In this paper, we propose a novel training strategy for convolutional neural network(CNN) named Feature Mining, that aims to strengthen the network's learning of the local feature. Through experiments, we find that semantic contained in different parts of the feature is different, while the network will inevitably lose the local information during feedforward propagation. In order to enhance the learning of local feature, Feature Mining divides the complete feature into two complementary parts and reuse these divided feature to make the network learn more local information, we call the two steps as feature segmentation and feature reusing. Feature Mining is a parameter-free method and has plug-and-play nature, and can be applied to any CNN models. Extensive experiments demonstrate the wide applicability, versatility, and compatibility of our method.
Crowdfunding has emerged as a prominent way for entrepreneurs to secure funding without sophisticated intermediation. In crowdfunding, an entrepreneur often has to decide how to disclose the campaign status in order to collect as many contributions as possible. Such decisions are difficult to make primarily due to incomplete information. We propose information design as a tool to help the entrepreneur to improve revenue by influencing backers' beliefs. We introduce a heuristic algorithm to dynamically compute information-disclosure policies for the entrepreneur, followed by an empirical evaluation to demonstrate its competitiveness over the widely-adopted immediate-disclosure policy. Our results demonstrate that the immediate-disclosure policy is not optimal when backers follow thresholding policies despite its ease of implementation. With appropriate heuristics, an entrepreneur can benefit from dynamic information disclosure. Our work sheds light on information design in a dynamic setting where agents make decisions using thresholding policies.
The fusion of multi-modal sensors has become increasingly popular in autonomous driving and intelligent robots since it can provide richer information than any single sensor, enhance reliability in complex environments. Multi-sensor extrinsic calibration is one of the key factors of sensor fusion. However, such calibration is difficult due to the variety of sensor modalities and the requirement of calibration targets and human labor. In this paper, we demonstrate a new targetless cross-modal calibration framework by focusing on the extrinsic transformations among stereo cameras, thermal cameras, and laser sensors. Specifically, the calibration between stereo and laser is conducted in 3D space by minimizing the registration error, while the thermal extrinsic to the other two sensors is estimated by optimizing the alignment of the edge features. Our method requires no dedicated targets and performs the multi-sensor calibration in a single shot without human interaction. Experimental results show that the calibration framework is accurate and applicable in general scenes.
Lip reading, aiming to recognize spoken sentences according to the given video of lip movements without relying on the audio stream, has attracted great interest due to its application in many scenarios. Although prior works that explore lip reading have obtained salient achievements, they are all trained in a non-simultaneous manner where the predictions are generated requiring access to the full video. To breakthrough this constraint, we study the task of simultaneous lip reading and devise SimulLR, a simultaneous lip Reading transducer with attention-guided adaptive memory from three aspects: (1) To address the challenge of monotonic alignments while considering the syntactic structure of the generated sentences under simultaneous setting, we build a transducer-based model and design several effective training strategies including CTC pre-training, model warm-up and curriculum learning to promote the training of the lip reading transducer. (2) To learn better spatio-temporal representations for simultaneous encoder, we construct a truncated 3D convolution and time-restricted self-attention layer to perform the frame-to-frame interaction within a video segment containing fixed number of frames. (3) The history information is always limited due to the storage in real-time scenarios, especially for massive video data. Therefore, we devise a novel attention-guided adaptive memory to organize semantic information of history segments and enhance the visual representations with acceptable computation-aware latency. The experiments show that the SimulLR achieves the translation speedup 9.10$\times$ compared with the state-of-the-art non-simultaneous methods, and also obtains competitive results, which indicates the effectiveness of our proposed methods.
Salient object detection requires a comprehensive and scalable receptive field to locate the visually significant objects in the image. Recently, the emergence of visual transformers and multi-branch modules has significantly enhanced the ability of neural networks to perceive objects at different scales. However, compared to the traditional backbone, the calculation process of transformers is time-consuming. Moreover, different branches of the multi-branch modules could cause the same error back propagation in each training iteration, which is not conducive to extracting discriminative features. To solve these problems, we propose a bilateral network based on transformer and CNN to efficiently broaden local details and global semantic information simultaneously. Besides, a Multi-Head Boosting (MHB) strategy is proposed to enhance the specificity of different network branches. By calculating the errors of different prediction heads, each branch can separately pay more attention to the pixels that other branches predict incorrectly. Moreover, Unlike multi-path parallel training, MHB randomly selects one branch each time for gradient back propagation in a boosting way. Additionally, an Attention Feature Fusion Module (AF) is proposed to fuse two types of features according to respective characteristics. Comprehensive experiments on five benchmark datasets demonstrate that the proposed method can achieve a significant performance improvement compared with the state-of-the-art methods.
We consider the task of learning latent community structure from multiple correlated networks. First, we study the problem of learning the latent vertex correspondence between two edge-correlated stochastic block models, focusing on the regime where the average degree is logarithmic in the number of vertices. We derive the precise information-theoretic threshold for exact recovery: above the threshold there exists an estimator that outputs the true correspondence with probability close to 1, while below it no estimator can recover the true correspondence with probability bounded away from 0. As an application of our results, we show how one can exactly recover the latent communities using multiple correlated graphs in parameter regimes where it is information-theoretically impossible to do so using just a single graph.
Motivated by the common strategic activities in crowdsourcing labeling, we study the problem of sequential eliciting information without verification (EIWV) for workers with a heterogeneous and unknown crowd. We propose a reinforcement learning-based approach that is effective against a wide range of settings including potential irrationality and collusion among workers. With the aid of a costly oracle and the inference method, our approach dynamically decides the oracle calls and gains robustness even under the presence of frequent collusion activities. Extensive experiments show the advantage of our approach. Our results also present the first comprehensive experiments of EIWV on large-scale real datasets and the first thorough study of the effects of environmental variables.
Cross-modal representation learning allows to integrate information from different modalities into one representation. At the same time, research on generative models tends to focus on the visual domain with less emphasis on other domains, such as audio or text, potentially missing the benefits of shared representations. Studies successfully linking more than one modality in the generative setting are rare. In this context, we verify the possibility to train variational autoencoders (VAEs) to reconstruct image archetypes from audio data. Specifically, we consider VAEs in an adversarial training framework in order to ensure more variability in the generated data and find that there is a trade-off between the consistency and diversity of the generated images - this trade-off can be governed by scaling the reconstruction loss up or down, respectively. Our results further suggest that even in the case when the generated images are relatively inconsistent (diverse), features that are critical for proper image classification are preserved.
The shape and motion of the heart provide essential clues to understanding the mechanisms of cardiovascular disease. With the advent of large-scale cardiac imaging data, statistical atlases become a powerful tool to provide automated and precise quantification of the status of patient-specific heart geometry with respect to reference populations. The Multi-Ethnic Study of Atherosclerosis (MESA), begun in 2000, was the first large cohort study to incorporate cardiovascular MRI in over 5000 participants, and there is now a wealth of follow-up data over 20 years. Building a machine learning based automated analysis is necessary to extract the additional imaging information necessary for expanding original manual analyses. However, machine learning tools trained on MRI datasets with different pulse sequences fail on such legacy datasets. Here, we describe an automated atlas construction pipeline using deep learning methods applied to the legacy cardiac MRI data in MESA. For detection of anatomical cardiac landmark points, a modified VGGNet convolutional neural network architecture was used in conjunction with a transfer learning sequence between two-chamber, four-chamber, and short-axis MRI views. A U-Net architecture was used for detection of the endocardial and epicardial boundaries in short axis images. Both network architectures resulted in good segmentation and landmark detection accuracies compared with inter-observer variations. Statistical relationships with common risk factors were similar between atlases derived from automated vs manual annotations. The automated atlas can be employed in future studies to examine the relationships between cardiac morphology and future events.
In this paper, we investigate the combination of multigrid methods and neural networks, starting from a Finite Element discretization of an elliptic PDE. Multigrid methods use interpolation operators to transfer information between different levels of approximation. These operators are crucial for fast convergence of multigrid, but they are generally unknown. We propose Deep Neural Network models for learning interpolation operators and we build a multilevel hierarchy based on the output of the network. We investigate the accuracy of the interpolation operator predicted by the Neural Network, testing it with different network architectures. This Neural Network approach for the construction of grid operators can then be extended for an automatic definition of multilevel solvers, allowing a portable solution in scientific computing