Not all camouflages are equally effective, as even a partially visible
contour or a slight color difference can make the animal stand out and break
its camouflage. In this paper, we address the question of what makes a
camouflage successful, by proposing three scores for automatically assessing
its effectiveness. In particular, we show that camouflage can be measured by
the similarity between background and foreground features and boundary
visibility. We use these camouflage scores to assess and compare all available
camouflage datasets. We also incorporate the proposed camouflage score into a
generative model as an auxiliary loss and show that effective camouflage images
or videos can be synthesised in a scalable manner. The generated synthetic
dataset is used to train a transformer-based model for segmenting camouflaged
animals in videos. Experimentally, we demonstrate state-of-the-art camouflage
breaking performance on the public MoCA-Mask benchmark.

本文提出了三个评估指标来衡量伪装效果，将伪装分数集成到生成模型中，用于合成有效的伪装图像或视频，进而训练基于转化模型的动物分割模型，在公共 MoCA-Mask 基准测试中展现了最先进的伪装破解表现。

迷彩的制造和破解

The Making and Breaking of Camouflage

Camouflaged object detection (COD) is the challenging task of identifying
camouflaged objects visually blended into surroundings. Albeit achieving
remarkable success, existing COD detectors still struggle to obtain precise
results in some challenging cases. To handle this problem, we draw inspiration
from the prey-vs-predator game that leads preys to develop better camouflage
and predators to acquire more acute vision systems and develop algorithms from
both the prey side and the predator side. On the prey side, we propose an
adversarial training framework, Camouflageator, which introduces an auxiliary
generator to generate more camouflaged objects that are harder for a COD method
to detect. Camouflageator trains the generator and detector in an adversarial
way such that the enhanced auxiliary generator helps produce a stronger
detector. On the predator side, we introduce a novel COD method, called
Internal Coherence and Edge Guidance (ICEG), which introduces a camouflaged
feature coherence module to excavate the internal coherence of camouflaged
objects, striving to obtain more complete segmentation results. Additionally,
ICEG proposes a novel edge-guided separated calibration module to remove false
predictions to avoid obtaining ambiguous boundaries. Extensive experiments show
that ICEG outperforms existing COD detectors and Camouflageator is flexible to
improve various COD detectors, including ICEG, which brings state-of-the-art
COD performance.

Camouflaged object detection faces challenges, and this research proposes an adversarial training framework, Camouflageator, to generate more camouflaged objects and improve the detection. They also introduce ICEG, a novel COD method that utilizes internal coherence and edge guidance for better segmentation results. Experimental results show that ICEG outperforms existing detectors, and Camouflageator is flexible in improving various COD detectors, achieving state-of-the-art COD performance.

策略性猎物使敏锐的捕食者：通过生成伪装对象增强伪装物体检测器

Strategic Preys Make Acute Predators: Enhancing Camouflaged Object  Detectors by Generating Camouflaged Objects

Camouflage in nature seems to arise from competition between predator and
prey. To survive, predators must find prey, and prey must avoid being found.
This work simulates an abstract model of that adversarial relationship. It
looks at crypsis through evolving prey camouflage patterns (as color textures)
in competition with evolving predator vision. During their "lifetime" predators
learn to better locate camouflaged prey. The environment for this 2D simulation
is provided by a set of photographs, typically of natural scenes. This model is
based on two evolving populations, one of prey and another of predators. Mutual
conflict between these populations can produce both effective prey camouflage
and predators skilled at "breaking" camouflage. The result is an open source
artificial life model to help study camouflage in nature, and the perceptual
phenomenon of camouflage more generally.

通过模拟抽象模型，探讨猎物和捕猎者之间的对抗关系，研究猎物伪装和捕猎者视觉进化等现象，从而提出一种开放源代码的人工生命模型。

伪装的共同进化

Coevolution of Camouflage

To perform adversarial attacks in the physical world, many studies have
proposed adversarial camouflage, a method to hide a target object by applying
camouflage patterns on 3D object surfaces. For obtaining optimal physical
adversarial camouflage, previous studies have utilized the so-called neural
renderer, as it supports differentiability. However, existing neural renderers
cannot fully represent various real-world transformations due to a lack of
control of scene parameters compared to the legacy photo-realistic renderers.
In this paper, we propose the Differentiable Transformation Attack (DTA), a
framework for generating a robust physical adversarial pattern on a target
object to camouflage it against object detection models with a wide range of
transformations. It utilizes our novel Differentiable Transformation Network
(DTN), which learns the expected transformation of a rendered object when the
texture is changed while preserving the original properties of the target
object. Using our attack framework, an adversary can gain both the advantages
of the legacy photo-realistic renderers including various physical-world
transformations and the benefit of white-box access by offering
differentiability. Our experiments show that our camouflaged 3D vehicles can
successfully evade state-of-the-art object detection models in the
photo-realistic environment (i.e., CARLA on Unreal Engine). Furthermore, our
demonstration on a scaled Tesla Model 3 proves the applicability and
transferability of our method to the real world.

本文提出了 Differentiable Transformation Attack (DTA) 框架，基于 Differentiable Transformation Network (DTN) 生成具备动态适应性的伪装图案，成功地使 3D 车辆在物理世界和虚拟现实环境中逃避最先进的目标检测模型。

DTA：利用可微变换网络进行物理伪装攻击

DTA: Physical Camouflage Attacks using Differentiable Transformation  Network

Camouflage is a key defence mechanism across species that is critical to
survival. Common strategies for camouflage include background matching,
imitating the color and pattern of the environment, and disruptive coloration,
disguising body outlines [35]. Camouflaged object detection (COD) aims to
segment camouflaged objects hiding in their surroundings. Existing COD models
are built upon binary ground truth to segment the camouflaged objects without
illustrating the level of camouflage. In this paper, we revisit this task and
argue that explicitly modeling the conspicuousness of camouflaged objects
against their particular backgrounds can not only lead to a better
understanding about camouflage and evolution of animals, but also provide
guidance to design more sophisticated camouflage techniques. Furthermore, we
observe that it is some specific parts of the camouflaged objects that make
them detectable by predators. With the above understanding about camouflaged
objects, we present the first ranking based COD network (Rank-Net) to
simultaneously localize, segment and rank camouflaged objects. The localization
model is proposed to find the discriminative regions that make the camouflaged
object obvious. The segmentation model segments the full scope of the
camouflaged objects. And, the ranking model infers the detectability of
different camouflaged objects. Moreover, we contribute a large COD testing set
to evaluate the generalization ability of COD models. Experimental results show
that our model achieves new state-of-the-art, leading to a more interpretable
COD network.

本研究通过建立 Rank-Net 模型，结合 camouflaged object detection 技术和 conspicuousness 的概念，来探讨动物进化中的 Camouflage 技术，并提出一个可以定位、分割和排名 Camouflaged 目标的方法。实验结果表明，该模型取得了新的最先进水平，使 Camouflaged 目标的检测更具可解释性。