Related papers: Hierarchy-Consistent Learning and Adaptive Loss Ba…

Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…

Anomaly detection aims at identifying deviant samples from the normal data distribution. Contrastive learning has provided a successful way to sample representation that enables effective discrimination on anomalies. However, when…

We study how to design learning-based adaptive controllers that enable fast and accurate online adaptation in changing environments. In these settings, learning is typically done during an initial (offline) design phase, where the vehicle…

Classification is a fundamental task in machine learning. While conventional methods-such as binary, multiclass, and multi-label classification-are effective for simpler problems, they may not adequately address the complexities of some…

Hierarchical reinforcement learning (HRL) has seen widespread interest as an approach to tractable learning of complex modular behaviors. However, existing work either assume access to expert-constructed hierarchies, or use…

Multi-task learning (MTL) can improve performance on a task by sharing representations with one or more related auxiliary-tasks. Usually, MTL-networks are trained on a composite loss function formed by a constant weighted combination of the…

Hierarchical text classification is a challenging subtask of multi-label classification due to its complex label hierarchy. Existing methods encode text and label hierarchy separately and mix their representations for classification, where…

This paper investigates, from information theoretic grounds, a learning problem based on the principle that any regularity in a given dataset can be exploited to extract compact features from data, i.e., using fewer bits than needed to…

Multi-task learning (MTL) has become an essential machine learning tool for addressing multiple learning tasks simultaneously and has been effectively applied across fields such as healthcare, marketing, and biomedical research. However, to…

Recent advances in Hierarchical Multi-label Classification (HMC), particularly neurosymbolic-based approaches, have demonstrated improved consistency and accuracy by enforcing constraints on a neural model during training. However, such…

Vision-Language Models (VLMs), with their powerful content generation capabilities, have been successfully applied to data annotation processes. However, the VLM-generated labels exhibit dual limitations: low quality (i.e., label noise) and…

Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only…

Hierarchical Extreme Multi-Label Classification poses greater difficulties compared to traditional multi-label classification because of the intricate hierarchical connections of labels within a domain-specific taxonomy and the substantial…

Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolving task distributions. Existing approaches rely on fixed compression strategies (e.g.,…

We propose a novel framework and a solution to tackle the continual learning (CL) problem with changing network architectures. Most CL methods focus on adapting a single architecture to a new task/class by modifying its weights. However,…

Hierarchical text classification (HTC) is a challenging subtask of multi-label classification due to its complex label hierarchy. Recently, the pretrained language models (PLM)have been widely adopted in HTC through a fine-tuning paradigm.…

Classification algorithms in machine learning often assume a flat label space. However, most real world data have dependencies between the labels, which can often be captured by using a hierarchy. Utilizing this relation can help develop a…

Traditional Multi-level Hierarchical Classification (MLHC) classifiers often rely on backbone models with $n$ independent output layers. This structure tends to overlook the hierarchical relationships between classes, leading to…

Hierarchical classification aims to sort the object into a hierarchical structure of categories. For example, a bird can be categorized according to a three-level hierarchy of order, family, and species. Existing methods commonly address…

Achieving safe and coordinated behavior in dynamic, constraint-rich environments remains a major challenge for learning-based control. Pure end-to-end learning often suffers from poor sample efficiency and limited reliability, while…