Vehicle viewpoint estimation from monocular images is a crucial component for autonomous driving vehicles and for fleet management applications. In this paper, we make several contributions to advance the state-of-the-art on this problem. We show the effectiveness of applying a smoothing filter to the output neurons of a Convolutional Neural Network (CNN) when estimating vehicle viewpoint. We point out the overlooked fact that, under the same viewpoint, the appearance of a vehicle is strongly influenced by its position in the image plane, which renders viewpoint estimation from appearance an ill-posed problem. We show how, by inserting in the model a CoordConv layer to provide the coordinates of the vehicle, we are able to solve such ambiguity and greatly increase performance. Finally, we introduce a new data augmentation technique that improves viewpoint estimation on vehicles that are closer to the camera or partially occluded. All these improvements let a lightweight CNN reach optimal results while keeping inference time low. An extensive evaluation on a viewpoint estimation benchmark () and on actual vehicle camera data () shows that our method significantly outperforms the state-of-the-art in vehicle viewpoint estimation, both in terms of accuracy and memory footprint.

In this paper we deal with batch Bayesian Optimization (Bayes-Opt) problems over a box. Bayes-Opt approaches find their main applications when the objective function is very expensive to evaluate. Sometimes, given the availability of multi-processor computing architectures, function evaluation might be performed in parallel in order to lower the clock-time of the overall computation. This paper fits this situation and is devoted to the development of a novel bi-objective optimization (BOO) acquisition strategy to sample batches of points where to evaluate the objective function. The BOO problem involves the Gaussian Process posterior mean and variance functions, which, in most of the acquisition strategies from the literature, are generally used in combination, frequently through scalarization. However, such scalarization could compromise the Bayes-Opt process performance, as getting the desired trade-off between exploration and exploitation is not trivial in most cases. We instead aim to reconstruct the Pareto front of the BOO problem exploiting first order information of the posterior mean and variance, thus generating multiple trade-offs of the two functions without any a priori knowledge. The algorithm used for the reconstruction is the Non-dominated Sorting Memetic Algorithm (NSMA), recently proposed in the literature and proved to be effective in solving hard MOO problems. Finally, we present two clustering approaches, each of them operating on a different space, to select potentially optimal points from the Pareto front. We compare our methodology with well-known acquisition strategies from the literature, showing its effectiveness on a wide set of experiments.

Exemplar-free Class Incremental Learning (EFCIL) aims to learn from a sequence of tasks without having access to previous task data. In this paper, we consider the challenging Cold Start scenario in which insufficient data is available in the first task to learn a high-quality backbone. This is especially challenging for EFCIL since it requires high plasticity, resulting in feature drift which is difficult to compensate for in the exemplar-free setting. To address this problem, we propose an effective approach to consolidate feature representations by regularizing drift in directions highly relevant to previous tasks while employing prototypes to reduce task-recency bias. Our approach, which we call Elastic Feature Consolidation++ (EFC++), exploits a tractable second-order approximation of feature drift based on a proposed Empirical Feature Matrix (EFM). The EFM induces a pseudo-metric in feature space which we use to regularize feature drift in important directions and to update Gaussian prototypes. In addition, we introduce a post-training prototype re-balancing phase that updates classifiers to compensate for feature drift. This strategy allows to improve over our previous EFC method by mitigating the misalignment between stored prototypes and the evolving feature space. Extensive experimental results on Tiny-ImageNet, ImageNet-Subset, ImageNet-1K, and DomainNet show that EFC++ achieves a strong stability–plasticity trade-off in Cold Start and outperforms recent exemplar-free baselines. Code is available at https://github.com/simomagi/elastic_feature_consolidation .