paper-with-me

Papers

Revisiting ensembling for improving the performance of deep learning models

2022-08-21 · 8th International Workshop Image Mining: Theory and Applications 2022 8 · Antonio Bruno, Davide Moroni, Massimo Martinelli

Ensembling is a very well-known strategy consisting in fusing several different models to achieve a new model for classification or regression tasks. Over the years, ensembling has been proven to provide superior performance in various contexts related to pattern recognition and artificial intelligence. Moreover, the basic ideas that are at the basis of ensembling have been a source of inspiration for the design of the most recent deep learning architectures. Indeed, a close analysis of those architectures shows that some connections among layers and groups of layers achieve effects similar to those obtainable by bagging, boosting and stacking, which are the well-known three basic approaches to ensembling. However, we argue that research has not fully leveraged the potential offered by ensembling. Indeed, this paper investigates some possible approaches to the combination of weak learners, or sub-components of weak learners, in the context of bagging. Based on previous results obtained in specific domains, we extend the approach to a reference dataset obtaining encouraging results.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningImage Classification

Similar Papers 제목 키워드 기반

Revisiting Ensembling in One-Shot Federated Learning

2024-11-11 · Youssef Allouah, Akash Dhasade, Rachid Guerraoui, Nirupam Gupta 외

Federated learning (FL) is an appealing approach to training machine learning models without sharing raw data. However, standard FL algorithms are iterative and thus induce a significant communication cost. One-shot fede…

Federated Learning

Revisiting Single-gated Mixtures of Experts

2023-04-11 · Amelie Royer, Ilia Karmanov, Andrii Skliar, Babak Ehteshami Bejnordi 외

Mixture of Experts (MoE) are rising in popularity as a means to train extremely large-scale models, yet allowing for a reasonable computational cost at inference time. Recent state-of-the-art approaches usually assume a …

Mixture-of-Experts

Revisiting semi-supervised learning in the era of foundation models

2025-03-12 · Ping Zhang, Zheda Mai, Quang-Huy Nguyen, Wei-Lun Chao

Semi-supervised learning (SSL) leverages abundant unlabeled data alongside limited labeled data to enhance learning. As vision foundation models (VFMs) increasingly serve as the backbone of vision applications, it remain…

parameter-efficient fine-tuningPseudo Label

Multi-Layer Ensembling Techniques for Multilingual Intent Classification

2018-06-20 · Charles Costello, Ruixi Lin, Vishwas Mruthyunjaya, Bettina Bolla 외

In this paper we determine how multi-layer ensembling improves performance on multilingual intent classification. We develop a novel multi-layer ensembling approach that ensembles both different model initializations and…

ClassificationGeneral Classificationintent-classificationIntent Classification

When are ensembles really effective?

2023-05-21 · NeurIPS 2023 11

Ensembling has a long history in statistical data analysis, with many impactful applications. However, in many modern machine learning settings, the benefits of ensembling are less ubiquitous and less obvious. We study, …