Detecting Camouflaged Object in Frequency Domain

Zhong, Yijie; Li, Bo; Tang, Liming; Kuang, Senyun; Wu, Shuang; Ding, Shouhong

doi:10.1109/cvpr52688.2022.00446

Cited by 87 publications

(19 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Frequency methods have also yielded promising results in domain adaption and image translation, mainly by taking advantage of domain-invariant spectrum components [3,18,[55][56][57]. Previous research also shows that particular features and details can be better extracted in the frequency domain, leading to improvements in camouflaged object detection [60], face forgery detection [21,28], and face editing [9]. Frequency-based networks have also made notable strides in CT reconstruction.…”

Section: Frequency Methods In Deep Learningmentioning

confidence: 99%

Transfer Learning in Motor Imagery Brain Computer Interface: A Review

2022

J. Shanghai Jiaotong Univ. (Sci.)

View full text Add to dashboard Cite

Sparse-view computed tomography (CT)-using a small number of projections for tomographic reconstructionenables much lower radiation dose to patients and accelerated data acquisition. The reconstructed images, however, suffer from strong artifacts, greatly limiting their diagnostic value. Current trends for sparse-view CT turn to the raw data for better information recovery. The resultant dual-domain methods, nonetheless, suffer from secondary artifacts, especially in ultra-sparse view scenarios, and their generalization to other scanners/protocols is greatly limited. A crucial question arises: have the image post-processing methods reached the limit? Our answer is not yet. In this paper, we stick to image post-processing methods due to great flexibility and propose global representation(GloRe) distillation framework for sparse-view CT, termed GloReDi. First, we propose to learn GloRe with Fourier convolution, so each element in GloRe has an image-wide receptive field. Second, unlike methods that only use the full-view images for supervision, we propose to distill GloRe from intermediate-view reconstructed images that are readily available but not explored in previous literature. The success of GloRe distillation is attributed to two key components: representation directional distillation to align the GloRe directions, and band-pass-specific contrastive distillation to gain clinically important details. Extensive experiments demonstrate the superiority of the proposed GloReDi over the state-of-the-art methods, including dual-domain ones. The source code is available at https: //github.com/longzilicart/GloReDi.

show abstract

Section: Frequency Methods In Deep Learningmentioning

confidence: 99%

Transfer Learning in Motor Imagery Brain Computer Interface: A Review

2022

J. Shanghai Jiaotong Univ. (Sci.)

View full text Add to dashboard Cite

show abstract

“…In image space, spatial domain processing refers to the direct processing of the pixel values, with length as the independent variable. In recent years, many image-based methods for saliency object detection have been proposed [ 10 , 11 , 12 ]. The early SOD algorithm [ 13 ] works mainly based on the handcrafted saliency map for feature prediction.…”

Section: Related Workmentioning

confidence: 99%

FESNet: Frequency-Enhanced Saliency Detection Network for Grain Pest Segmentation

Zhai

Liu

et al. 2023

Insects

View full text Add to dashboard Cite

As insect infestation is the leading factor accounting for nutritive and economic losses in stored grains, it is important to detect the presence and number of insects for the sake of taking proper control measures. Inspired by the human visual attention mechanism, we propose a U-net-like frequency-enhanced saliency (FESNet) detection model, resulting in the pixelwise segmentation of grain pests. The frequency clues, as well as the spatial information, are leveraged to enhance the detection performance of small insects from the cluttered grain background. Firstly, we collect a dedicated dataset, GrainPest, with pixel-level annotation after analyzing the image attributes of the existing salient object detection datasets. Secondly, we design a FESNet with the discrete wavelet transformation (DWT) and the discrete cosine transformation (DCT), both involved in the traditional convolution layers. As current salient object detection models will reduce the spatial information with pooling operations in the sequence of encoding stages, a special branch of the discrete wavelet transformation (DWT) is connected to the higher stages to capture accurate spatial information for saliency detection. Then, we introduce the discrete cosine transform (DCT) into the backbone bottlenecks to enhance the channel attention with low-frequency information. Moreover, we also propose a new receptive field block (NRFB) to enlarge the receptive fields by aggregating three atrous convolution features. Finally, in the phase of decoding, we use the high-frequency information and aggregated features together to restore the saliency map. Extensive experiments and ablation studies on our dataset, GrainPest, and open dataset, Salient Objects in Clutter (SOC), demonstrate that the proposed model performs favorably against the state-of-the-art model.

show abstract

“…Recently, CNN-based approaches have made impressive progress on the COD task by releasing large-scale datasets. Some works attempt to mine inconspicuous features of camouflage objects from the background through meticulously designed feature exploration modules, e.g., contextual feature learning [28,36], texture-aware learning [60], and frequency-domain learning [57]. There are also some models [19,21,47] which propose to model uncertainty in data labeling or camouflaged data itself for COD.…”

Section: Cnn-based Camouflaged Object Detectionmentioning

confidence: 99%

Horizontal Feature Pyramid Network for Object Detection in UAV Images

Tang

Sun

Wang

2021

2021 China Automation Congress (CAC)

View full text Add to dashboard Cite

Vision transformers have recently shown strong global context modeling capabilities in camouflaged object detection. However, they suffer from two major limitations: less effective locality modeling and insufficient feature aggregation in decoders, which are not conducive to camouflaged object detection that explores subtle cues from indistinguishable backgrounds. To address these issues, in this paper, we propose a novel transformer-based Feature Shrinkage Pyramid Network (FSPNet), which aims to hierarchically decode locality-enhanced neighboring transformer features through progressive shrinking for camouflaged object detection. Specifically, we propose a nonlocal token enhancement module (NL-TEM) that employs the non-local mechanism to interact neighboring tokens and explore graph-based high-order relations within tokens to enhance local representations of transformers. Moreover, we design a feature shrinkage decoder (FSD) with adjacent interaction modules (AIM), which progressively aggregates adjacent transformer features through a layer-bylayer shrinkage pyramid to accumulate imperceptible but effective cues as much as possible for object information decoding. Extensive quantitative and qualitative experiments demonstrate that the proposed model significantly outperforms the existing 24 competitors on three challenging COD benchmark datasets under six widely-used evaluation metrics. Our code is publicly available at https: //github.com/ZhouHuang23/FSPNet.

show abstract

Detecting Camouflaged Object in Frequency Domain

Cited by 87 publications

References 55 publications

Transfer Learning in Motor Imagery Brain Computer Interface: A Review

Transfer Learning in Motor Imagery Brain Computer Interface: A Review

FESNet: Frequency-Enhanced Saliency Detection Network for Grain Pest Segmentation

Horizontal Feature Pyramid Network for Object Detection in UAV Images

Contact Info

Product

Resources

About