Author name cluster

Robert Mullins

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

NeurIPS Conference 2025 Conference Paper

PhySwin: An Efficient and Physically-Informed Foundation Model for Multispectral Earth Observation

Chong Tang
Joseph Powell
Dirk Koch
Robert Mullins
Alex Weddell
Jagmohan Chauhan

Recent progress on Remote Sensing Foundation Models (RSFMs) aims toward universal representations for Earth observation imagery. However, current efforts often scale up in size significantly without addressing efficiency constraints critical for real-world applications (e. g. , onboard processing, rapid disaster response) or treat multispectral (MS) data as generic imagery, overlooking valuable physical priors. We introduce PhySwin, a foundation model for MS data that integrates physical priors with computational efficiency. PhySwin combines three innovations: (i) physics-informed pretraining objectives leveraging radiometric constraints to enhance feature learning; (ii) an efficient MixMAE formulation tailored to SwinV2 for low-FLOP, scalable pretraining; and (iii) token-efficient spectral embedding to retain spectral detail without increasing token counts. Pretrained on over 1M Sentinel-2 tiles, PhySwin achieves SOTA results (+1. 32\% mIoU segmentation, +0. 80\% F1 change detection) while reducing inference latency by up to 14. 4$\times$ and computational complexity by up to 43. 6$\times$ compared to ViT-based RSFMs.

PDF Details

NeurIPS Conference 2024 Conference Paper

Beyond Slow Signs in High-fidelity Model Extraction

Hanna Foerster
Robert Mullins
Ilia Shumailov
Jamie Hayes

Deep neural networks, costly to train and rich in intellectual property value, areincreasingly threatened by model extraction attacks that compromise their confiden-tiality. Previous attacks have succeeded in reverse-engineering model parametersup to a precision of float64 for models trained on random data with at most threehidden layers using cryptanalytical techniques. However, the process was identifiedto be very time consuming and not feasible for larger and deeper models trained onstandard benchmarks. Our study evaluates the feasibility of parameter extractionmethods of Carlini et al. [1] further enhanced by Canales-Martínez et al. [2] formodels trained on standard benchmarks. We introduce a unified codebase thatintegrates previous methods and reveal that computational tools can significantlyinfluence performance. We develop further optimisations to the end-to-end attackand improve the efficiency of extracting weight signs by up to 14. 8 times com-pared to former methods through the identification of easier and harder to extractneurons. Contrary to prior assumptions, we identify extraction of weights, notextraction of weight signs, as the critical bottleneck. With our improvements, a16, 721 parameter model with 2 hidden layers trained on MNIST is extracted withinonly 98 minutes compared to at least 150 minutes previously. Finally, addressingmethodological deficiencies observed in previous studies, we propose new ways ofrobust benchmarking for future model extraction attacks.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Rapid Model Architecture Adaption for Meta-Learning

Yiren Zhao
Xitong Gao
I Shumailov
Nicolo Fusi
Robert Mullins

Network Architecture Search (NAS) methods have recently gathered much attention. They design networks with better performance and use a much shorter search time compared to traditional manual tuning. Despite their efficiency in model deployments, most NAS algorithms target a single task on a fixed hardware system. However, real-life few-shot learning environments often cover a great number of tasks ($T$) and deployments on a wide variety of hardware platforms ($H$). The combinatorial search complexity $T \times H$ creates a fundamental search efficiency challenge if one naively applies existing NAS methods to these scenarios. To overcome this issue, we show, for the first time, how to rapidly adapt model architectures to new tasks in a \emph{many-task many-hardware} few-shot learning setup by integrating Model Agnostic Meta Learning (MAML) into the NAS flow. The proposed NAS method (H-Meta-NAS) is hardware-aware and performs optimisation in the MAML framework. MetaNAS shows a Pareto dominance compared to a variety of NAS and manual baselines in popular few-shot learning benchmarks with various hardware platforms and constraints. In particular, on the 5-way 1-shot Mini-ImageNet classification task, the proposed method outperforms the best manual baseline by a large margin ($5. 21\%$ in accuracy) using $60\%$ less computation.

PDF Details

AILAW Journal 2022 Journal Article

Two factor-based models of precedential constraint: a comparison and proposal

Robert Mullins

Abstract The article considers two different interpretations of the reason model of precedent pioneered by John Horty. On a plausible interpretation of the reason model, past cases provide reasons to prioritize reasons favouring the same outcome as a past case over reasons favouring the opposing outcome. Here I consider the merits of this approach to the role of precedent in legal reasoning in comparison with a closely related view favoured by some legal theorists, according to which past cases provide reasons for undercutting (or ‘excluding’) reasons favouring the opposing outcome. After embedding both accounts within a general default logic, I note some important differences between the two approaches that emerge as a result of plausible distinctions between rebutting and undercutting defeat in formal models of legal reasoning. These differences stem from the ‘preference independence’ of undercutting defeat. Undercutting reasons succeed in defeating opposing reasons irrespective of their relative strength. As a result, the two accounts differ in their account of the way in which precedents constrain judicial reasoning. I conclude by suggesting that the two approaches can be integrated within a single model, in which the distinction between undercutting and rebutting defeat is used to account for the distinction between strict and persuasive forms of precedential constraint.

Details DOI

NeurIPS Conference 2019 Conference Paper

Focused Quantization for Sparse CNNs

Yiren Zhao
Xitong Gao
Daniel Bates
Robert Mullins
Cheng-Zhong Xu

Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs poses a challenge in deploying them on constrained devices. Existing compression techniques, while excelling at reducing model sizes, struggle to be computationally friendly. In this paper, we attend to the statistical properties of sparse CNNs and present focused quantization, a novel quantization strategy based on power-of-two values, which exploits the weight distributions after fine-grained pruning. The proposed method dynamically discovers the most effective numerical representation for weights in layers with varying sparsities, significantly reducing model sizes. Multiplications in quantized CNNs are replaced with much cheaper bit-shift operations for efficient inference. Coupled with lossless encoding, we build a compression pipeline that provides CNNs with high compression ratios (CR), low computation cost and minimal loss in accuracies. In ResNet-50, we achieved a 18. 08x CR with only 0. 24% loss in top-5 accuracy, outperforming existing compression methods. We fully compress a ResNet-18 and found that it is not only higher in CR and top-5 accuracy, but also more hardware efficient as it requires fewer logic gates to implement when compared to other state-of-the-art quantization methods assuming the same throughput.

PDF Details