20 citations · 59 across the 17 of their papers we have counts for
18 papers
Robust Topological Orderings for Directed Graphs
James Smith
We modify the Pearce-Kelly algorithm that maintains a topological ordering for a directed acyclic graph in order to allow cycles to be tolerated. Cycles make topological orderings…
Continual Adaptation of Vision Transformers for Federated Learning
Shaunak Halbe, James Seale Smith, Junjiao Tian +1
In this paper, we focus on the important yet understudied problem of Continual Federated Learning (CFL), where a server communicates with a set of clients to incrementally learn ne…
Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA
James Seale Smith, Yen-Chang Hsu, Lingyu Zhang +4
Recent works demonstrate a remarkable ability to customize text-to-image diffusion models while only providing a few example images. What happens if you try to customize such model…
Going Beyond Nouns With Vision & Language Models Using Synthetic Data
Paola Cascante-Bonilla, Khaled Shehada, James Seale Smith +8
Large-scale pre-trained Vision & Language (VL) models have shown remarkable performance in many applications, enabling replacing a fixed set of supported classes with zero-shot ope…
System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games
Indranil Sur, Zachary Daniels, Abrar Rahman +16
As Artificial and Robotic Systems are increasingly deployed and relied upon for real-world applications, it is important that they exhibit the ability to continually learn and adap…
On the Transferability of Visual Features in Generalized Zero-Shot Learning
Paola Cascante-Bonilla, Leonid Karlinsky, James Seale Smith +2
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…
Secret Sharing for Generic Theoretic Cryptography
James Smith
Sharing a secret efficiently amongst a group of participants is not easy since there is always an adversary / eavesdropper trying to retrieve the secret. In secret sharing schemes,…
CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning
James Seale Smith, Leonid Karlinsky, Vyshnavi Gutta +6
Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this c…
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
James Seale Smith, Paola Cascante-Bonilla, Assaf Arbelle +7
Recently, large-scale pre-trained Vision-and-Language (VL) foundation models have demonstrated remarkable capabilities in many zero-shot downstream tasks, achieving competitive res…
FedFOR: Stateless Heterogeneous Federated Learning with First-Order Regularization
Junjiao Tian, James Seale Smith, Zsolt Kira
Federated Learning (FL) seeks to distribute model training across local clients without collecting data in a centralized data-center, hence removing data-privacy concerns. A major…
Lifelong Wandering: A realistic few-shot online continual learning setting
Mayank Lunayach, James Smith, Zsolt Kira
Online few-shot learning describes a setting where models are trained and evaluated on a stream of data while learning emerging classes. While prior work in this setting has achiev…
Incremental Learning with Differentiable Architecture and Forgetting Search
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 i…
A Closer Look at Knowledge Distillation with Features, Logits, and Gradients
Yen-Chang Hsu, James Smith, Yilin Shen +2
Knowledge distillation (KD) is a substantial strategy for transferring learned knowledge from one neural network model to another. A vast number of methods have been developed for…
A Closer Look at Rehearsal-Free Continual Learning
James Seale Smith, Junjiao Tian, Shaunak Halbe +2
Continual learning is a setting where machine learning models learn novel concepts from continuously shifting training data, while simultaneously avoiding degradation of knowledge…
Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning
James Smith, Yen-Chang Hsu, Jonathan Balloch +3
Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgett…
Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer
James Smith, Jonathan Balloch, Yen-Chang Hsu +1
Rehearsal is a critical component for class-incremental continual learning, yet it requires a substantial memory budget. Our work investigates whether we can significantly reduce t…
Unsupervised Progressive Learning and the STAM Architecture
James Smith, Cameron Taylor, Seth Baer +1
We first pose the Unsupervised Progressive Learning (UPL) problem: an online representation learning problem in which the learner observes a non-stationary and unlabeled data strea…
Operational Concurrency Control in the Face of Arbitrary Scale and Latency
James Smith
We present for the first time a complete solution to the problem of proving the correctness of a concurrency control algorithm for collaborative text editors against the standard c…