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

TL;DR

An adversarial training framework is proposed, Camouflageator, which introduces an auxiliary generator to generate more camouflaged objects that are harder for a COD method to detect and ICEG, which brings state-of-the-art COD performance.

Abstract

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.

Figures (6)

• Figure 1: Results of FEDER He2023Camouflaged, ICEG, and ICEG+. ICEG+ indicates to optimize ICEG under the Camouflageator framework. Both ICEG and ICEG+ generate more complete results with clearer edges. ICEG+ also exhibits better localization capacity.
• Figure 2: Architecture of Camouflageator. In Phase I, we fix detector $D_s$ and update generator $G_c$ to synthesize more camouflaged objects to deceive $D_s$. In Phase II, we fix $G_c$ and train the detector $D_s$ to segment the synthesized image.
• Figure 3: Framework of our ICEG. CRB is the Conv-ReLU-BN structure. We omit the Sigmoid operator in (b) for clarity.
• Figure 4: Details of IFA and CFA.
• Figure 5: Qualitative analysis of ICEG and other four cutting-edge methods. ICEG generates more complete results with clearer edges. We also provide the results of ICEG+, which is optimized under Camouflageator.