This paper reviews the first AIM challenge on mapping camera RAW to RGB images with the focus on proposed solutions and results. The participating teams were solving a real-world photo enhancement problem, where the goal was to map the original low-quality RAW images from the Huawei P20 device to the same photos captured with the Canon 5D DSLR camera. The considered problem embraced a number of computer vision subtasks, such as image demosaicing, denoising, gamma correction, image resolution and sharpness enhancement, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions' perceptual results measured in a user study. The proposed solutions significantly improved baseline results, defining the state-of-the-art for RAW to RGB image restoration.

Conventional Neural Network (NN) control for robots uses radial basis function (RBF) and for n-link robot with online control, the number of nodes and weighting matrix increases exponentially, which requires a number of calculations to be performed within a very short duration of time. This consumes a large amount of computational memory and may subsequently result in system failure. To avoid this problem, this paper proposes an innovative NN robot control using a dimension compressed RBF (DCRBF) for a class of n-degree of freedom (DOF) robot with full-state constraints. The proposed DCRBF NN control scheme can compress the nodes and weighting matrix greatly and provide an output that meets the prescribed tracking performance. Additionally, adaption laws are designed to compensate for the internal and external uncertainties. Finally, the effectiveness of the proposed method has been verified by simulations. The results indicate that the proposed method, integral Barrier Lyapunov Functions (iBLF), avoids the existing defects of Barrier Lyapunov Functions (BLF) and prevents the constraint violations.

Deep reinforcement learning (DRL) has been utilized in numerous computer vision tasks, such as object detection, autonomous driving, etc. However, relatively few DRL methods have been proposed in the area of image segmentation, particularly in left ventricle segmentation. Reinforcement learning-based methods in earlier works often rely on learning proper thresholds to perform segmentation, and the segmentation results are inaccurate due to the sensitivity of the threshold. To tackle this problem, a novel DRL agent is designed to imitate the human process to perform LV segmentation. For this purpose, we formulate the segmentation problem as a Markov decision process and innovatively optimize it through DRL. The proposed DRL agent consists of two neural networks, i.e., First-P-Net and Next-P-Net. The First-P-Net locates the initial edge point, and the Next-P-Net locates the remaining edge points successively and ultimately obtains a closed segmentation result. The experimental results show that the proposed model has outperformed the previous reinforcement learning methods and achieved comparable performances compared with deep learning baselines on two widely used LV endocardium segmentation datasets, namely Automated Cardiac Diagnosis Challenge (ACDC) 2017 dataset, and Sunnybrook 2009 dataset. Moreover, the proposed model achieves higher F-measure accuracy compared with deep learning methods when training with a very limited number of samples.

In recent years, the angle-based softmax losses have significantly improved the performance of face recognition whereas these loss functions are all based on cosine logit. A potential weakness is that the nonlinearity of the cosine function may undesirably saturate the angular optimization between the features and the corresponding weight vectors, thereby preventing the network from fully learning to maximize the angular discriminability of features. As a result, the generalization of learned features may be compromised. To tackle this issue, we propose a Linear-Cosine Softmax Loss (LinCos-Softmax) to more effectively learn angle-discriminative facial features. The main characteristic of the loss function we propose is the use of an approximated linear logit. Compared with the conventional cosine logit, it has a stronger linear relationship with the angle on enhancing angular discrimination through Taylor expansion. We also propose an automatic scale parameter selection scheme, which can conveniently provide an appropriate scale for different logits without the need for exhaustive parameter search to improve performance. In addition, we propose a marginenhanced Linear-Cosine Softmax Loss (m-LinCos-Softmax) to further enlarge inter-class distances and reduce intra-class variations. Experimental results on several face recognition benchmarks (LFW, AgeDB- 30, CFP-FP, MegaFace Challenge 1) demonstrate the effectiveness of the proposed method and its superiority to existing angular softmax loss variants.