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

arXiv: https://arxiv.org/abs/1707.06399 · HTML: https://mlsanity.com/paper/1707.06399/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2017.

## Built on by (most cited first, 12 of 12)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Dynamic Multimodal Fusion](https://mlsanity.com/paper/2204.00102/) (2022)
- [Auto-Split: A General Framework of Collaborative Edge-Cloud AI](https://mlsanity.com/paper/2108.13041/) (2021)
- [DynamicDet: A Unified Dynamic Architecture for Object Detection](https://mlsanity.com/paper/2304.05552/) (2023)
- [Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems](https://mlsanity.com/paper/2104.09286/) (2021)
- [EBJR: Energy-Based Joint Reasoning for Adaptive Inference](https://mlsanity.com/paper/2110.10343/) (2021)
- [Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?](https://mlsanity.com/paper/2110.10369/) (2021)
- [Optimizing Edge Offloading Decisions for Object Detection](https://mlsanity.com/paper/2410.18919/) (2024)
- [DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors](https://mlsanity.com/paper/2311.17098/) (2023)
- [Ensembling object detectors for image and video data analysis](https://mlsanity.com/paper/2102.04798/) (2021)
- [Accelerating Local AI on Consumer GPUs: A Hardware-Aware Dynamic Strategy for YOLOv10s](https://mlsanity.com/paper/2509.07928/) (2025)
- [The Decision Value of Perception Compute](https://mlsanity.com/paper/2609.35910/) (2026)

## Abstract (arXiv)

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.