相关论文: Rashomon Sets for Prototypical-Part Networks: Edit…

Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), but their lack of interpretability has been a major concern. Current methods for interpreting LLMs are post hoc, applied after…

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…

The deep CNNs in image semantic segmentation typically require a large number of densely-annotated images for training and have difficulties in generalizing to unseen object categories. Therefore, few-shot segmentation has been developed to…

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction…

Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness. Anomalies are rare and hard to collect and supervised models easily over-fit to these seen anomalies with a handful of…

Recent success of semantic segmentation approaches on demanding road driving datasets has spurred interest in many related application fields. Many of these applications involve real-time prediction on mobile platforms such as cars, drones…

In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector.…

Recognizing relations between entities is a pivotal task of relational learning. Learning relation representations from distantly-labeled datasets is difficult because of the abundant label noise and complicated expressions in human…

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…

Different prediction models might perform equally well (Rashomon set) in the same task, but offer conflicting interpretations and conclusions about the data. The Rashomon effect in the context of Explainable AI (XAI) has been recognized as…

Face representation learning using datasets with a massive number of identities requires appropriate training methods. Softmax-based approach, currently the state-of-the-art in face recognition, in its usual "full softmax" form is not…

Neural networks have in recent years shown promise for helping software engineers write programs and even formally verify them. While semantic information plays a crucial part in these processes, it remains unclear to what degree popular…

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on text classification tasks with their powerful word embeddings, but their black-box nature, which leads to a lack of…

MOTIVATION: Proteins fold into complex structures that are crucial for their biological functions. Experimental determination of protein structures is costly and therefore limited to a small fraction of all known proteins. Hence, different…

In many application domains, it is important to characterize how complex learned models make their decisions across the distribution of instances. One way to do this is to identify the features and interactions among them that contribute to…

We introduce Prototype Generation, a stricter and more robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. We demonstrate its ability to generate inputs that result in…

The large language models have achieved superior performance on various natural language tasks. One major drawback of such approaches is they are resource-intensive in fine-tuning new datasets. Soft-prompt tuning presents a…

Despite the advances achieved by neural models in sequence to sequence learning, exploited in a variety of tasks, they still make errors. In many use cases, these are corrected by a human expert in a posterior revision process. The…

Articulated human pose estimation is a fundamental yet challenging task in computer vision. The difficulty is particularly pronounced in scale variations of human body parts when camera view changes or severe foreshortening happens.…