Audio adversarial examples are audio files that have been manipulated to fool an automatic speech recognition (ASR) system, while still sounding benign to a human listener. Most methods to generate such samples are based on a two-step algorithm: first, a viable adversarial audio file is produced, then, this is fine-tuned with respect to perceptibility and robustness. In this work, we present an integrated algorithm that uses psychoacoustic models and room impulse responses (RIR) in the generation step. The RIRs are dynamically created by a neural network during the generation process to simulate a physical environment to harden our examples against transformations experienced in over-the-air attacks. We compare the different approaches in three experiments: in a simulated environment and in a realistic over-the-air scenario to evaluate the robustness, and in a human study to evaluate the perceptibility. Our algorithms considering psychoacoustics only or in addition to the robustness show an improvement in the signal-to-noise ratio (SNR) as well as in the human perception study, at the cost of an increased word error rate (WER).
相關內容
Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper, we present a plug-and-play pruning-and-recovering framework, called Hourglass Tokenizer (HoT), for efficient transformer-based 3D human pose estimation from videos. Our HoT begins with pruning pose tokens of redundant frames and ends with recovering full-length tokens, resulting in a few pose tokens in the intermediate transformer blocks and thus improving the model efficiency. To effectively achieve this, we propose a token pruning cluster (TPC) that dynamically selects a few representative tokens with high semantic diversity while eliminating the redundancy of video frames. In addition, we develop a token recovering attention (TRA) to restore the detailed spatio-temporal information based on the selected tokens, thereby expanding the network output to the original full-length temporal resolution for fast inference. Extensive experiments on two benchmark datasets (i.e., Human3.6M and MPI-INF-3DHP) demonstrate that our method can achieve both high efficiency and estimation accuracy compared to the original VPT models. For instance, applying to MotionBERT and MixSTE on Human3.6M, our HoT can save nearly 50% FLOPs without sacrificing accuracy and nearly 40% FLOPs with only 0.2% accuracy drop, respectively. Our source code will be open-sourced.
As IoT devices become widely, it is crucial to protect them from malicious intrusions. However, the data scarcity of IoT limits the applicability of traditional intrusion detection methods, which are highly data-dependent. To address this, in this paper we propose the Open-Set Dandelion Network (OSDN) based on unsupervised heterogeneous domain adaptation in an open-set manner. The OSDN model performs intrusion knowledge transfer from the knowledge-rich source network intrusion domain to facilitate more accurate intrusion detection for the data-scarce target IoT intrusion domain. Under the open-set setting, it can also detect newly-emerged target domain intrusions that are not observed in the source domain. To achieve this, the OSDN model forms the source domain into a dandelion-like feature space in which each intrusion category is compactly grouped and different intrusion categories are separated, i.e., simultaneously emphasising inter-category separability and intra-category compactness. The dandelion-based target membership mechanism then forms the target dandelion. Then, the dandelion angular separation mechanism achieves better inter-category separability, and the dandelion embedding alignment mechanism further aligns both dandelions in a finer manner. To promote intra-category compactness, the discriminating sampled dandelion mechanism is used. Assisted by the intrusion classifier trained using both known and generated unknown intrusion knowledge, a semantic dandelion correction mechanism emphasises easily-confused categories and guides better inter-category separability. Holistically, these mechanisms form the OSDN model that effectively performs intrusion knowledge transfer to benefit IoT intrusion detection. Comprehensive experiments on several intrusion datasets verify the effectiveness of the OSDN model, outperforming three state-of-the-art baseline methods by 16.9%.
Quantum entanglement is a crucial resource in quantum information processing. However, quantifying the entanglement required to prepare quantum states and implement quantum processes remains challenging. This paper proposes computable and faithful lower bounds for the entanglement cost of general quantum states and quantum channels. We introduce the concept of logarithmic $k$-negativity, a generalization of logarithmic negativity, to establish a general lower bound for the entanglement cost of quantum states under quantum operations that completely preserve the positivity of partial transpose (PPT). This bound is efficiently computable via semidefinite programming and is non-zero for any entangled state that is not PPT, making it faithful in the entanglement theory with non-positive partial transpose. Furthermore, we delve into specific and general examples to demonstrate the advantages of our proposed bounds compared with previously known computable ones. Notably, we affirm the irreversibility of asymptotic entanglement manipulation under PPT operations for full-rank entangled states and the irreversibility of channel manipulation for amplitude damping channels. We also establish the best-known lower bound for the entanglement cost of arbitrary dimensional isotropic states. These findings push the boundaries of understanding the structure of entanglement and the fundamental limits of entanglement manipulation.
The introduction of the Segment Anything Model (SAM) has marked a significant advancement in prompt-driven image segmentation. However, SAM's application to medical image segmentation requires manual prompting of target structures to obtain acceptable performance, which is still labor-intensive. Despite attempts of auto-prompting to turn SAM into a fully automatic manner, it still exhibits subpar performance and lacks of reliability in the field of medical imaging. In this paper, we propose UR-SAM, an uncertainty rectified SAM framework to enhance the robustness and reliability for auto-prompting medical image segmentation. Our method incorporates a prompt augmentation module to estimate the distribution of predictions and generate uncertainty maps, and an uncertainty-based rectification module to further enhance the performance of SAM. Extensive experiments on two public 3D medical datasets covering the segmentation of 35 organs demonstrate that without supplementary training or fine-tuning, our method further improves the segmentation performance with up to 10.7 % and 13.8 % in dice similarity coefficient, demonstrating efficiency and broad capabilities for medical image segmentation without manual prompting.
Deep-learning inverse techniques have attracted significant attention in recent years. Among them, the neural adjoint (NA) method, which employs a neural network surrogate simulator, has demonstrated impressive performance in the design tasks of artificial electromagnetic materials (AEM). However, the impact of the surrogate simulators' accuracy on the solutions in the NA method remains uncertain. Furthermore, achieving sufficient optimization becomes challenging in this method when the surrogate simulator is large, and computational resources are limited. Additionally, the behavior under constraints has not been studied, despite its importance from the engineering perspective. In this study, we investigated the impact of surrogate simulators' accuracy on the solutions and discovered that the more accurate the surrogate simulator is, the better the solutions become. We then developed an extension of the NA method, named Neural Lagrangian (NeuLag) method, capable of efficiently optimizing a sufficient number of solution candidates. We then demonstrated that the NeuLag method can find optimal solutions even when handling sufficient candidates is difficult due to the use of a large and accurate surrogate simulator. The resimulation errors of the NeuLag method were approximately 1/50 compared to previous methods for three AEM tasks. Finally, we performed optimization under constraint using NA and NeuLag, and confirmed their potential in optimization with soft or hard constraints. We believe our method holds potential in areas that require large and accurate surrogate simulators.
Magnetic resonance imaging (MRI) is an essential diagnostic tool that suffers from prolonged scan time. To alleviate this limitation, advanced fast MRI technology attracts extensive research interests. Recent deep learning has shown its great potential in improving image quality and reconstruction speed. Faithful coil sensitivity estimation is vital for MRI reconstruction. However, most deep learning methods still rely on pre-estimated sensitivity maps and ignore their inaccuracy, resulting in the significant quality degradation of reconstructed images. In this work, we propose a Joint Deep Sensitivity estimation and Image reconstruction network, called JDSI. During the image artifacts removal, it gradually provides more faithful sensitivity maps with high-frequency information, leading to improved image reconstructions. To understand the behavior of the network, the mutual promotion of sensitivity estimation and image reconstruction is revealed through the visualization of network intermediate results. Results on in vivo datasets and radiologist reader study demonstrate that, for both calibration-based and calibrationless reconstruction, the proposed JDSI achieves the state-of-the-art performance visually and quantitatively, especially when the acceleration factor is high. Additionally, JDSI owns nice robustness to patients and autocalibration signals.
Existing knowledge graph (KG) embedding models have primarily focused on static KGs. However, real-world KGs do not remain static, but rather evolve and grow in tandem with the development of KG applications. Consequently, new facts and previously unseen entities and relations continually emerge, necessitating an embedding model that can quickly learn and transfer new knowledge through growth. Motivated by this, we delve into an expanding field of KG embedding in this paper, i.e., lifelong KG embedding. We consider knowledge transfer and retention of the learning on growing snapshots of a KG without having to learn embeddings from scratch. The proposed model includes a masked KG autoencoder for embedding learning and update, with an embedding transfer strategy to inject the learned knowledge into the new entity and relation embeddings, and an embedding regularization method to avoid catastrophic forgetting. To investigate the impacts of different aspects of KG growth, we construct four datasets to evaluate the performance of lifelong KG embedding. Experimental results show that the proposed model outperforms the state-of-the-art inductive and lifelong embedding baselines.
Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three challenges:(1) word ambiguity, (2) word synonymity, and (3) dynamic contextual dependency. To address these challenges, we propose a novel GNN-based sparse structure learning model for inductive document classification. Specifically, a document-level graph is initially generated by a disjoint union of sentence-level word co-occurrence graphs. Our model collects a set of trainable edges connecting disjoint words between sentences and employs structure learning to sparsely select edges with dynamic contextual dependencies. Graphs with sparse structures can jointly exploit local and global contextual information in documents through GNNs. For inductive learning, the refined document graph is further fed into a general readout function for graph-level classification and optimization in an end-to-end manner. Extensive experiments on several real-world datasets demonstrate that the proposed model outperforms most state-of-the-art results, and reveal the necessity to learn sparse structures for each document.
Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, achieving CIDEr / SPICE / BLEU-4 scores of 117.9, 21.5 and 36.9, respectively. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.
Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, convolutional neural network (CNN) has established itself as a powerful model in segmentation and classification by demonstrating excellent performances. The use of a graphical model such as a conditional random field (CRF) contributes further in capturing contextual information and thus improving the segmentation performance. In this paper, we propose a method to segment hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF. We use multiple spectral cubes to learn deep features using CNN, and then formulate deep CRF with CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between patches consisting of three-dimensional data cubes. Effective piecewise training is applied in order to avoid the computationally expensive iterative CRF inference. Furthermore, we introduce a deep deconvolution network that improves the segmentation masks. We also introduce a new dataset and experimented our proposed method on it along with several widely adopted benchmark datasets to evaluate the effectiveness of our method. By comparing our results with those from several state-of-the-art models, we show the promising potential of our method.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191