	US 12,136,261 B2
	Counterfactual context-aware texture learning for camouflaged object detection
Shuohao Li, Hunan (CN); Xiaofei Li, Hunan (CN); Jun Zhang, Hunan (CN); Kuihua Huang, Hunan (CN); Chao Chen, Hunan (CN); Boliang Sun, Hunan (CN); Jun Lei, Hunan (CN); and Miaomiao Yu, Hunan (CN)
Assigned to National University of Defense Technology, Changsha (CN)
Filed by National University of Defense Technology, Hunan (CN)
Filed on Apr. 24, 2024, as Appl. No. 18/644,727.
Application 18/644,727 is a continuation of application No. PCT/CN2023/081035, filed on Mar. 13, 2023.
Prior Publication US 2024/0312194 A1, Sep. 19, 2024
Int. Cl. G06V 10/80 (2022.01); G06V 10/54 (2022.01); G06V 10/70 (2022.01); G06V 10/77 (2022.01)

CPC G06V 10/806 (2022.01) [G06V 10/54 (2022.01); G06V 10/768 (2022.01); G06V 10/7715 (2022.01)]

12 Claims

1. A counterfactual context-aware texture learning network system, comprising:

a camera configured to capture an input image;

a processor configured to perform camouflaged object detection on the input image; and

a memory configured to store a texture-aware refinement module (TRM), a context-aware fused module (CFM), and a counterfactual intervention module (CIM);

wherein the processor is configured to execute program instructions of the TRM, the CFM, and the CIM;

the TRM is configured to extract dimension features from the input image;

the CFM is configured to infuse multi-scale contextual features;

the CIM is configured to identify a camouflaged object with counterfactual intervention via the processor;

the TRM comprises:

a receptive field block (RFB) configured to expand a receptive field and extract texture features; and

a position attention module (PAM) and a channel attention module (CAM) configured to further refine texture-aware features and obtain discriminant feature representation;

the RFB comprises five branches b_k, (k=1,2,3,4,5), each branch of the five branches comprising a 1×1 convolution operation to reduce a channel size to 64;

each branch where k>2 further comprises a 1×(2i−1) convolutional layer, a (2i−1)×1 convolutional layer, and a (2i−1)×(2i−1) convolutional layer, with a dilation rate of (2i−1), where i=k−1;

each branch where k>1 is concatenated, input into a second 1×1 convolution operation, and added with a branch of the five branches where k=1;

a result of the RFB is input into a Rectified Linear Unit (ReLU) activation function to obtain an output feature f_i′∈ custom character

^C×H×W, where C, H and W represent a channel number, a channel height, and a channel width, respectively;

the output feature f′ is input into the PAM and the CAM,

the PAM is configured to:

obtain three feature maps B, C, and D through three convolution layers, where {B, C, and D}∈ custom character

^C×H×W, and the three feature maps are reshaped to custom character

^C×N; and

multiply the transpose of B by C, and perform a softmax layer to calculate the spatial attention map sa∈ custom character

^N×N:

where sa_ijdenotes the j^thposition's impact on the i^thposition;

a loss function L=L_BCE^W+L_IoU^Wis used to train the counterfactual context-aware texture learning network system to learn effective textures, where L_BCE^Wis the weighted binary cross entropy (BCE) loss which restricts each pixel, and Lou is a weighted intersection-over-union (IoU) loss that focuses on a global structure; and

a total loss is formulated as:

L_total=L(Y,y)+λL(Y_effect,y) (2)

where y is a ground truth, λ=0:1, L(Y, y) are main clues which learn general texture features, Y is a prediction of the main clues, and λL(Y_effect, y) is a counterfactual term that penalizes a wrong prediction affected by contextual biases;

thereby performing the camouflaged object detection in the input image with enhanced accuracy.