CHAL：因果引导的分层异常感知学习用于运动红外小目标检测
CHAL: Causal-guided Hierarchical Anomaly-aware Learning for Moving Infrared Small Target Detection
将目标检测转化为背景建模下的异常发现，利用时空神经场学习背景演化模式，并通过因果引导机制抑制背景混杂造成的虚假关联，为弱小目标检测提供了新思路。
原文依据 we propose the first Causal-guided Hierarchical Anomaly-aware Learning (CHAL) framework
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论红外小目标检测是目标检测中一个非常特殊的类别，面临着目标成像尺寸小和背景杂波干扰的问题。目前，几乎所有现有方法都以目标为中心，直接从背景中学习目标特征。然而，由于目标信号微弱，这些方法往往难以有效捕捉稳定的特征。有时，它们甚至无法区分真实目标和背景混杂因素。为了克服这些问题，我们从相反的角度提出了首个因果引导的分层异常感知学习（CHAL）框架。该框架突破了以目标为中心的范式，专注于背景学习，同时将目标视为背景中的异常。具体而言，为了实现这一目标，设计了一个时空神经场，从生成的角度对背景演化模式进行建模。同时，提出了一种分层异常感知学习来分解异常发现过程。此外，为了阻断背景混杂因素常常导致的虚假关联，并增强真实目标的因果性，设计了一种因果引导机制。在三个红外数据集上的实验验证了CHAL的有效性和优越性。即使在可见光场景中，它仍然具有明显的适应性。源代码将开源。
英文原文摘要 1334 字符
Infrared small target detection is one highly special category of object detection, faced with tiny target imaging size and cluttered backgrounds. Currently, almost all existing methods are target-centered, directly learning the target features from backgrounds. However, due to weak target signals, they are often difficult in effectively capturing stable features. Sometimes, they cannot even distinguish real targets from background confounders. To overcome these problems, from an opposite perspective, we propose the first Causal-guided Hierarchical Anomaly-aware Learning (CHAL) framework. Breaking through target-centered paradigm, it focuses on background learning, while the targets are handled as the anomalies in backgrounds. In detail, to fulfill the goal, a spatio-temporal neural field is designed to model the background evolution patterns from generative perspective. Meanwhile, a hierarchical anomaly-aware learning is proposed to decompose anomaly discovery. Furthermore, to block the spurious correlations often caused by background confounders, and enhance true target causality, a causal-guiding mechanism is designed. The experiments on three infrared datasets verify the effectiveness and superiority of our CHAL. Even in visible-light scenarios, it still possesses obvious adaptivity. Source code will be open.