5 papers
Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns
Yameng Peng, Andy Song, HaythamM. Fayek +2
Zero-shot proxies, also known as training-free metrics, are widely adopted to reduce the computational overhead in neural network evaluation for scenarios such as Neural Architectu…
Learning A Zero-shot Occupancy Network from Vision Foundation Models via Self-supervised Adaptation
Sihao Lin, Daqi Liu, Ruochong Fu +6
Estimating the 3D world from 2D monocular images is a fundamental yet challenging task due to the labour-intensive nature of 3D annotations. To simplify label acquisition, this wor…
MLP Can Be A Good Transformer Learner
Sihao Lin, Pumeng Lyu, Dongrui Liu +4
Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of comput…
Self-Supervised Multi-Frame Neural Scene Flow
Dongrui Liu, Daqi Liu, Xueqian Li +5
Neural Scene Flow Prior (NSFP) and Fast Neural Scene Flow (FNSF) have shown remarkable adaptability in the context of large out-of-distribution autonomous driving. Despite their su…
SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS
Yameng Peng, Andy Song, Haytham M. Fayek +2
Training-free metrics (a.k.a. zero-cost proxies) are widely used to avoid resource-intensive neural network training, especially in Neural Architecture Search (NAS). Recent studies…