papers

Publications (7)

cs.CL2026

Benchmarking Speech-to-Speech Translation Models

Alkis Koudounas, Hayato Futami, Quentin Jodelet +3

Speech-to-speech translation (S2ST) has advanced rapidly, but offline evaluation lacks a unified protocol: studies report non-overlapping metric subsets, preventing direct comparis…

cs.LG2023

Class-Incremental Learning using Diffusion Model for Distillation and Replay

Quentin Jodelet, Xin Liu, Yin Jun Phua +1

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data…

cs.CV2020

CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions

Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez +12

In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems…

cs.LG2025

Future-Proofing Class-Incremental Learning

Quentin Jodelet, Xin Liu, Yin Jun Phua +1

Exemplar-Free Class Incremental Learning is a highly challenging setting where replay memory is unavailable. Methods relying on frozen feature extractors have drawn attention recen…

cs.CV2021

Natural Image Reconstruction from fMRI using Deep Learning: A Survey

Zarina Rakhimberdina, Quentin Jodelet, Xin Liu +1

With the advent of brain imaging techniques and machine learning tools, much effort has been devoted to building computational models to capture the encoding of visual information…

cs.LG2019

Transfer Learning with Sparse Associative Memories

Quentin Jodelet, Vincent Gripon, Masafumi Hagiwara

In this paper, we introduce a novel layer designed to be used as the output of pre-trained neural networks in the context of classification. Based on Associative Memories, this lay…

cs.LG2022

Balanced softmax cross-entropy for incremental learning with and without memory

Quentin Jodelet, Xin Liu, Tsuyoshi Murata

When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old class…