Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors

By Hong-Yu Zhou, Bin-Bin Gao, Jianxin Wu. 2017

37 citations recorded by the source corpus.

Object detection aims at high speed and accuracy simultaneously. However, fast models are usually less accurate, while accurate models cannot satisfy our need for speed. A fast model can be 10 times faster but 50% less accurate than an accurate model. In this paper, we propose Adaptive Feeding (AF) to combine a fast (but less accurate) detector and an accurate (but slow) detector, by adaptively determining whether an image is easy or hard and choosing an appropriate detector for it. In practice, we build a cascade of detectors, including the AF classifier which make the easy vs. hard decision and the two detectors. The AF classifier can be tuned to obtain different tradeoff between speed and accuracy, which has negligible training time and requires no additional training data. Experimental results on the PASCAL VOC, MS COCO and Caltech Pedestrian datasets confirm that AF has the ability to achieve comparable speed as the fast detector and comparable accuracy as the accurate one at the same time. As an example, by combining the fast SSD300 with the accurate SSD500 detector, AF leads to 50% speedup over SSD500 with the same precision on the VOC2007 test set.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Aniruddha Kembhavi
2. Ali Farhadi
3. Alan L. Yuille
4. Mohit Bansal
5. Mohammad Rastegari
6. Jianfeng Gao
7. Luke S. Zettlemoyer
8. Huiyu Wang

In Computer Vision and Pattern Recognition

1. Alan L. Yuille
2. Luc Van Gool
3. Ali Farhadi
4. Dacheng Tao
5. Xiaogang Wang
6. Jitendra Malik
7. Li Fei-Fei
8. Aniruddha Kembhavi

In Efficiency & Compression

1. Ali Farhadi
2. Mohammad Rastegari
3. Alan L. Yuille
4. Aniruddha Kembhavi
5. Huiyu Wang
6. Song Han
7. Yunhe Wang
8. Dacheng Tao

Citations in the corpus

• A Survey of Deep Learning-Based Object Detection (2019, background): “[125] combine an accurate (but slow) detector and a fast (but less accurate) detector adaptively determining whether an image is easy or hard to detect and choosing an appropriate detector to”
• ELASTIC: Improving CNNs With Dynamic Scaling Policies (2018, methodology): “In addition, [4] used 2 CNNs to deal with high and low frequencies, and [40] proposed to adaptively choose from 2 CNNs with different capacity.”