A trade-off exists between reconstruction quality and the prior regularisation in the Evidence Lower Bound (ELBO) loss that Variational Autoencoder (VAE) models use for learning. There are few satisfactory approaches to deal with a balance between the prior and reconstruction objective, with most methods dealing with this problem through heuristics. In this paper, we show that the noise variance (often set as a fixed value) in the Gaussian likelihood p(x|z) for real-valued data can naturally act to provide such a balance. By learning this noise variance so as to maximise the ELBO loss, we automatically obtain an optimal trade-off between the reconstruction error and the prior constraint on the posteriors. This variance can be interpreted intuitively as the necessary noise level for the current model to be the best explanation of the observed dataset. Further, by allowing the variance inference to be more flexible it can conveniently be used as an uncertainty estimator for reconstructed or generated samples. We demonstrate that optimising the noise variance is a crucial component of VAE learning, and showcase the performance on MNIST, Fashion MNIST and CelebA datasets. We find our approach can significantly improve the quality of generated samples whilst maintaining a smooth latent-space manifold to represent the data. The method also offers an indication of uncertainty in the final generative model.
Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single image as input. Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. The source code is avaliable at https://github.com/BingCS/AtLoc.
Facial recognition is a key enabling component for emerging Internet of Things (IoT) services such as smart homes or responsive offices. Through the use of deep neural networks, facial recognition has achieved excellent performance. However, this is only possibly when trained with hundreds of images of each user in different viewing and lighting conditions. Clearly, this level of effort in enrolment and labelling is impossible for wide-spread deployment and adoption. Inspired by the fact that most people carry smart wireless devices with them, e.g. smartphones, we propose to use this wireless identifier as a supervisory label. This allows us to curate a dataset of facial images that are unique to a certain domain e.g. a set of people in a particular office. This custom corpus can then be used to finetune existing pre-trained models e.g. FaceNet. However, due to the vagaries of wireless propagation in buildings, the supervisory labels are noisy and weak.We propose a novel technique, AutoTune, which learns and refines the association between a face and wireless identifier over time, by increasing the inter-cluster separation and minimizing the intra-cluster distance. Through extensive experiments with multiple users on two sites, we demonstrate the ability of AutoTune to design an environment-specific, continually evolving facial recognition system with entirely no user effort.
Dynamical models estimate and predict the temporal evolution of physical systems. State Space Models (SSMs) in particular represent the system dynamics with many desirable properties, such as being able to model uncertainty in both the model and measurements, and optimal (in the Bayesian sense) recursive formulations e.g. the Kalman Filter. However, they require significant domain knowledge to derive the parametric form and considerable hand-tuning to correctly set all the parameters. Data driven techniques e.g. Recurrent Neural Networks have emerged as compelling alternatives to SSMs with wide success across a number of challenging tasks, in part due to their ability to extract relevant features from rich inputs. They however lack interpretability and robustness to unseen conditions. In this work, we present DynaNet, a hybrid deep learning and time-varying state-space model which can be trained end-to-end. Our neural Kalman dynamical model allows us to exploit the relative merits of each approach. We demonstrate state-of-the-art estimation and prediction on a number of physically challenging tasks, including visual odometry, sensor fusion for visual-inertial navigation and pendulum control. In addition we show how DynaNet can indicate failures through investigation of properties such as the rate of innovation (Kalman Gain).
This paper presents a novel method to distill knowledge from a deep pose regressor network for efficient Visual Odometry (VO). Standard distillation relies on "dark knowledge" for successful knowledge transfer. As this knowledge is not available in pose regression and the teacher prediction is not always accurate, we propose to emphasize the knowledge transfer only when we trust the teacher. We achieve this by using teacher loss as a confidence score which places variable relative importance on the teacher prediction. We inject this confidence score to the main training task via Attentive Imitation Loss (AIL) and when learning the intermediate representation of the teacher through Attentive Hint Training (AHT) approach. To the best of our knowledge, this is the first work which successfully distill the knowledge from a deep pose regression network. Our evaluation on the KITTI and Malaga dataset shows that we can keep the student prediction close to the teacher with up to 92.95% parameter reduction and 2.12x faster in computation time.
We propose a novel, conceptually simple and general framework for instance segmentation on 3D point clouds. Our method, called 3D-BoNet, follows the simple design philosophy of per-point multilayer perceptrons (MLPs). The framework directly regresses 3D bounding boxes for all instances in a point cloud, while simultaneously predicting a point-level mask for each instance. It consists of a backbone network followed by two parallel network branches for 1) bounding box regression and 2) point mask prediction. 3D-BoNet is single-stage, anchor-free and end-to-end trainable. Moreover, it is remarkably computationally efficient as, unlike existing approaches, it does not require any post-processing steps such as non-maximum suppression, feature sampling, clustering or voting. Extensive experiments show that our approach surpasses existing work on both ScanNet and S3DIS datasets while being approximately 10x more computationally efficient. Comprehensive ablation studies demonstrate the effectiveness of our design.
Inspired by the cognitive process of humans and animals, Curriculum Learning (CL) trains a model by gradually increasing the difficulty of the training data. In this paper, we study whether CL can be applied to complex geometry problems like estimating monocular Visual Odometry (VO). Unlike existing CL approaches, we present a novel CL strategy for learning the geometry of monocular VO by gradually making the learning objective more difficult during training. To this end, we propose a novel geometry-aware objective function by jointly optimizing relative and composite transformations over small windows via bounded pose regression loss. A cascade optical flow network followed by recurrent network with a differentiable windowed composition layer, termed CL-VO, is devised to learn the proposed objective. Evaluation on three real-world datasets shows superior performance of CL-VO over state-of-the-art feature-based and learning-based VO.
Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data. In this paper, we derive an alternative variational lower bound from the one common in VAEs, which aims to minimize aggregate information loss. Using our lower bound as the objective function for an auto-encoder enables us to place a prior on the bulk statistics, corresponding to an aggregate posterior for the entire dataset, as opposed to a single sample posterior as in the original VAE. This alternative form of prior constraint allows individual posteriors more flexibility to preserve necessary information for good reconstruction quality. We further derive an analytic approximation to our lower bound, leading to an efficient learning algorithm - WiSE-ALE. Through various examples, we demonstrate that WiSE-ALE can reach excellent reconstruction quality in comparison to other state-of-the-art VAE models, while still retaining the ability to learn a smooth, compact representation.
Deep learning approaches for Visual-Inertial Odometry (VIO) have proven successful, but they rarely focus on incorporating robust fusion strategies for dealing with imperfect input sensory data. We propose a novel end-to-end selective sensor fusion framework for monocular VIO, which fuses monocular images and inertial measurements in order to estimate the trajectory whilst improving robustness to real-life issues, such as missing and corrupted data or bad sensor synchronization. In particular, we propose two fusion modalities based on different masking strategies: deterministic soft fusion and stochastic hard fusion, and we compare with previously proposed direct fusion baselines. During testing, the network is able to selectively process the features of the available sensor modalities and produce a trajectory at scale. We present a thorough investigation on the performances on three public autonomous driving, Micro Aerial Vehicle (MAV) and hand-held VIO datasets. The results demonstrate the effectiveness of the fusion strategies, which offer better performances compared to direct fusion, particularly in presence of corrupted data. In addition, we study the interpretability of the fusion networks by visualising the masking layers in different scenarios and with varying data corruption, revealing interesting correlations between the fusion networks and imperfect sensory input data.
Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data. In this paper, we derive an alternative variational lower bound from the one common in VAEs, which aims to minimize aggregate information loss. Using our lower bound as the objective function for an auto-encoder enables us to place a prior on the bulk statistics, corresponding to an aggregate posterior of all latent codes, as opposed to a single code posterior as in the original VAE. This alternative form of prior constraint allows individual posteriors more flexibility to preserve necessary information for good reconstruction quality. We further derive an analytic approximation to our lower bound, leading to our proposed model - WiSE-VAE. Through various examples, we demonstrate that WiSE-VAE can reach excellent reconstruction quality in comparison to other state-of-the-art VAE models, while still retaining the ability to learn a smooth, compact representation.