The monocular Visual-Inertial Odometry (VIO) based on the direct method can leverage all the available pixels in the image to estimate the camera motion and reconstruct the environment. The denser map reconstruction provides more information about the environment, making it easier to extract structure and planar regularities. In this paper, we propose a monocular direct sparse visual-inertial odometry, which exploits the plane regularities (PVI-DSO). Our system detects coplanar information from 3D meshes generated from 3D point clouds and uses coplanar parameters to introduce coplanar constraints. In order to reduce computation and improve compactness, the plane-distance cost is directly used as the prior information of plane parameters. We conduct ablation experiments on public datasets and compare our system with other state-of-the-art algorithms. The experimental results verified leveraging the plane information can improve the accuracy of the VIO system based on the direct method.
C\^ote d'Ivoire and Ghana, the world's largest producers of cocoa, account for two thirds of the global cocoa production. In both countries, cocoa is the primary perennial crop, providing income to almost two million farmers. Yet precise maps of cocoa planted area are missing, hindering accurate quantification of expansion in protected areas, production and yields, and limiting information available for improved sustainability governance. Here, we combine cocoa plantation data with publicly available satellite imagery in a deep learning framework and create high-resolution maps of cocoa plantations for both countries, validated in situ. Our results suggest that cocoa cultivation is an underlying driver of over 37% and 13% of forest loss in protected areas in C\^ote d'Ivoire and Ghana, respectively, and that official reports substantially underestimate the planted area, up to 40% in Ghana. These maps serve as a crucial building block to advance understanding of conservation and economic development in cocoa producing regions.
Brain science and artificial intelligence have made great progress toward the understanding and engineering of the human mind. The progress has accelerated significantly since the turn of the century thanks to new methods for probing the brain (both structure and function), and rapid development in deep learning research. However, despite these new developments, there are still many open questions, such as how to understand the brain at the system level, and various robustness issues and limitations of deep learning. In this informal essay, I will talk about some of the concepts that are central to brain science and artificial intelligence, such as information and memory, and discuss how a different view on these concepts can help us move forward, beyond current limits of our understanding in these fields.
Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused -- strategic machines might craft representations that manipulate their users. How can a user make good choices based on strategic representations? We formalize this as a learning problem, and pursue algorithms for decision-making that are robust to manipulation. In our main setting of interest, the system represents attributes of an item to the user, who then decides whether or not to consume. We model this interaction through the lens of strategic classification (Hardt et al. 2016), reversed: the user, who learns, plays first; and the system, which responds, plays second. The system must respond with representations that reveal `nothing but the truth' but need not reveal the entire truth. Thus, the user faces the problem of learning set functions under strategic subset selection, which presents distinct algorithmic and statistical challenges. Our main result is a learning algorithm that minimizes error despite strategic representations, and our theoretical analysis sheds light on the trade-off between learning effort and susceptibility to manipulation.
If a unit cannot receive intelligence from a source due to external factors, we consider them disadvantaged users. We categorize this as a preoccupied unit working on a low connectivity device on the edge. This case requires that we use a different approach to deliver intelligence, particularly satellite imagery information, than normally employed. To address this, we propose a survey of information reduction techniques to deliver the information from a satellite image in a smaller package. We investigate four techniques to aid in the reduction of delivered information: traditional image compression, neural network image compression, object detection image cutout, and image to caption. Each of these mechanisms have their benefits and tradeoffs when considered for a disadvantaged user.
The advent of noisy intermediate-scale quantum computers has put the search for possible applications to the forefront of quantum information science. One area where hopes for an advantage through near-term quantum computers are high is quantum machine learning, where variational quantum learning models based on parametrized quantum circuits are discussed. In this work, we introduce the concept of a classical surrogate, a classical model which can be efficiently obtained from a trained quantum learning model and reproduces its input-output relations. As inference can be performed classically, the existence of a classical surrogate greatly enhances the applicability of a quantum learning strategy. However, the classical surrogate also challenges possible advantages of quantum schemes. As it is possible to directly optimize the ansatz of the classical surrogate, they create a natural benchmark the quantum model has to outperform. We show that large classes of well-analyzed re-uploading models have a classical surrogate. We conducted numerical experiments and found that these quantum models show no advantage in performance or trainability in the problems we analyze. This leaves only generalization capability as possible point of quantum advantage and emphasizes the dire need for a better understanding of inductive biases of quantum learning models.
Unsupervised domain adaptive (UDA) person re-identification (ReID) has gained increasing attention for its effectiveness on the target domain without manual annotations. Most fine-tuning based UDA person ReID methods focus on encoding global features for pseudo labels generation, neglecting the local feature that can provide for the fine-grained information. To handle this issue, we propose a Learning Feature Fusion (LF2) framework for adaptively learning to fuse global and local features to obtain a more comprehensive fusion feature representation. Specifically, we first pre-train our model within a source domain, then fine-tune the model on unlabeled target domain based on the teacher-student training strategy. The average weighting teacher network is designed to encode global features, while the student network updating at each iteration is responsible for fine-grained local features. By fusing these multi-view features, multi-level clustering is adopted to generate diverse pseudo labels. In particular, a learnable Fusion Module (FM) for giving prominence to fine-grained local information within the global feature is also proposed to avoid obscure learning of multiple pseudo labels. Experiments show that our proposed LF2 framework outperforms the state-of-the-art with 73.5% mAP and 83.7% Rank1 on Market1501 to DukeMTMC-ReID, and achieves 83.2% mAP and 92.8% Rank1 on DukeMTMC-ReID to Market1501.
Deep convolutional autoencoders provide an effective tool for learning non-linear dimensionality reduction in an unsupervised way. Recently, they have been used for the task of anomaly detection in the visual domain. By optimising for the reconstruction error using anomaly-free examples, the common belief is that a trained network will have difficulties to reconstruct anomalous parts during the test phase. This is usually done by controlling the capacity of the network by either reducing the size of the bottleneck layer or enforcing sparsity constraints on its activations. However, neither of these techniques does explicitly penalise reconstruction of anomalous signals often resulting in a poor detection. We tackle this problem by adapting a self-supervised learning regime which allows to use discriminative information during training while regularising the model to focus on the data manifold by means of a modified reconstruction error resulting in an accurate detection. Unlike related approaches, the inference of the proposed method during training and prediction is very efficient processing the whole input image in one single step. Our experiments on the MVTec Anomaly Detection dataset demonstrate high recognition and localisation performance of the proposed method. On the texture-subset, in particular, our approach consistently outperforms a bunch of recent anomaly detection methods by a big margin.
Considering high-temperature heating, the equations of transient heat conduction model require an adaptation, i.e. the dependence of thermophysical parameters of the model on the temperature is to be identified for each specific material to be heated. This problem is most often solved by approximation of the tabular data on the measurements of the required parameters, which can be found in the literature, by means of regression equations. But, for example, considering the steel heating process, this approach is difficult to be implemented due to the lack of tabular discrete measurements for many grades of steel, such as alloyed ones. In this paper, the new approach is proposed, which is based on a solution of a related variational problem. Its main idea is to substitute the adaptation process in the classical sense (i.e., to find the dependencies of thermophysical parameters on temperature) with 'supervised learning' of a mesh model on the basis of the technological data received from the plant. The equations to adjust the parameters of the transient heat conduction model, which are related to the thermophysical coefficients, have been derived. A numerical experiment is conducted for steel of a particular group of grades, for which enough both technological as well as tabular data are available. As a result, the 'trained' mesh model, which has not received explicitly any information about the physical and chemical properties of the heated substance, demonstrated an average error of 18.820 C, which is quite close to the average error of the model adapted classically on the basis of the tabular data (18.10 C).
Today's state of the art visual navigation agents typically consist of large deep learning models trained end to end. Such models offer little to no interpretability about the learned skills or the actions of the agent taken in response to its environment. While past works have explored interpreting deep learning models, little attention has been devoted to interpreting embodied AI systems, which often involve reasoning about the structure of the environment, target characteristics and the outcome of one's actions. In this paper, we introduce the Interpretability System for Embodied agEnts (iSEE) for Point Goal and Object Goal navigation agents. We use iSEE to probe the dynamic representations produced by these agents for the presence of information about the agent as well as the environment. We demonstrate interesting insights about navigation agents using iSEE, including the ability to encode reachable locations (to avoid obstacles), visibility of the target, progress from the initial spawn location as well as the dramatic effect on the behaviors of agents when we mask out critical individual neurons. The code is available at: https://github.com/allenai/iSEE