4 papers · 1 filter
YOLO-NAS-Bench: A Surrogate Benchmark with Self-Evolving Predictors for YOLO Architecture Search
Zhe Li, Xiaoyu Ding, Jiaxin Zheng +1
Neural Architecture Search (NAS) for object detection is severely bottlenecked by high evaluation cost, as fully training each candidate YOLO architecture on COCO demands days of G…
NAS-BNN: Neural Architecture Search for Binary Neural Networks
Zhihao Lin, Yongtao Wang, Jinhe Zhang +2
Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. Howev…
Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection
Xinzhu Ma, Yongtao Wang, Yinmin Zhang +5
In this work, we build a modular-designed codebase, formulate strong training recipes, design an error diagnosis toolbox, and discuss current methods for image-based 3D object dete…
DADA: Differentiable Automatic Data Augmentation
Yonggang Li, Guosheng Hu, Yongtao Wang +3
Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for opt…