# Learning to Detect Instantaneous Changes with Retrospective Convolution and Static Sample Synthesis

arXiv: https://arxiv.org/abs/1811.08138 · HTML: https://mlsanity.com/paper/1811.08138/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2018.

## Built on by (most cited first, 1 of 1)

- [IDET: Iterative Difference-Enhanced Transformers for High-Quality Change Detection](https://mlsanity.com/paper/2207.09240/) (2022)

## Abstract (arXiv)

Change detection has been a challenging visual task due to the dynamic nature of real-world scenes. Good performance of existing methods depends largely on prior background images or a long-term observation. These methods, however, suffer severe degradation when they are applied to detection of instantaneously occurred changes with only a few preceding frames provided. In this paper, we exploit spatio-temporal convolutional networks to address this challenge, and propose a novel retrospective convolution, which features efficient change information extraction between the current frame and frames from historical observation. To address the problem of foreground-specific over-fitting in learning-based methods, we further propose a data augmentation method, named static sample synthesis, to guide the network to focus on learning change-cued information rather than specific spatial features of foreground. Trained end-to-end with complex scenarios, our framework proves to be accurate in detecting instantaneous changes and robust in combating diverse noises. Extensive experiments demonstrate that our proposed method significantly outperforms existing methods.