Semantic segmentation from fine-resolution remotely sensed images is an urgent issue in satellite imagery processing. Due to the complicated environment, automatic categorization and segmen-tation is a challenging matter especially for images with a fine resolution. Solving it can help to surmount a wide varied range of obstacles in urban planning, environmental protection, and natural landscape monitoring, which paves the way for complete scene understanding. However, the existing frequently-used encoder-decoder structure is unable to effectively combine the extracted spatial and contextual features. Therefore, in this paper, we introduce the Feature Pyramid Net-work (FPN) to bridge the gap between the low-level and high-level features. Moreover, we enhance the contextual information with the elaborate Multi-Head Attention module and propose the Feature Pyramid Network with Multi-Head Attention (FPN-MHA) for semantic segmentation of fine-resolution remotely sensed images. Extensive experiments conducted on the ISPRS Potsdam and Vaihingen datasets demonstrate the effectiveness of our FPN-MHA. Code is available at https://github.com/lironui/FPN-MHA.
The soft-aided bit-marking (SABM) algorithm is based on the idea of marking bits as highly reliable bits (HRBs), highly unreliable bits (HUBs), and uncertain bits to improve the performance of hard-decision (HD) decoders. The HRBs and HUBs are used to assist the HD decoders to prevent miscorrections and to decode those originally uncorrectable cases via bit flipping (BF), respectively. In this paper, an improved SABM algorithm (called iSABM) is proposed for staircase codes (SCCs). Similar to the SABM, iSABM marks bits with the help of channel reliabilities, i.e., using the absolute values of the log-likelihood ratios. The improvements offered by iSABM include: (i) HUBs being classified using a reliability threshold, (ii) BF randomly selecting HUBs, and (iii) soft-aided decoding over multiple SCC blocks. The decoding complexity of iSABM is comparable of that of SABM. This is due to the fact that on the one hand no sorting is required (lower complexity) because of the use of a threshold for HUBs, while on the other hand multiple SCC blocks use soft information (higher complexity). Additional gains of up to 0.53 dB with respect to SABM and 0.91 dB with respect to standard SCC decoding at a bit error rate of $10^{-6}$ are reported. Furthermore, it is shown that using 1-bit reliability marking, i.e., only having HRBs and HUBs, only causes a gain penalty of up to 0.25 dB with a significantly reduced memory requirement.
Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space. Existing deep learning methods follow a hierarchical feature extraction paradigm in which high-level abstract features are derived from low-level features. However, they fail to exploit different granularity of information due to the limited interaction between these features. To this end, we propose Multi-Abstraction Refinement Network (MARNet) that ensures an effective exchange of information between multi-level features to gain local and global contextual cues while effectively preserving them till the final layer. We empirically show the effectiveness of MARNet in terms of state-of-the-art results on two challenging tasks: Shape classification and Coarse-to-fine grained semantic segmentation. MARNet significantly improves the classification performance by 2% over the baseline and outperforms the state-of-the-art methods on semantic segmentation task.
Robustness is a significant constraint in machine learning models. The performance of the algorithms must not deteriorate when training and testing with slightly different data. Deep neural network models achieve awe-inspiring results in a wide range of applications of computer vision. Still, in the presence of noise or region occlusion, some models exhibit inaccurate performance even with data handled in training. Besides, some experiments suggest deep learning models sometimes use incorrect parts of the input information to perform inference. Activate Image Augmentation (ADA) is an augmentation method that uses interpretability methods to augment the training data and improve its robustness to face the described problems. Although ADA presented interesting results, its original version only used the Vanilla Backpropagation interpretability to train the U-Net model. In this work, we propose an extensive experimental analysis of the interpretability method's impact on ADA. We use five interpretability methods: Vanilla Backpropagation, Guided Backpropagation, GradCam, Guided GradCam, and InputXGradient. The results show that all methods achieve similar performance at the ending of training, but when combining ADA with GradCam, the U-Net model presented an impressive fast convergence.
This study considers the task of machine reading at scale (MRS) wherein, given a question, a system first performs the information retrieval (IR) task of finding relevant passages in a knowledge source and then carries out the reading comprehension (RC) task of extracting an answer span from the passages. Previous MRS studies, in which the IR component was trained without considering answer spans, struggled to accurately find a small number of relevant passages from a large set of passages. In this paper, we propose a simple and effective approach that incorporates the IR and RC tasks by using supervised multi-task learning in order that the IR component can be trained by considering answer spans. Experimental results on the standard benchmark, answering SQuAD questions using the full Wikipedia as the knowledge source, showed that our model achieved state-of-the-art performance. Moreover, we thoroughly evaluated the individual contributions of our model components with our new Japanese dataset and SQuAD. The results showed significant improvements in the IR task and provided a new perspective on IR for RC: it is effective to teach which part of the passage answers the question rather than to give only a relevance score to the whole passage.
We introduce algorithmic information theory, also known as the theory of Kolmogorov complexity. We explain the main concepts of this quantitative approach to defining `information'. We discuss the extent to which Kolmogorov's and Shannon's information theory have a common purpose, and where they are fundamentally different. We indicate how recent developments within the theory allow one to formally distinguish between `structural' (meaningful) and `random' information as measured by the Kolmogorov structure function, which leads to a mathematical formalization of Occam's razor in inductive inference. We end by discussing some of the philosophical implications of the theory.
In this paper, we propose a learning-based approach for denoising raw videos captured under low lighting conditions. We propose to do this by first explicitly aligning the neighboring frames to the current frame using a convolutional neural network (CNN). We then fuse the registered frames using another CNN to obtain the final denoised frame. To avoid directly aligning the temporally distant frames, we perform the two processes of alignment and fusion in multiple stages. Specifically, at each stage, we perform the denoising process on three consecutive input frames to generate the intermediate denoised frames which are then passed as the input to the next stage. By performing the process in multiple stages, we can effectively utilize the information of neighboring frames without directly aligning the temporally distant frames. We train our multi-stage system using an adversarial loss with a conditional discriminator. Specifically, we condition the discriminator on a soft gradient mask to prevent introducing high-frequency artifacts in smooth regions. We show that our system is able to produce temporally coherent videos with realistic details. Furthermore, we demonstrate through extensive experiments that our approach outperforms state-of-the-art image and video denoising methods both numerically and visually.
The current optimization approaches of construction machinery are mainly based on internal sensors. However, the decision of a reasonable strategy is not only determined by its intrinsic signals, but also very strongly by environmental information, such as terrain. Due to the lack of methods to aware the environment, although many promising methods were proposed to improve the mobile machines' efficiency, most construction machinery engineers must focus on the most hazardous situation and have to give the highest priority to safety when designing. Consequently, the industry does not fully benefited from the existing research. Also, due to the dynamically changing of the construction site and the consequent absence of a high definition map, the localization of mobile machines is still a challenging task. In this study, we proposed a SLAM method to create a multi-layer gird map for the construction site so that the machine can have the environmental information and be optimized accordingly. Concretely, after the machine passes by, we can get the local information and record it. Combining with positioning technology, we then create a map of the interesting places of the construction site. As a result of our research gathered from Gazebo, we showed that a suitable layout is the combination of 1 IMU and 2 differential GPS antennas using the unscented Kalman filter, which keeps the average distance error lower than 2m and the mapping error lower than 2% in the harsh environment. As an outlook, our SLAM technology provides the cornerstone to activate many efficiency improvement approaches.
An inductive logic can be formulated in which the elements are not propositions or probability distributions, but information systems. The logic is complete for information systems with binary hypotheses, i.e., it applies to all such systems. It is not complete for information systems with more than two hypotheses, but applies to a subset of such systems. The logic is inductive in that conclusions are more informative than premises. Inferences using the formalism have a strong justification in terms of the expected value of the derived information system.
Task engagement is defined as loadings on energetic arousal (affect), task motivation, and concentration (cognition). It is usually challenging and expensive to label cognitive state data, and traditional computational models trained with limited label information for engagement assessment do not perform well because of overfitting. In this paper, we proposed two deep models (i.e., a deep classifier and a deep autoencoder) for engagement assessment with scarce label information. We recruited 15 pilots to conduct a 4-h flight simulation from Seattle to Chicago and recorded their electroencephalograph (EEG) signals during the simulation. Experts carefully examined the EEG signals and labeled 20 min of the EEG data for each pilot. The EEG signals were preprocessed and power spectral features were extracted. The deep models were pretrained by the unlabeled data and were fine-tuned by a different proportion of the labeled data (top 1%, 3%, 5%, 10%, 15%, and 20%) to learn new representations for engagement assessment. The models were then tested on the remaining labeled data. We compared performances of the new data representations with the original EEG features for engagement assessment. Experimental results show that the representations learned by the deep models yielded better accuracies for the six scenarios (77.09%, 80.45%, 83.32%, 85.74%, 85.78%, and 86.52%), based on different proportions of the labeled data for training, as compared with the corresponding accuracies (62.73%, 67.19%, 73.38%, 79.18%, 81.47%, and 84.92%) achieved by the original EEG features. Deep models are effective for engagement assessment especially when less label information was used for training.