Dense prediction tasks such as depth perception and semantic segmentation are important applications in computer vision that have a concrete topological description in terms of partitioning an image into connected components or estimating a function with a small number of local extrema corresponding to objects in the image. We develop a form of topological regularization based on persistent homology that can be used in dense prediction tasks with these topological descriptions. Experimental results show that the output topology can also appear in the internal activations of trained neural networks which allows for a novel use of topological regularization to the internal states of neural networks during training, reducing the computational cost of the regularization. We demonstrate that this topological regularization of internal activations leads to improved convergence and test benchmarks on several problems and architectures.
翻译:深度感知和语义分解等密集的预测任务,是计算机视觉中的重要应用,在将图像分割成相连接的组件或估计与图像中物体相对应的少量局部外形函数方面,具有具体的地形学描述,或具有与图像中物体相对应的微小局部外形函数; 我们开发了一种基于持久性同质学的形态学正规化形式,可用这些地形学描述来进行密集的预测任务; 实验结果显示,产出表层学也可以出现在经过训练的神经网络的内部激活中,从而可以在培训期间对神经网络的内部状态进行新的利用,从而降低神经网络的计算成本; 我们证明,这种对内部活化的形态学正规化能够改善对若干问题和结构的趋同性和测试基准。