Adaptive Convolution for Object Detection

By Chunlin Chen, Q. Ling. 2019

36 citations recorded by the source corpus.

It is quite challenging to detect objects, especially, small objects, in complex scenes. To solve this problem, we propose a novel module named as adaptive convolution block (ACB), which adaptively adjusts the parameters of convolutional filters according to the current feature maps, and then, filter these feature maps with the obtained adaptive convolutional filters to generate enhanced features. Due to such adaptive convolution, the enhanced features can pay more attention to the concerned objects, suppress the interference information caused by irrelevant surroundings, and efficiently improve the detection accuracy. The proposed ACB is light weight and fast. By directly embedding the ACB into the single shot detection framework, we construct a novel real-time adaptive convolutional detector (ACD). Experiments on PASCAL VOC and MS COCO benchmarks confirm that our ACD outperforms the existing state-of-the-art single-stage detection models, and achieves a better tradeoff between accuracy and speed.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

  1. Shiji Song
  2. Yulin Wang
  3. Gao Huang
  4. Yizeng Han
  5. Le Yang
  6. Yong Liu
  7. Honghui Wang
  8. Mengmeng Wang

Citations in the corpus