Browsing by Subject "Attention learning"

Now showing 1 - 2 of 2

Open Access
AttentionBoost: learning what to attend for gland segmentation in histopathological images by boosting fully convolutional networks
(IEEE, 2020) Güneşli, Gözde Nur; Sökmensüer, C.; Gündüz-Demir, Çiğdem
Fully convolutional networks (FCNs) are widely used for instance segmentation. One important challenge is to sufficiently train these networks to yield good generalizations for hard-to-learn pixels, correct prediction of which may greatly affect the success. A typical group of such hard-to-learn pixels are boundaries between instances. Many studies have developed strategies to pay more attention to learning these 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 an adaptable solution to learn different groups of hard-to-learn pixels, this article proposes AttentionBoost, which is a new multi-attention learning model based on adaptive boosting, for the task of gland instance segmentation in histopathological images. AttentionBoost designs a multi-stage network and introduces a new loss adjustment mechanism for an FCN to adaptively learn what to attend at each stage directly on image data without necessitating any prior definition. 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. Working on histopathological images of colon tissues, our experiments demonstrate that the proposed AttentionBoost model improves the results of gland segmentation compared to its counterparts.
Unknown
Boosting fully convolutional networks for gland instance segmentation in histopathological images
(2019-08) Güneşli, Gözde Nur
In the current literature, fully convolutional neural networks (FCNs) are the most preferred architectures for dense prediction tasks, including gland segmentation. However, a signi cant challenge is to adequately train these networks to correctly predict pixels that are hard-to-learn. Without additional strategies developed for this purpose, networks tend to learn poor generalizations of the dataset since the loss functions of the networks during training may be dominated by the most common and easy-to-learn pixels in the dataset. A typical example of this is the border separation problem in the gland instance segmentation task. Glands can be very close to each other, and since the border regions contain relatively few pixels, it is more di cult to learn these regions and separate gland instances. As this separation is essential for the gland instance segmentation task, this situation arises major drawbacks on the results. To address this border separation problem, it has been proposed to increase the given attention to border pixels during network training either by increasing the relative loss contribution of these pixels or by adding border detection as an additional task to the architecture. Although these techniques may help better separate gland borders, there may exist other types of hard-to-learn pixels (and thus, other mistake types), mostly related to noise and artifacts in the images. Yet, explicitly adjusting the appropriate attention to train the networks against every type of mistake is not feasible. Motivated by this, as a more e ective solution, this thesis proposes an iterative attention learning model based on adaptive boosting. The proposed AttentionBoost model is a multi-stage dense segmentation network trained directly on image data without making any prior assumption. During the end-to-end training of this network, each stage adjusts the importance of each pixel-wise prediction for each image depending on the errors of the previous stages. This way, each stage learns the task with di erent attention forcing the stage to learn the mistakes of the earlier stages. With experiments on the gland instance segmentation task, we demonstrate that our model achieves better segmentation results than the approaches in the literature.