학술논문
Causal Intervention for Object Detection
Document Type
Conference
Author
Source
2021 IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI) ICTAI Tools with Artificial Intelligence (ICTAI), 2021 IEEE 33rd International Conference on. :770-774 Nov, 2021
Subject
Language
ISSN
2375-0197
Abstract
We present a causal intervention module (CIM) to improve object detection methods. State-of-the-art object detectors learn the association between image pixels and bounding boxes with labels, which implicitly use contextual information in the backbone. Intuitively, context is such a rich source of information that an improvement due to contextual information is relatively modest. Inspired by this, we use the context explicitly in a novel framework of causal intervention for object detection. Specifically, we use a structural causal model to reveal how context confounders affect the object detection model, and adopt causal intervention to deal with the effect. The proposed CIM is applied to a two-stage object detection baseline, and extensive experiments show its effectiveness.