Existing video frame interpolation methods can only interpolate the frame at a given intermediate time-step, e.g. 1/2. In this paper, we aim to explore a more generalized kind of video frame interpolation, that at an arbitrary time-step. To this end, we consider processing different time-steps with adaptively generated convolutional kernels in a unified way with the help of meta-learning. Specifically, we develop a dual meta-learned frame interpolation framework to synthesize intermediate frames with the guidance of context information and optical flow as well as taking the time-step as side information. First, a content-aware meta-learned flow refinement module is built to improve the accuracy of the optical flow estimation based on the down-sampled version of the input frames. Second, with the refined optical flow and the time-step as the input, a motion-aware meta-learned frame interpolation module generates the convolutional kernels for every pixel used in the convolution operations on the feature map of the coarse warped version of the input frames to generate the predicted frame. Extensive qualitative and quantitative evaluations, as well as ablation studies, demonstrate that, via introducing meta-learning in our framework in such a well-designed way, our method not only achieves superior performance to state-of-the-art frame interpolation approaches but also owns an extended capacity to support the interpolation at an arbitrary time-step.
Recently vision transformer models have become prominent models for a range of vision tasks. These models, however, are usually opaque with weak feature interpretability. Moreover, there is no method currently built for an intrinsically interpretable transformer, which is able to explain its reasoning process and provide a faithful explanation. To close these crucial gaps, we propose a novel vision transformer dubbed the eXplainable Vision Transformer (eX-ViT), an intrinsically interpretable transformer model that is able to jointly discover robust interpretable features and perform the prediction. Specifically, eX-ViT is composed of the Explainable Multi-Head Attention (E-MHA) module, the Attribute-guided Explainer (AttE) module and the self-supervised attribute-guided loss. The E-MHA tailors explainable attention weights that are able to learn semantically interpretable representations from local patches in terms of model decisions with noise robustness. Meanwhile, AttE is proposed to encode discriminative attribute features for the target object through diverse attribute discovery, which constitutes faithful evidence for the model's predictions. In addition, a self-supervised attribute-guided loss is developed for our eX-ViT, which aims at learning enhanced representations through the attribute discriminability mechanism and attribute diversity mechanism, to localize diverse and discriminative attributes and generate more robust explanations. As a result, we can uncover faithful and robust interpretations with diverse attributes through the proposed eX-ViT.
This paper presents the summary report on our DFGC 2022 competition. The DeepFake is rapidly evolving, and realistic face-swaps are becoming more deceptive and difficult to detect. On the contrary, methods for detecting DeepFakes are also improving. There is a two-party game between DeepFake creators and defenders. This competition provides a common platform for benchmarking the game between the current state-of-the-arts in DeepFake creation and detection methods. The main research question to be answered by this competition is the current state of the two adversaries when competed with each other. This is the second edition after the last year's DFGC 2021, with a new, more diverse video dataset, a more realistic game setting, and more reasonable evaluation metrics. With this competition, we aim to stimulate research ideas for building better defenses against the DeepFake threats. We also release our DFGC 2022 dataset contributed by both our participants and ourselves to enrich the DeepFake data resources for the research community (https://github.com/NiCE-X/DFGC-2022).
Radar target recognition (RTR), as a key technology of intelligent radar systems, has been well investigated. Accurate RTR at low signal-to-noise ratios (SNRs) still remains an open challenge. Most existing methods are based on a single radar or the homogeneous radar network, which do not fully exploit frequency-dimensional information. In this paper, a two-stream semantic feature fusion model, termed Multi-faceted Graph Attention Network (MF-GAT), is proposed to greatly improve the accuracy in the low SNR region of the heterogeneous radar network. By fusing the features extracted from the source domain and transform domain via a graph attention network model, the MF-GAT model distills higher-level semantic features before classification in a unified framework. Extensive experiments are presented to demonstrate that the proposed model can greatly improve the RTR performance at low SNRs.
High-resolution (HR) MRI is critical in assisting the doctor's diagnosis and image-guided treatment, but is hard to obtain in a clinical setting due to long acquisition time. Therefore, the research community investigated deep learning-based super-resolution (SR) technology to reconstruct HR MRI images with shortened acquisition time. However, training such neural networks usually requires paired HR and low-resolution (LR) in-vivo images, which are difficult to acquire due to patient movement during and between the image acquisition. Rigid movements of hard tissues can be corrected with image-registration, whereas the alignment of deformed soft tissues is challenging, making it impractical to train the neural network with such authentic HR and LR image pairs. Therefore, most of the previous studies proposed SR reconstruction by employing authentic HR images and synthetic LR images downsampled from the HR images, yet the difference in degradation representations between synthetic and authentic LR images suppresses the performance of SR reconstruction from authentic LR images. To mitigate the aforementioned problems, we propose a novel Unsupervised DEgradation Adaptation Network (UDEAN). Our model consists of two components: the degradation learning network and the SR reconstruction network. The degradation learning network downsamples the HR images by addressing the degradation representation of the misaligned or unpaired LR images, and the SR reconstruction network learns the mapping from the downsampled HR images to their original HR images. As a result, the SR reconstruction network can generate SR images from the LR images and achieve comparable quality to the HR images. Experimental results show that our method outperforms the state-of-the-art models and can potentially be applied in real-world clinical settings.
This paper proposes a knowledge-and-data-driven graph neural network-based collaboration learning model for reliable aircraft recognition in a heterogeneous radar network. The aircraft recognizability analysis shows that: (1) the semantic feature of an aircraft is motion patterns driven by the kinetic characteristics, and (2) the grammatical features contained in the radar cross-section (RCS) signals present spatial-temporal-frequency (STF) diversity decided by both the electromagnetic radiation shape and motion pattern of the aircraft. Then a STF graph attention convolutional network (STFGACN) is developed to distill semantic features from the RCS signals received by the heterogeneous radar network. Extensive experiment results verify that the STFGACN outperforms the baseline methods in terms of detection accuracy, and ablation experiments are carried out to further show that the expansion of the information dimension can gain considerable benefits to perform robustly in the low signal-to-noise ratio region.
The automotive mmWave radar plays a key role in advanced driver assistance systems (ADAS) and autonomous driving. Deep learning-based instance segmentation enables real-time object identification from the radar detection points. In the conventional training process, accurate annotation is the key. However, high-quality annotations of radar detection points are challenging to achieve due to their ambiguity and sparsity. To address this issue, we propose a contrastive learning approach for implementing radar detection points-based instance segmentation. We define the positive and negative samples according to the ground-truth label, apply the contrastive loss to train the model first, and then perform training for the following downstream task. In addition, these two steps can be merged into one, and pseudo labels can be generated for the unlabeled data to improve the performance further. Thus, there are four different training settings for our method. Experiments show that when the ground-truth information is only available for 5% of the training data, our method still achieves a comparable performance to the approach trained in a supervised manner with 100% ground-truth information.
In this paper, we first present a single-input, multiple-output convolutional neural network that can estimate both heart rate and respiration rate simultaneously by exploiting the underlying link between heart rate and respiration rate. The inputs to the neural network are the amplitude and phase of channel state information collected by a pair of WiFi devices. Our WiFi-based technique addresses privacy concerns and is adapt- able to a variety of settings. This system overall accuracy for the heart and respiration rate estimation can reach 99.109% and 98.581%, respectively. Furthermore, we developed and analyzed two deep learning-based neural network classification algorithms for categorizing four types of sleep stages: wake, rapid eye movement (REM) sleep, non-rapid eye movement (NREM) light sleep, and NREM deep sleep. This system overall classification accuracy can reach 95.925%
A discourse containing one or more sentences describes daily issues and events for people to communicate their thoughts and opinions. As sentences are normally consist of multiple text segments, correct understanding of the theme of a discourse should take into consideration of the relations in between text segments. Although sometimes a connective exists in raw texts for conveying relations, it is more often the cases that no connective exists in between two text segments but some implicit relation does exist in between them. The task of implicit discourse relation recognition (IDRR) is to detect implicit relation and classify its sense between two text segments without a connective. Indeed, the IDRR task is important to diverse downstream natural language processing tasks, such as text summarization, machine translation and so on. This article provides a comprehensive and up-to-date survey for the IDRR task. We first summarize the task definition and data sources widely used in the field. We categorize the main solution approaches for the IDRR task from the viewpoint of its development history. In each solution category, we present and analyze the most representative methods, including their origins, ideas, strengths and weaknesses. We also present performance comparisons for those solutions experimented on a public corpus with standard data processing procedures. Finally, we discuss future research directions for discourse relation analysis.
Extracting roads from high-resolution remote sensing images (HRSIs) is vital in a wide variety of applications, such as autonomous driving, path planning, and road navigation. Due to the long and thin shape as well as the shades induced by vegetation and buildings, small-sized roads are more difficult to discern. In order to improve the reliability and accuracy of small-sized road extraction when roads of multiple sizes coexist in an HRSI, an enhanced deep neural network model termed Dual-Decoder-U-Net (DDU-Net) is proposed in this paper. Motivated by the U-Net model, a small decoder is added to form a dual-decoder structure for more detailed features. In addition, we introduce the dilated convolution attention module (DCAM) between the encoder and decoders to increase the receptive field as well as to distill multi-scale features through cascading dilated convolution and global average pooling. The convolutional block attention module (CBAM) is also embedded in the parallel dilated convolution and pooling branches to capture more attention-aware features. Extensive experiments are conducted on the Massachusetts Roads dataset with experimental results showing that the proposed model outperforms the state-of-the-art DenseUNet, DeepLabv3+ and D-LinkNet by 6.5%, 3.3%, and 2.1% in the mean Intersection over Union (mIoU), and by 4%, 4.8%, and 3.1% in the F1 score, respectively. Both ablation and heatmap analyses are presented to validate the effectiveness of the proposed model.