High-Resolution Iterative Feedback Network for Camouflaged Object Detection

Hu, Xiaobin; Wang, Shuo; Qin, Xuebin; Dai, Honghua; Ren, Wenqi; Luo, Donghao; Tai, Ying; Shao, Ling

doi:10.1609/aaai.v37i1.25167

Cited by 20 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With feedback connections, high-level features are rerouted to the low layer to refine low-level feature representations. The feedback mechanism has been widely employed in various 2D image vision tasks, some works [28][29][30] use feedback mechanism in image super-resolution, Sam 31 and Feng 32 use it to enrich network features, and Chen 33 use it in image deraining problems. In the 3D field, Su 34 and Yan 35 use it to complete the point cloud.…”

Section: Feedback Mechanismmentioning

confidence: 99%

CPDC-MFNet: conditional point diffusion completion network with Muti-scale Feedback Refine for 3D Terracotta Warriors

Xu,

Song,

Geng

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Due to the antiquity and difficulty of excavation, the Terracotta Warriors have suffered varying degrees of damage. To restore the cultural relics to their original appearance, utilizing point clouds to repair damaged Terracotta Warriors has always been a hot topic in cultural relic protection. The output results of existing methods in point cloud completion often lack diversity. Probability-based models represented by Denoising Diffusion Probabilistic Models have recently achieved great success in the field of images and point clouds and can output a variety of results. However, one drawback of diffusion models is that too many samples result in slow generation speed. Toward this issue, we propose a new neural network for Terracotta Warriors fragments completion. During the reverse diffusion stage, we initially decrease the number of sampling steps to generate a coarse result. This preliminary outcome undergoes further refinement through a multi-scale refine network. Additionally, we introduce a novel approach called Partition Attention Sampling to enhance the representation capabilities of features. The effectiveness of the proposed model is validated in the experiments on the real Terracotta Warriors dataset and public dataset. The experimental results conclusively demonstrate that our model exhibits competitive performance in comparison to other existing models.

show abstract

Section: Feedback Mechanismmentioning

confidence: 99%

CPDC-MFNet: conditional point diffusion completion network with Muti-scale Feedback Refine for 3D Terracotta Warriors

Xu,

Song,

Geng

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Concretely, early methods are designed based on hard-crafted features (e.g, 3D convexity [34], motion boundary [20], and intensity features [35]). However, as highlighted in [36], these traditional algorithms are less robust and are prone to generate erroneous results in complex scenarios. Recently, owing to the availability of large-scale COD dataset [1], [21], an increasing number of deep-learning-based COD models have emerged.…”

Section: Related Work a Camouflaged Object Detectionmentioning

confidence: 99%

Detecting Camouflaged Objects via Multi-Stage Coarse-to-Fine Refinement

Wang,

Chen,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Camouflaged objects are typically assimilated into their surroundings. Consequently, in contrast to generic object detection/segmentation, camouflaged object detection proves to be considerably more intricate due to the indistinct boundaries and heightened intrinsic similarities between foreground targets and the surrounding environment. Despite the proposition of numerous algorithms that have demonstrated commendable performance across various scenarios, these approaches may still grapple with blurred boundaries, leading to the inadvertent omission of camouflaged targets in challenging scenes. In this paper, we introduce a multi-stage framework tailored for segmenting camouflaged objects through a process of coarse-to-fine refinement. Specifically, our network encompasses three distinct decoders, each fulfilling a unique role in the model. In the initial decoder, we introduce the Bi-directional Locating Module to excavate foreground and background cues, enhancing target localization. The second decoder focuses on leveraging boundary information to augment overall performance, incorporating the Multi-level Feature Fusion Module to generate prediction maps with finer boundaries. Subsequently, the third decoder introduces the Maskguided Fusion Module, designed to process high-resolution features under the guidance of the second decoder's results. This approach enables the preservation of structural details and the generation of finegrained prediction maps. Through the integration of the three decoders, our model effectively identifies and segments camouflaged targets. Extensive experiments are conducted on three commonly used benchmark datasets. The results of these experiments demonstrate that, even without the application of pre-processing or post-processing techniques, our model outperforms 14 state-of-the-art algorithms. INDEX TERMSCamouflaged object detection, coarse-to-fine refinement, convolutional neural network, multi-stage detection. Recently, with the rapid development of Convolutional Neural Networks (CNNs), researchers have endeavored to construct CNN-based models to address the COD problem. Diverging from early traditional hard-crafted methods, CNN-based approaches can simultaneously exploit low-level

show abstract

“…SegMaR [23] proposed an iterative refinement framework to segment camouflaged targets at multi-resolution. HitNet [24] used high-resolution-based features to iteratively refine the low-resolution-based ones. DGNet [25] used imagebased gradients to support the refinement of texture-based features.…”

Section: Related Workmentioning

confidence: 99%