Research on potential disruptive technology identification based on technology network.

Three evident and meaningful characteristics of disruptive technology are the zeroing effect that causes sustaining technology useless for its remarkable and unprecedented progress, reshaping the landscape of technology and economy, and leading the future mainstream of technology system, all of which have profound impacts and positive influences. The identification of disruptive technology is a universally difficult task. Therefore, this paper aims to enhance the technical relevance of potential disruptive technology identification results and improve the granularity and effectiveness of potential disruptive technology identification topics. According to the life cycle theory, dividing the time stage, then constructing and analyzing the dynamic of technology networks to identify potential disruptive technology. Thereby, using the Latent Dirichlet Allocation (LDA) topic model further to clarify the topic content of potential disruptive technologies. This paper takes the large civil unmanned aerial vehicles (UAVs) as an example to prove the feasibility and effectiveness of the model. The results show that the potential disruptive technology in this field is the data acquisition, main equipment, and ground platform intelligence.

An End-to-End Framework for Joint Denoising and Classification of Hyperspectral Images.

Image denoising and classification are typically conducted separately and sequentially according to their respective objectives. In such a setup, where the two tasks are decoupled, the denoising operation does not optimally serve the classification task and sometimes even deteriorates it. We introduce here a unified deep learning framework for joint denoising and classification of high-dimensional images, and we particularly apply it in the framework of hyperspectral imaging. Earlier works on joint image denoising and classification are very scarce, and to the best of our knowledge, no deep learning models were proposed or studied yet for this type of multitask image processing. A key component in our joint learning model is a compound loss function, designed in such a way that the denoising and classification operations benefit each other iteratively during the learning process. Hyperspectral images (HSIs) are particularly challenging for both denoising and classification due to their high dimensionality and varying noise statistics across the bands. We argue that a well-designed end-to-end deep learning framework for joint denoising and classification is superior to current deep learning approaches for processing HSI data, and we substantiate this by results on real HSI images in remote sensing. We experimentally show that the proposed joint learning framework substantially improves the classification performance compared to the common deep learning approaches in HSI processing, and as a by-product, the denoising results are enhanced as well, especially in terms of the semantic content, benefiting from the classification.

Uncertainty-Aware Contrastive Distillation for Incremental Semantic Segmentation.

A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e., the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely investigated in the research community and several Incremental Learning (IL) approaches have been proposed in the past years. While earlier works in computer vision have mostly focused on image classification and object detection, more recently some IL approaches for semantic segmentation have been introduced. These previous works showed that, despite its simplicity, knowledge distillation can be effectively employed to alleviate catastrophic forgetting. In this paper, we follow this research direction and, inspired by recent literature on contrastive learning, we propose a novel distillation framework, Uncertainty-aware Contrastive Distillation (UCD). In a nutshell, UCDis operated by introducing a novel distillation loss that takes into account all the images in a mini-batch, enforcing similarity between features associated to all the pixels from the same classes, and pulling apart those corresponding to pixels from different classes. In order to mitigate catastrophic forgetting, we contrast features of the new model with features extracted by a frozen model learned at the previous incremental step. Our experimental results demonstrate the advantage of the proposed distillation technique, which can be used in synergy with previous IL approaches, and leads to state-of-art performance on three commonly adopted benchmarks for incremental semantic segmentation.

Variational Structured Attention Networks for Deep Visual Representation Learning.

Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in visual representation learning. Typically, state of the art models integrate attention mechanisms for improved deep feature representations. Recently, some works have demonstrated the significance of learning and combining both spatial- and channel-wise attentions for deep feature refinement. In this paper, we aim at effectively boosting previous approaches and propose a unified deep framework to jointly learn both spatial attention maps and channel attention vectors in a principled manner so as to structure the resulting attention tensors and model interactions between these two types of attentions. Specifically, we integrate the estimation and the interaction of the attentions within a probabilistic representation learning framework, leading to VarIational STructured Attention networks (VISTA-Net). We implement the inference rules within the neural network, thus allowing for end-to-end learning of the probabilistic and the CNN front-end parameters. As demonstrated by our extensive empirical evaluation on six large-scale datasets for dense visual prediction, VISTA-Net outperforms the state-of-the-art in multiple continuous and discrete prediction tasks, thus confirming the benefit of the proposed approach in joint structured spatial-channel attention estimation for deep representation learning. The code is available at https://github.com/ygjwd12345/VISTA-Net.

GMSRI: A Texture-Based Martian Surface Rock Image Dataset.

CNN-based Martian rock image processing has attracted much attention in Mars missions lately, since it can help planetary rover autonomously recognize and collect high value science targets. However, due to the difficulty of Martian rock image acquisition, the accuracy of the processing model is affected. In this paper, we introduce a new dataset called "GMSRI" that is a mixture of real Mars images and synthetic counterparts which are generated by GAN. GMSRI aims to provide a set of Martian rock images sorted by the texture and spatial structure of rocks. This paper offers a detailed analysis of GMSRI in its current state: Five sub-trees with 28 leaf nodes and 30,000 images in total. We show that GMSRI is much larger in scale and diversity than the current same kinds of datasets. Constructing such a database is a challenging task, and we describe the data collection, selection and generation processes carefully in this paper. Moreover, we evaluate the effectiveness of the GMSRI by an image super-resolution task. We hope that the scale, diversity and hierarchical structure of GMSRI can offer opportunities to researchers in the Mars exploration community and beyond.

KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild.

In real-world scenarios (i.e., in the wild), pedestrians are often far from the camera (i.e., small scale), and they often gather together and occlude with each other (i.e., heavily occluded). However, detecting these small-scale and heavily occluded pedestrians remains a challenging problem for the existing pedestrian detection methods. We argue that these problems arise because of two factors: 1) insufficient resolution of feature maps for handling small-scale pedestrians and 2) lack of an effective strategy for extracting body part information that can directly deal with occlusion. To solve the above-mentioned problems, in this article, we propose a key-point-guided super-resolution network (coined KGSNet) for detecting these small-scale and heavily occluded pedestrians in the wild. Specifically, to address factor 1), a super-resolution network is first trained to generate a clear super-resolution pedestrian image from a small-scale one. In the super-resolution network, we exploit key points of the human body to guide the super-resolution network to recover fine details of the human body region for easier pedestrian detection. To address factor 2), a part estimation module is proposed to encode the semantic information of different human body parts where four semantic body parts (i.e., head and upper/middle/bottom body) are extracted based on the key points. Finally, based on the generated clear super-resolved pedestrian patches padded with the extracted semantic body part images at the image level, a classification network is trained to further distinguish pedestrians/backgrounds from the inputted proposal regions. Both proposed networks (i.e., super-resolution network and classification network) are optimized in an alternating manner and trained in an end-to-end fashion. Extensive experiments on the challenging CityPersons data set demonstrate the effectiveness of the proposed method, which achieves superior performance over previous state-of-the-art methods, especially for those small-scale and heavily occluded instances. Beyond this, we also achieve state-of-the-art performance (i.e., 3.89% MR-2 on the reasonable subset) on the Caltech data set.