Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks. In this context, we are targeting knowledge transfer from a set with abundant data to other sets with few available examples. We propose two simple and effective solutions: (i) dense classification over feature maps, which for the first time studies local activations in the domain of few-shot learning, and (ii) implanting, that is, attaching new neurons to a previously trained network to learn new, taskspecific features. On miniImageNet, we improve the prior state-of-the-art on few-shot classification, i.e., we achieve 62.5%, 79.8% and 83.8% on 5-way 1-shot, 5-shot and 10shot settings respectively. 1 We use the notation [i] := {1, . . . , i} for i ∈ N.
In this paper, we address the problem of dataset quality in the context of Machine Learning (ML)-based critical systems. We briefly analyse the applicability of some existing standards dealing with data and show that the specificities of the ML context are neither properly captured nor taken into account. As a first answer to this concerning situation, we propose a dataset specification and verification process, and apply it on a signal recognition system from the railway domain. In addition, we also give a list of recommendations for the collection and management of datasets. This work is one step towards the dataset engineering process that will be required for ML to be used on safety critical systems.
This paper aims at understanding the role of multi-scale information in the estimation of depth from monocular images. More precisely, the paper investigates four different deep CNN architectures, designed to explicitly make use of multi-scale features along the network, and compare them to a state-of-the-art single-scale approach. The paper also shows that involving multi-scale features in depth estimation not only improves the performance in terms of accuracy, but also gives qualitatively better depth maps. Experiments are done on the widely used NYU Depth dataset, on which the proposed method achieves state-of-the-art performance.
Abstract. Image retrieval from image databases is usually performed by using global image characteristics. However the use of local image information is highly desirable when only part of the image is of interest. An original solution was introduced in [9] using invariant local signal characteristics. This paper extends this contribution by extending the set of invariants considered to allow illumination change. Then it is shown that the invariant distribution is far from uniform and a probabilistic indexing scheme is proposed. Experimental results validate the approch and the different methods are discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.