no code implementations • 18 Apr 2024 • James Seale Smith, Lazar Valkov, Shaunak Halbe, Vyshnavi Gutta, Rogerio Feris, Zsolt Kira, Leonid Karlinsky
This continual learning (CL) phenomenon has been extensively studied, but primarily in a setting where only a small amount of past data can be stored.
no code implementations • 30 Nov 2023 • James Seale Smith, Yen-Chang Hsu, Zsolt Kira, Yilin Shen, Hongxia Jin
We show that STAMINA outperforms the prior SOTA for the setting of text-to-image continual customization on a 50-concept benchmark composed of landmarks and human faces, with no stored replay data.
no code implementations • 16 Jun 2023 • Shaunak Halbe, James Seale Smith, Junjiao Tian, Zsolt Kira
In this paper, we attempt to tackle forgetting and heterogeneity while minimizing overhead costs and without requiring access to any stored data.
no code implementations • 12 Apr 2023 • James Seale Smith, Yen-Chang Hsu, Lingyu Zhang, Ting Hua, Zsolt Kira, Yilin Shen, Hongxia Jin
We show that C-LoRA not only outperforms several baselines for our proposed setting of text-to-image continual customization, which we refer to as Continual Diffusion, but that we achieve a new state-of-the-art in the well-established rehearsal-free continual learning setting for image classification.
1 code implementation • ICCV 2023 • Paola Cascante-Bonilla, Khaled Shehada, James Seale Smith, Sivan Doveh, Donghyun Kim, Rameswar Panda, Gül Varol, Aude Oliva, Vicente Ordonez, Rogerio Feris, Leonid Karlinsky
We contribute Synthetic Visual Concepts (SyViC) - a million-scale synthetic dataset and data generation codebase allowing to generate additional suitable data to improve VLC understanding and compositional reasoning of VL models.
Ranked #68 on Visual Reasoning on Winoground
1 code implementation • CVPR 2023 • James Seale Smith, Leonid Karlinsky, Vyshnavi Gutta, Paola Cascante-Bonilla, Donghyun Kim, Assaf Arbelle, Rameswar Panda, Rogerio Feris, Zsolt Kira
Our experiments show that we outperform the current SOTA method DualPrompt on established benchmarks by as much as 4. 5% in average final accuracy.
1 code implementation • 22 Nov 2022 • Paola Cascante-Bonilla, Leonid Karlinsky, James Seale Smith, Yanjun Qi, Vicente Ordonez
Generalized Zero-Shot Learning (GZSL) aims to train a classifier that can generalize to unseen classes, using a set of attributes as auxiliary information, and the visual features extracted from a pre-trained convolutional neural network.
1 code implementation • CVPR 2023 • James Seale Smith, Paola Cascante-Bonilla, Assaf Arbelle, Donghyun Kim, Rameswar Panda, David Cox, Diyi Yang, Zsolt Kira, Rogerio Feris, Leonid Karlinsky
This leads to reasoning mistakes, which need to be corrected as they occur by teaching VL models the missing SVLC skills; often this must be done using private data where the issue was found, which naturally leads to a data-free continual (no task-id) VL learning setting.
1 code implementation • 21 Sep 2022 • Junjiao Tian, James Seale Smith, Zsolt Kira
For the more typical applications of FL where the number of clients is large (e. g., edge-device and mobile applications), these methods cannot be applied, motivating the need for a stateless approach to heterogeneous FL which can be used for any number of clients.
no code implementations • 19 May 2022 • James Seale Smith, Zachary Seymour, Han-Pang Chiu
As progress is made on training machine learning models on incrementally expanding classification tasks (i. e., incremental learning), a next step is to translate this progress to industry expectations.
no code implementations • 31 Mar 2022 • James Seale Smith, Junjiao Tian, Shaunak Halbe, Yen-Chang Hsu, Zsolt Kira
Next, we explore how to leverage knowledge from a pre-trained model in rehearsal-free continual learning and find that vanilla L2 parameter regularization outperforms EWC parameter regularization and feature distillation.