Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. Because of this, there is growing interest in automated neural architecture search methods. We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy.

Neural Architecture Search: A Survey

Monocular depth prediction plays a crucial role in understanding 3D scene geometry. Although recent methods have achieved impressive progress in evaluation metrics such as the pixel-wise relative error, most methods neglect the geometric constraints in the 3D space. In this work, we show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces one simple type of geometric constraints, namely, virtual normal directions determined by randomly sampled three points in the reconstructed 3D space, we can considerably improve the depth prediction accuracy. Furthermore, we can not only predict accurate depth but also achieve high-quality other 3D information from the depth without retraining new parameters, Significantly, the byproduct of this predicted depth being sufficiently accurate is that we are now able to recover good 3D structures of the scene such as the point cloud and surface normal directly from the depth, eliminating the necessity of training new sub-models as was previously done. Experiments on two challenging benchmarks: NYU Depth-V2 and KITTI demonstrate the effectiveness of our method and state-of-the-art performance.

/pdf/enforcing-geometric-constraints-of-virtual-normal-for-depth-dskrdmury1.pdf

Enforcing Geometric Constraints of Virtual Normal for Depth Prediction

As designing appropriate Convolutional Neural Network (CNN) architecture in the context of a given application usually involves heavy human works or numerous GPU hours, the research community is soliciting the architecture-neutral CNN structures, which can be easily plugged into multiple mature architectures to improve the performance on our real-world applications. We propose Asymmetric Convolution Block (ACB), an architecture-neutral structure as a CNN building block, which uses 1D asymmetric convolutions to strengthen the square convolution kernels. For an off-the-shelf architecture, we replace the standard square-kernel convolutional layers with ACBs to construct an Asymmetric Convolutional Network (ACNet), which can be trained to reach a higher level of accuracy. After training, we equivalently convert the ACNet into the same original architecture, thus requiring no extra computations anymore. We have observed that ACNet can improve the performance of various models on CIFAR and ImageNet by a clear margin. Through further experiments, we attribute the effectiveness of ACB to its capability of enhancing the model's robustness to rotational distortions and strengthening the central skeleton parts of square convolution kernels.

/pdf/acnet-strengthening-the-kernel-skeletons-for-powerful-cnn-3cd36jyfg3.pdf

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

We address the problem of estimating a high quality dense depth map from a single RGB input image. We start out with a baseline encoder-decoder convolutional neural network architecture and pose the question of how the global processing of information can help improve overall depth estimation. To this end, we propose a transformer-based architecture block that divides the depth range into bins whose center value is estimated adaptively per image. The final depth values are estimated as linear combinations of the bin centers. We call our new building block AdaBins. Our results show a decisive improvement over the state-of-the-art on several popular depth datasets across all metrics. We also validate the effectiveness of the proposed block with an ablation study and provide the code and corresponding pre-trained weights of the new state-of-the-art model.

AdaBins: Depth Estimation using Adaptive Bins

Advancements in the field of autonomous underwater vehicle

This paper considers the problem of single image depth estimation. The employment of convolutional neural networks (CNNs) has recently brought about significant advancements in the research of this problem. However, most existing methods suffer from loss of spatial resolution in the estimated depth maps; a typical symptom is distorted and blurry reconstruction of object boundaries. In this paper, toward more accurate estimation with a focus on depth maps with higher spatial resolution, we propose two improvements to existing approaches. One is about the strategy of fusing features extracted at different scales, for which we propose an improved network architecture consisting of four modules: an encoder, decoder, multi-scale feature fusion module, and refinement module. The other is about loss functions for measuring inference errors used in training. We show that three loss terms, which measure errors in depth, gradients and surface normals, respectively, contribute to improvement of accuracy in an complementary fashion. Experimental results show that these two improvements enable to attain higher accuracy than the current state-of-the-arts, which is given by finer resolution reconstruction, for example, with small objects and object boundaries.

Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries

Researchers have applied deep neural networks to image restoration tasks, in which they proposed various network architectures, loss functions, and training methods. In particular, adversarial training, which is employed in recent studies, seems to be a key ingredient to success. In this paper, we show that simple convolutional autoencoders (CAEs) built upon only standard network components, i.e., convolutional layers and skip connections, can outperform the state-of-the-art methods which employ adversarial training and sophisticated loss functions. The secret is to employ an evolutionary algorithm to automatically search for good architectures. Training optimized CAEs by minimizing the $\ell_2$ loss between reconstructed images and their ground truths using the ADAM optimizer is all we need. Our experimental results show that this approach achieves 27.8 dB peak signal to noise ratio (PSNR) on the CelebA dataset and 40.4 dB on the SVHN dataset, compared to 22.8 dB and 33.0 dB provided by the former state-of-the-art methods, respectively.

/pdf/exploiting-the-potential-of-standard-convolutional-gqux4p2lk0.pdf

Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search

Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search

The potential of using autonomous underwater vehicles (AUVs) for underwater exploration is confined by its limited on-board battery energy and data storage capacity. This problem has been addressed using docking systems by underwater recharging and data transfer for AUVs. In this paper, we propose a vision-based framework by addressing the detection and pose estimation problems for short-range underwater docking using these systems. For robust and credible detection of docking stations, we propose a convolutional neural network called docking neural network (DoNN). For accurate pose estimation, a perspective-n-point algorithm is integrated into our framework. In order to examine our framework in underwater docking tasks, we collected a dataset of 2D images, named underwater docking images dataset (UDID), which is the first publicly available underwater docking dataset to the best of our knowledge. In the field experiments, we first evaluate the performance of DoNN on the UDID and its deformed variations. Next, we examine the pose estimation module by ground and underwater experiments. At last, we integrate our proposed vision-based framework with an ultra-short baseline acoustic sensor, to demonstrate the efficiency and accuracy of our framework by performing experiments in a lake. The experimental results show that the proposed framework is able to detect docking stations and estimate their relative pose more efficiently and successfully, compared with the state-of-the-art baseline systems.

Detection and Pose Estimation for Short-range Vision-Based Underwater Docking

This paper considers the problem of material recognition. Motivated by observation of close interconnections between material and object recognition, we study how to select and integrate multiple features obtained by different models of Convolutional Neural Networks (CNNs) trained in a transfer learning setting. To be specific, we first compute activations of features using representations on images to select a set of samples which are best represented by the features. Then, we measure uncertainty of the features by computing entropy of class distributions for each sample set. Finally, we compute contribution of each feature to representation of classes for feature selection and integration. Experimental results show that the proposed method achieves state-of-the-art performance on two benchmark datasets for material recognition. Additionally, we introduce a new material dataset, named EFMD, which extends Flickr Material Database (FMD). By the employment of the EFMD for transfer learning, we achieve 84.0% ± 1.8% accuracy on the FMD dataset, which is close to the reported human performance 84.9%.

Mete Ozay

Papers

Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries

Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search

Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search

Detection and Pose Estimation for Short-range Vision-Based Underwater Docking

Integrating deep features for material recognition