AIConfPaper
← Search

Frederic Z Zhang

7 accepted papers

2025

RandLoRA: Full rank parameter-efficient fine-tuning of large models

Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Cristian Rodriguez-Opazo, Anton van den Hengel, Ehsan Abbasnejad
ICLR 2025poster

Low-Rank Adaptation (LoRA) and its variants have shown impressive results in reducing the number of trainable parameters and memory requirements of large transformer networks while maintaining fine-tuning performance. The low-rank nature of the weight update inherently limits the representation powe…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Towards Higher Effective Rank in Parameter-Efficient Fine-tuning using Khatri-Rao Product

Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Anton van den Hengel, Ehsan Abbasnejad
ICCV 2025poster

Parameter-efficient fine-tuning (PEFT) has become a standard for adapting large pre-trained models. While low-rank adaptation (LoRA) has achieved notable success, recent studies highlight its limitations when compared to full-rank variants, particularly when scaling to demanding tasks such as vision…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling

Frederic Z. Zhang, Paul Albert, Cristian Rodriguez-Opazo, Anton van den Hengel, Ehsan Abbasnejad
NeurIPS 2024poster

Pre-trained models produce strong generic representations that can be adapted via fine-tuning on specialised datasets. The learned weight difference relative to the pre-trained model, known as a task vector, characterises the direction and stride of fine-tuning that enables the model to capture thes…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2023

Exploring Predicate Visual Context in Detecting of Human-Object Interactions

Frederic Z Zhang, Yuhui Yuan, Dylan Campbell, Zhuoyao Zhong, Stephen Gould
ICCV 2023poster

Recently, the DETR framework has emerged as the dominant approach for human--object interaction (HOI) research. In particular, two-stage transformer-based HOI detectors are amongst the most performant and training-efficient approaches. However, these often condition HOI classification on object feat…

Cited by 50PDF ↗code ↗Scholar ↗
2022

Efficient Two-Stage Detection of Human-Object Interactions With a Novel Unary-Pairwise Transformer

Frederic Z. Zhang, Dylan Campbell, Stephen Gould
CVPR 2022poster

Recent developments in transformer models for visual data have led to significant improvements in recognition and detection tasks. In particular, using learnable queries in place of region proposals has given rise to a new class of one-stage detection models, spearheaded by the Detection Transformer…

Cited by 143PDF ↗code ↗Scholar ↗
2021

Memory-Augmented Dynamic Neural Relational Inference

Dong Gong, Frederic Z. Zhang, Javen Qinfeng Shi, Anton van den Hengel
ICCV 2021poster

Dynamic interacting systems are prevalent in vision tasks. These interactions are usually difficult to observe and measure directly, and yet understanding latent interactions is essential for performing inference tasks on dynamic systems like forecasting. Neural relational inference (NRI) techniques…

Cited by 13PDF ↗Scholar ↗
2021

Spatially Conditioned Graphs for Detecting Human-Object Interactions

Frederic Z. Zhang, Dylan Campbell, Stephen Gould
ICCV 2021poster

We address the problem of detecting human-object interactions in images using graphical neural networks. Unlike conventional methods, where nodes send scaled but otherwise identical messages to each of their neighbours, we propose to condition messages between pairs of nodes on their spatial relatio…

Cited by 147PDF ↗code ↗Scholar ↗