no code implementations • 7 Oct 2024 • Mingxuan Liu, Zhun Zhong, Jun Li, Gianni Franchi, Subhankar Roy, Elisa Ricci
Our framework, Text Driven Semantic Multiple Clustering (TeDeSC), uses text as a proxy to concurrently reason over large image collections, discover partitioning criteria, expressed in natural language, and reveal semantic substructures.
no code implementations • 16 Jul 2024 • Thomas De Min, Subhankar Roy, Massimiliano Mancini, Stéphane Lathuilière, Elisa Ricci
To this extent, existing MU approaches assume complete or partial access to the training data, which can be limited over time due to privacy regulations.
1 code implementation • 24 May 2024 • Thomas De Min, Massimiliano Mancini, Stéphane Lathuilière, Subhankar Roy, Elisa Ricci
Since independent pathways in truly incremental scenarios will result in an explosion of computation due to the quadratically complex multi-head self-attention (MSA) operation in prompt tuning, we propose to reduce the original patch token embeddings into summarized tokens.
no code implementations • 24 Jan 2024 • Mingxuan Liu, Subhankar Roy, Wenjing Li, Zhun Zhong, Nicu Sebe, Elisa Ricci
Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR).
1 code implementation • CVPR 2024 • Yasser Benigmim, Subhankar Roy, Slim Essid, Vicky Kalogeiton, Stéphane Lathuilière
Domain Generalized Semantic Segmentation (DGSS) deals with training a model on a labeled source domain with the aim of generalizing to unseen domains during inference.
1 code implementation • 14 Dec 2023 • Imad Eddine Marouf, Subhankar Roy, Enzo Tartaglione, Stéphane Lathuilière
In this work, we study the problem of continual learning (CL) where the goal is to learn a model on a sequence of tasks, such that the data from the previous tasks becomes unavailable while learning on the current task data.
1 code implementation • 17 Oct 2023 • Imad Eddine Marouf, Subhankar Roy, Enzo Tartaglione, Stéphane Lathuilière
However, repeated fine-tuning on each task destroys the rich representations of the PTMs and further leads to forgetting previous tasks.
1 code implementation • ICCV 2023 • Giacomo Zara, Alessandro Conti, Subhankar Roy, Stéphane Lathuilière, Paolo Rota, Elisa Ricci
Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target dataset, without accessing the actual source data.
1 code implementation • 15 Jun 2023 • Tianyu Li, Subhankar Roy, Huayi Zhou, Hongtao Lu, Stephane Lathuiliere
To address this, we present CONtrastive FEaTure and pIxel alignment (CONFETI) for bridging the domain gap at both the pixel and feature levels using a unique contrastive formulation.
no code implementations • 31 May 2023 • Subhankar Roy, Riccardo Volpi, Gabriela Csurka, Diane Larlus
Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories.
1 code implementation • CVPR 2023 • Giacomo Zara, Subhankar Roy, Paolo Rota, Elisa Ricci
Open-set Unsupervised Video Domain Adaptation (OUVDA) deals with the task of adapting an action recognition model from a labelled source domain to an unlabelled target domain that contains "target-private" categories, which are present in the target but absent in the source.
1 code implementation • 31 Mar 2023 • Yasser Benigmim, Subhankar Roy, Slim Essid, Vicky Kalogeiton, Stéphane Lathuilière
Departing from the common notion of transferring only the target ``texture'' information, we leverage text-to-image diffusion models (e. g., Stable Diffusion) to generate a synthetic target dataset with photo-realistic images that not only faithfully depict the style of the target domain, but are also characterized by novel scenes in diverse contexts.
Data Augmentation
One-shot Unsupervised Domain Adaptation
+2
1 code implementation • 28 Mar 2023 • Mingxuan Liu, Subhankar Roy, Zhun Zhong, Nicu Sebe, Elisa Ricci
Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners.
1 code implementation • 9 Jan 2023 • Giacomo Zara, Victor Guilherme Turrisi da Costa, Subhankar Roy, Paolo Rota, Elisa Ricci
In this work we address a more realistic scenario, called open-set video domain adaptation (OUVDA), where the target dataset contains "unknown" semantic categories that are not shared with the source.
1 code implementation • 4 Oct 2022 • Yangsong Zhang, Subhankar Roy, Hongtao Lu, Elisa Ricci, Stéphane Lathuilière
In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions.
1 code implementation • 16 Aug 2022 • Subhankar Roy, Martin Trapp, Andrea Pilzer, Juho Kannala, Nicu Sebe, Elisa Ricci, Arno Solin
Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model.
1 code implementation • 18 Jul 2022 • Subhankar Roy, Mingxuan Liu, Zhun Zhong, Nicu Sebe, Elisa Ricci
We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data set containing disjoint yet related categories.
1 code implementation • CVPR 2021 • Zhun Zhong, Enrico Fini, Subhankar Roy, Zhiming Luo, Elisa Ricci, Nicu Sebe
In this paper, we address Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes.
1 code implementation • CVPR 2021 • Subhankar Roy, Evgeny Krivosheev, Zhun Zhong, Nicu Sebe, Elisa Ricci
In this paper we address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the task is to learn a robust predictor for all the target domains.
Ranked #2 on
Multi-target Domain Adaptation
on Office-Home
Blended-target Domain Adaptation
Multi-target Domain Adaptation
no code implementations • 19 Apr 2020 • Subhankar Roy, Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe, Elisa Ricci
In this paper we propose the first approach for Multi-Source Domain Adaptation (MSDA) based on Generative Adversarial Networks.
2 code implementations • 7 Apr 2020 • Aliaksandr Siarohin, Subhankar Roy, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe
To overcome this limitation, we propose a self-supervised deep learning method for co-part segmentation.
Ranked #3 on
Unsupervised Human Pose Estimation
on Tai-Chi-HD
no code implementations • 15 May 2019 • Cristiano Saltori, Subhankar Roy, Nicu Sebe, Giovanni Iacca
Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i. e., network architectures) and is therefore memory expensive.
1 code implementation • 2 Apr 2019 • Subhankar Roy, Enver Sangineto, Begüm Demir, Nicu Sebe
Hashing methods have been recently found very effective in retrieval of remote sensing (RS) images due to their computational efficiency and fast search speed.
1 code implementation • CVPR 2019 • Subhankar Roy, Aliaksandr Siarohin, Enver Sangineto, Samuel Rota Bulo, Nicu Sebe, Elisa Ricci
A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift.