surface analysis
We investigate topological descriptors for 3D surface analysis, i. e. the classification of surfaces according to their geometric fine structure.
