Cenk Sökmensüer

C. T. Sari, C. Sokmensuer, C. Gunduz-Demir

This paper presents a new regularization method to train a fully convolutional network for semantic tissue segmentation in histopathological images. This method relies on the benefit of unsupervised learning, in the form of image reconstruction, for network training. To this end, it puts forward an idea of defining a new embedding that allows uniting the main supervised task of semantic segmentation and an auxiliary unsupervised task of image reconstruction into a single one and proposes to learn this united task by a single generative model. This embedding generates an output image by superimposing an input image on its segmentation map. Then, the method learns to translate the input image to this embedded output image using a conditional generative adversarial network, which is known as quite effective for image-to-image translations. This proposal is different than the existing approach that uses image reconstruction for the same regularization purpose. The existing approach considers segmentation and image reconstruction as two separate tasks in a multi-task network, defines their losses independently, and combines them in a joint loss function. However, the definition of such a function requires externally determining right contributions of the supervised and unsupervised losses that yield balanced learning between the segmentation and image reconstruction tasks. The proposed approach provides an easier solution to this problem by uniting these two tasks into a single one, which intrinsically combines their losses. We test our approach on three datasets of histopathological images. Our experiments demonstrate that it leads to better segmentation results in these datasets, compared to its counterparts.

Gozde Nur Gunesli, Cenk Sokmensuer, Cigdem Gunduz-Demir

Dense prediction models are widely used for image segmentation. One important challenge is to sufficiently train these models to yield good generalizations for hard-to-learn pixels. A typical group of such hard-to-learn pixels are boundaries between instances. Many studies have proposed to give specific attention to learning the boundary pixels. They include designing multi-task networks with an additional task of boundary prediction and increasing the weights of boundary pixels' predictions in the loss function. Such strategies require defining what to attend beforehand and incorporating this defined attention to the learning model. However, there may exist other groups of hard-to-learn pixels and manually defining and incorporating the appropriate attention for each group may not be feasible. In order to provide a more attainable and scalable solution, this paper proposes AttentionBoost, which is a new multi-attention learning model based on adaptive boosting. AttentionBoost designs a multi-stage network and introduces a new loss adjustment mechanism for a dense prediction model to adaptively learn what to attend at each stage directly on image data without necessitating any prior definition about what to attend. This mechanism modulates the attention of each stage to correct the mistakes of previous stages, by adjusting the loss weight of each pixel prediction separately with respect to how accurate the previous stages are on this pixel. This mechanism enables AttentionBoost to learn different attentions for different pixels at the same stage, according to difficulty of learning these pixels, as well as multiple attentions for the same pixel at different stages, according to confidence of these stages on their predictions for this pixel. Using gland segmentation as a showcase application, our experiments demonstrate that AttentionBoost improves the results of its counterparts.