Many interesting tasks in machine learning and computer vision are learned by optimising an objective function defined as a weighted linear combination of multiple losses. The final performance is sensitive to choosing the correct (relative) weights for these losses. Finding a good set of weights is often done by adopting them into the set of hyper-parameters, which are set using an extensive grid search. This is computationally expensive. In this paper, the weights are defined based on properties observed while training the model, including the specific batch loss, the average loss, and the variance for each of the losses. An additional advantage is that the defined weights evolve during training, instead of using static loss weights. In literature, loss weighting is mostly used in a multi-task learning setting, where the different tasks obtain different weights. However, there is a plethora of single-task multi-loss problems that can benefit from automatic loss weighting. In this paper, it is shown that these multi-task approaches do not work on single tasks. Instead, a method is proposed that automatically and dynamically tunes loss weights throughout training specifically for single-task multi-loss problems. The method incorporates a measure of uncertainty to balance the losses. The validity of the approach is shown empirically for different tasks on multiple datasets.

In this paper we address the benefit of adding adversarial training to the task of monocular depth estimation. A model can be trained in a self-supervised setting on stereo pairs of images, where depth (disparities) are an intermediate result in a right-to-left image reconstruction pipeline. For the quality of the image reconstruction and disparity prediction, a combination of different losses is used, including L1 image reconstruction losses and left-right disparity smoothness. These are local pixel-wise losses, while depth prediction requires global consistency. Therefore, we extend the self-supervised network to become a Generative Adversarial Network (GAN), by including a discriminator which should tell apart reconstructed (fake) images from real images. We evaluate Vanilla GANs, LSGANs and Wasserstein GANs in combination with different pixel-wise reconstruction losses. Based on extensive experimental evaluation, we conclude that adversarial training is beneficial if and only if the reconstruction loss is not too constrained. Even though adversarial training seems promising because it promotes global consistency, non-adversarial training outperforms (or is on par with) any method trained with a GAN when a constrained reconstruction loss is used in combination with batch normalisation. Based on the insights of our experimental evaluation we obtain state-of-the art monocular depth estimation results by using batch normalisation and different output scales.

<p>This paper provides a definition of back-propagation through geometric correspondences for morphological neural networks. In addition, dilation layers are shown to learn probe geometry by erosion of layer inputs and outputs. A proof-of-principle is provided, in which predictions and convergence of morphological networks significantly outperform convolutional networks.</p>

No abstract

Abstract. This research is the first to apply MeshCNN – a deep learning model that is specifically designed for 3D triangular meshes – in the photogrammetry domain. We highlight the challenges that arise when applying a mesh-based deep learning model to a photogrammetric mesh, especially w.r.t. data set properties. We provide solutions on how to prepare a remotely sensed mesh for a machine learning task. The most notable pre-processing step proposed is a novel application of the Breadth-First Search algorithm for chunking a large mesh into computable pieces. Furthermore, this work extends MeshCNN such that photometric features based on the mesh texture are considered in addition to the geometric information. Experiments show that including color information improves the predictive performance of the model by a large margin. Besides, experimental results indicate that segmentation performance could be advanced substantially with the introduction of a high-quality benchmark for semantic segmentation on meshes.