paper-with-me

Papers

Automated Search for Resource-Efficient Branched Multi-Task Networks

2020-08-24 · David Bruggemann, Menelaos Kanakis, Stamatios Georgoulis, Luc van Gool

The multi-modal nature of many vision problems calls for neural network architectures that can perform multiple tasks concurrently. Typically, such architectures have been handcrafted in the literature. However, given the size and complexity of the problem, this manual architecture exploration likely exceeds human design abilities. In this paper, we propose a principled approach, rooted in differentiable neural architecture search, to automatically define branching (tree-like) structures in the encoding stage of a multi-task neural network. To allow flexibility within resource-constrained environments, we introduce a proxyless, resource-aware loss that dynamically controls the model size. Evaluations across a variety of dense prediction tasks show that our approach consistently finds high-performing branching structures within limited resource budgets.

📄 PDF Abstract BibTeX arXiv:2008.10292

Code (2)

brdav/bmtas 공식 구현 pytorch
moukamisama/recon pytorch

Tasks

Neural Architecture Search

Similar Papers 제목 키워드 기반

Leveraging Large Language Models as Knowledge-Driven Agents for Reliable Retrosynthesis Planning

2025-01-15 · Qinyu Ma, Yuhao Zhou, Jianfeng Li

Identifying reliable synthesis pathways in materials chemistry is a complex task, particularly in polymer science, due to the intricate and often non-unique nomenclature of macromolecules. To address this challenge, we p…

Knowledge GraphsRetrievalRetrosynthesis

End-to-end driving simulation via angle branched network

2018-05-19 · Qing Wang, Long Chen, Wei Tian

Imitation learning for end-to-end autonomous driving has drawn attention from academic communities. Current methods either only use images as the input which is ambiguous when a car approaches an intersection, or use add…

Autonomous DrivingImitation LearningNavigate

Branched Multi-Task Networks: Deciding What Layers To Share

2019-04-05 · ICLR 2020 1 · Simon Vandenhende, Stamatios Georgoulis, Bert de Brabandere, Luc van Gool

In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand. Such ramified networks typically start with a number of shared layers, afte…

Multi-Task LearningNeural Architecture Search

Branched Schrödinger Bridge Matching

2025-06-10 · Sophia Tang, Yinuo Zhang, Alexander Tong, Pranam Chatterjee

Predicting the intermediate trajectories between an initial and target distribution is a central problem in generative modeling. Existing approaches, such as flow matching and Schr\"odinger Bridge Matching, effectively l…

DEFT: Differentiable Branched Discrete Elastic Rods for Modeling Furcated DLOs in Real-Time

2025-02-20 · Yizhou Chen, Xiaoyue Wu, Yeheng Zong, Yuzhen Chen 외

Autonomous wire harness assembly requires robots to manipulate complex branched cables with high precision and reliability. A key challenge in automating this process is predicting how these flexible and branched structu…