CONTA: Causal Intervention for Weakly-Supervised Semantic Segmentation

As the part of theory is hard to understand, I will start from method part and complete theory part in the future

method

CONTA: Causal Intervention for Weakly-Supervised Semantic Segmentation
The most difficult part is the meaning of C: confounder set. The c i c_i ci​ is the average of all X M X_M XM​ which is the processed CAMs. I am not confident to this.

CONTA: Causal Intervention for Weakly-Supervised Semantic Segmentation
The α \alpha α is a measurement of similarity, whereby get the weight of each class-specific entry c. The W 1 W_1 W1​ and W 2 W_2 W2​ is two learnable matrix.

Another question is how M take part in the calculate of network.
CONTA: Causal Intervention for Weakly-Supervised Semantic Segmentation

where s i = f ( X , M t , θ t i ) s_i=f(X, M_t, \theta^i_t) si​=f(X,Mt​,θti​), f consist of a shared convolutional network and a class-specific fully-connected network. The input of the first part is concat(X, M t M_t Mt​) on channel-wise.

上一篇:FCN的学习及理解(Fully Convolutional Networks for Semantic Segmentation)


下一篇:Fully-Automated Segmentation of Nasopharyngeal Carcinoma on Dual-Sequence MRI Using Convol