arXiv subjects

Zhi Zhang

Publications and source records attributed to Zhi Zhang.

At least 127 records · Page 7Linked to original sources

arXiv2021

Attention in Attention Network for Image Super-Resolution

Convolutional neural networks have allowed remarkable advances in single image super-resolution (SISR) over the last decade. Among recent advances in SISR, attention mechanisms are crucial for high-performance SR models. However, the attention mechanism remains unclear on why and how it works in SISR. In this work, we attempt to quantify and visualize attention mechanisms in SISR and show that not all attention modules are equally beneficial. We then propose attention in attention network (A$^2$N) for more efficient and accurate SISR. Specifically, A$^2$N consists of a non-attention branch and a coupling attention branch. A dynamic attention module is proposed to generate weights for these two branches to suppress unwanted attention adjustments dynamically, where the weights change adaptively according to the input features. This allows attention modules to specialize to beneficial examples without otherwise penalties and thus greatly improve the capacity of the attention network with few parameters overhead. Experimental results demonstrate that our final model A$^2$N could achieve superior trade-off performances comparing with state-of-the-art networks of similar sizes. Codes are available at https://github.com/haoyuc/A2N.

cs.CV↗

arXiv2021

GANSER: A Self-supervised Data Augmentation Framework for EEG-based Emotion Recognition

The data scarcity problem in Electroencephalography (EEG) based affective computing results into difficulty in building an effective model with high accuracy and stability using machine learning algorithms especially deep learning models. Data augmentation has recently achieved considerable performance improvement for deep learning models: increased accuracy, stability, and reduced over-fitting. In this paper, we propose a novel data augmentation framework, namely Generative Adversarial Network-based Self-supervised Data Augmentation (GANSER). As the first to combine adversarial training with self-supervised learning for EEG-based emotion recognition, the proposed framework can generate high-quality and high-diversity simulated EEG samples. In particular, we utilize adversarial training to learn an EEG generator and force the generated EEG signals to approximate the distribution of real samples, ensuring the quality of augmented samples. A transformation function is employed to mask parts of EEG signals and force the generator to synthesize potential EEG signals based on the remaining parts, to produce a wide variety of samples. The masking possibility during transformation is introduced as prior knowledge to guide to extract distinguishable features for simulated EEG signals and generalize the classifier to the augmented sample space. Finally, extensive experiments demonstrate our proposed method can help emotion recognition for performance gain and achieve state-of-the-art results.

cs.LG↗

arXiv2021

CrossNorm and SelfNorm for Generalization under Distribution Shifts

Traditional normalization techniques (e.g., Batch Normalization and Instance Normalization) generally and simplistically assume that training and test data follow the same distribution. As distribution shifts are inevitable in real-world applications, well-trained models with previous normalization methods can perform badly in new environments. Can we develop new normalization methods to improve generalization robustness under distribution shifts? In this paper, we answer the question by proposing CrossNorm and SelfNorm. CrossNorm exchanges channel-wise mean and variance between feature maps to enlarge training distribution, while SelfNorm uses attention to recalibrate the statistics to bridge gaps between training and test distributions. CrossNorm and SelfNorm can complement each other, though exploring different directions in statistics usage. Extensive experiments on different fields (vision and language), tasks (classification and segmentation), settings (supervised and semi-supervised), and distribution shift types (synthetic and natural) show the effectiveness. Code is available at https://github.com/amazon-research/crossnorm-selfnorm

cs.CV↗

arXiv2021

Progressive Coordinate Transforms for Monocular 3D Object Detection

Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment. While significant progress has been achieved with expensive LiDAR point clouds, it poses a great challenge for 3D object detection given only a monocular image. While there exist different alternatives for tackling this problem, it is found that they are either equipped with heavy networks to fuse RGB and depth information or empirically ineffective to process millions of pseudo-LiDAR points. With in-depth examination, we realize that these limitations are rooted in inaccurate object localization. In this paper, we propose a novel and lightweight approach, dubbed {\em Progressive Coordinate Transforms} (PCT) to facilitate learning coordinate representations. Specifically, a localization boosting mechanism with confidence-aware loss is introduced to progressively refine the localization prediction. In addition, semantic image representation is also exploited to compensate for the usage of patch proposals. Despite being lightweight and simple, our strategy leads to superior improvements on the KITTI and Waymo Open Dataset monocular 3D detection benchmarks. At the same time, our proposed PCT shows great generalization to most coordinate-based 3D detection frameworks. The code is available at: https://github.com/amazon-research/progressive-coordinate-transforms .

cs.CV↗

arXiv2021

Video Contrastive Learning with Global Context

Contrastive learning has revolutionized self-supervised image representation learning field, and recently been adapted to video domain. One of the greatest advantages of contrastive learning is that it allows us to flexibly define powerful loss objectives as long as we can find a reasonable way to formulate positive and negative samples to contrast. However, existing approaches rely heavily on the short-range spatiotemporal salience to form clip-level contrastive signals, thus limit themselves from using global context. In this paper, we propose a new video-level contrastive learning method based on segments to formulate positive pairs. Our formulation is able to capture global context in a video, thus robust to temporal content change. We also incorporate a temporal order regularization term to enforce the inherent sequential structure of videos. Extensive experiments show that our video-level contrastive learning framework (VCLR) is able to outperform previous state-of-the-arts on five video datasets for downstream action classification, action localization and video retrieval. Code is available at https://github.com/amazon-research/video-contrastive-learning.

cs.CV↗

arXiv2021

AI Enlightens Wireless Communication: Analyses, Solutions and Opportunities on CSI Feedback

In this paper, we give a systematic description of the 1st Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AI Work Group. Firstly, the framework of full channel state information (F-CSI) feedback problem and its corresponding channel dataset are provided. Then the enhancing schemes for DL-based F-CSI feedback including i) channel data analysis and preprocessing, ii) neural network design and iii) quantization enhancement are elaborated. The final competition results composed of different enhancing schemes are presented. Based on the valuable experience of 1st WAIC, we also list some challenges and potential study areas for the design of AI-based wireless communication systems.

eess.SP↗

arXiv2021

Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things

Federated learning (FL) and split learning (SL) are state-of-the-art distributed machine learning techniques to enable machine learning training without accessing raw data on clients or end devices. However, their \emph{comparative training performance} under real-world resource-restricted Internet of Things (IoT) device settings, e.g., Raspberry Pi, remains barely studied, which, to our knowledge, have not yet been evaluated and compared, rendering inconvenient reference for practitioners. This work firstly provides empirical comparisons of FL and SL in real-world IoT settings regarding (i) learning performance with heterogeneous data distributions and (ii) on-device execution overhead. Our analyses in this work demonstrate that the learning performance of SL is better than FL under an imbalanced data distribution but worse than FL under an extreme non-IID data distribution. Recently, FL and SL are combined to form splitfed learning (SFL) to leverage each of their benefits (e.g., parallel training of FL and lightweight on-device computation requirement of SL). This work then considers FL, SL, and SFL, and mount them on Raspberry Pi devices to evaluate their performance, including training time, communication overhead, power consumption, and memory usage. Besides evaluations, we apply two optimizations. Firstly, we generalize SFL by carefully examining the possibility of a hybrid type of model training at the server-side. The generalized SFL merges sequential (dependent) and parallel (independent) processes of model training and is thus beneficial for a system with large-scaled IoT devices, specifically at the server-side operations. Secondly, we propose pragmatic techniques to substantially reduce the communication overhead by up to four times for the SL and (generalized) SFL.

cs.LG↗

arXiv2020

ResNeSt: Split-Attention Networks

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.

cs.CV↗

arXiv2020

A Comprehensive Study of Deep Video Action Recognition

Video action recognition is one of the representative tasks for video understanding. Over the last decade, we have witnessed great advancements in video action recognition thanks to the emergence of deep learning. But we also encountered new challenges, including modeling long-range temporal information in videos, high computation costs, and incomparable results due to datasets and evaluation protocol variances. In this paper, we provide a comprehensive survey of over 200 existing papers on deep learning for video action recognition. We first introduce the 17 video action recognition datasets that influenced the design of models. Then we present video action recognition models in chronological order: starting with early attempts at adapting deep learning, then to the two-stream networks, followed by the adoption of 3D convolutional kernels, and finally to the recent compute-efficient models. In addition, we benchmark popular methods on several representative datasets and release code for reproducibility. In the end, we discuss open problems and shed light on opportunities for video action recognition to facilitate new research ideas.

cs.CV↗

arXiv2020

AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results

This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020. Common scaling factors for learned video super-resolution (VSR) do not go beyond factor 4. Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details. The task in this challenge is to upscale videos with an extreme factor of 16, which results in more serious degradations that also affect the structural integrity of the videos. A single pixel in the low-resolution (LR) domain corresponds to 256 pixels in the high-resolution (HR) domain. Due to this massive information loss, it is hard to accurately restore the missing information. Track 1 is set up to gauge the state-of-the-art for such a demanding task, where fidelity to the ground truth is measured by PSNR and SSIM. Perceptually higher quality can be achieved in trade-off for fidelity by generating plausible high-frequency content. Track 2 therefore aims at generating visually pleasing results, which are ranked according to human perception, evaluated by a user study. In contrast to single image super-resolution (SISR), VSR can benefit from additional information in the temporal domain. However, this also imposes an additional requirement, as the generated frames need to be consistent along time.

cs.CV↗

arXiv2020

Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review

This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attacker's capability and affected stage of the machine learning pipeline, the attack surfaces are recognized to be wide and then formalized into six categorizations: code poisoning, outsourcing, pretrained, data collection, collaborative learning and post-deployment. Accordingly, attacks under each categorization are combed. The countermeasures are categorized into four general classes: blind backdoor removal, offline backdoor inspection, online backdoor inspection, and post backdoor removal. Accordingly, we review countermeasures, and compare and analyze their advantages and disadvantages. We have also reviewed the flip side of backdoor attacks, which are explored for i) protecting intellectual property of deep learning models, ii) acting as a honeypot to catch adversarial example attacks, and iii) verifying data deletion requested by the data contributor.Overall, the research on defense is far behind the attack, and there is no single defense that can prevent all types of backdoor attacks. In some cases, an attacker can intelligently bypass existing defenses with an adaptive attack. Drawing the insights from the systematic review, we also present key areas for future research on the backdoor, such as empirical security evaluations from physical trigger attacks, and in particular, more efficient and practical countermeasures are solicited.

cs.CR↗

arXiv2020

TeleHammer: A Formal Model of Implicit Rowhammer

The rowhammer bug allows an attacker to gain privilege escalation or steal private data. A key requirement of all existing rowhammer attacks is that an attacker must have access to at least part of an exploitable hammer row. We refer to such rowhammer attacks as PeriHammer. The state-of-the-art software-only defenses against PeriHammer attacks is to make the exploitable hammer rows beyond the attacker's access permission. In this paper, we question the necessity of the above requirement and propose a new class of rowhammer attacks, termed as TeleHammer. It is a paradigm shift in rowhammer attacks since it crosses privilege boundary to stealthily rowhammer an inaccessible row by implicit DRAM accesses. Such accesses are achieved by abusing inherent features of modern hardware and or software. We propose a generic model to rigorously formalize the necessary conditions to initiate TeleHammer and PeriHammer, respectively. Compared to PeriHammer, TeleHammer can defeat the advanced software-only defenses, stealthy in hiding itself and hard to be mitigated. To demonstrate the practicality of TeleHammer and its advantages, we have created a TeleHammer's instance, called PThammer, which leverages the address-translation feature of modern processors. We observe that a memory access from user space can induce a load of a Level-1 page-table entry (L1PTE) from memory and thus hammer the L1PTE once, although L1PTE is not accessible to us. To achieve a high enough hammering frequency, we flush relevant TLB and cache effectively and efficiently. To this end, we demonstrate PThammer on three different test machines and show that it can cross user-kernel boundary and induce the first bit flips in L1PTEs within 15 minutes of double-sided PThammering. We have exploited PThammer to defeat advanced software-only rowhammer defenses in default system setting.

cs.CR↗

arXiv2020

DRAMDig: A Knowledge-assisted Tool to Uncover DRAM Address Mapping

As recently emerged rowhammer exploits require undocumented DRAM address mapping, we propose a generic knowledge-assisted tool, DRAMDig, which takes domain knowledge into consideration to efficiently and deterministically uncover the DRAM address mappings on any Intel-based machines. We test DRAMDig on a number of machines with different combinations of DRAM chips and microarchitectures ranging from Intel Sandy Bridge to Coffee Lake. Comparing to previous works, DRAMDig deterministically reverse-engineered DRAM address mappings on all the test machines with only 7.8 minutes on average. Based on the uncovered mappings, we perform double-sided rowhammer tests and the results show that DRAMDig induced significantly more bit flips than previous works, justifying the correctness of the uncovered DRAM address mappings.

cs.CR↗

arXiv2020

PThammer: Cross-User-Kernel-Boundary Rowhammer through Implicit Accesses

Rowhammer is a hardware vulnerability in DRAM memory, where repeated access to memory can induce bit flips in neighboring memory locations. Being a hardware vulnerability, rowhammer bypasses all of the system memory protection, allowing adversaries to compromise the integrity and confidentiality of data. Rowhammer attacks have shown to enable privilege escalation, sandbox escape, and cryptographic key disclosures. Recently, several proposals suggest exploiting the spatial proximity between the accessed memory location and the location of the bit flip for a defense against rowhammer. These all aim to deny the attacker's permission to access memory locations near sensitive data. In this paper, we question the core assumption underlying these defenses. We present PThammer, a confused-deputy attack that causes accesses to memory locations that the attacker is not allowed to access. Specifically, PThammer exploits the address translation process of modern processors, inducing the processor to generate frequent accesses to protected memory locations. We implement PThammer, demonstrating that it is a viable attack, resulting in a system compromise (e.g., kernel privilege escalation). We further evaluate the effectiveness of proposed software-only defenses showing that PThammer can overcome those.

cs.CR↗

arXiv2020

Calculating the Lyapunov exponents of a piecewise-smooth soft impacting system with a time-delayed feedback controller

Lyapunov exponents are a widely used tool for studying dynamical systems. When calculating Lyapunov exponents for piecewise-smooth systems with time-delayed arguments one faces a lack of continuity in the variational problem. This paper studies how to build a variational equation for the efficient construction of Jacobians along trajectories of the delayed nonsmooth system. Trajectories of the piecewise-smooth system may encounter a so-called grazing event where the trajectory approaches a discontinuity surface in the state space in a non-transversal manner. For this event we develop a grazing point estimation algorithm to ensure the accuracy of trajectories for the nonlinear and the variational equations. We show that the eigenvalues of the Jacobian matrix computed by the algorithm converge with an order consistent with the order of the numerical integration method, therefore guaranteeing the reliability of our proposed numerical method. Finally, the method is demonstrated on a periodically forced impacting oscillator under the time-delayed feedback control.

nlin.CD↗

arXiv2020

Improving Semantic Segmentation via Self-Training

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. We first train a teacher model on labeled data, and then generate pseudo labels on a large set of unlabeled data. Our robust training framework can digest human-annotated and pseudo labels jointly and achieve top performances on Cityscapes, CamVid and KITTI datasets while requiring significantly less supervision. We also demonstrate the effectiveness of self-training on a challenging cross-domain generalization task, outperforming conventional finetuning method by a large margin. Lastly, to alleviate the computational burden caused by the large amount of pseudo labels, we propose a fast training schedule to accelerate the training of segmentation models by up to 2x without performance degradation.

cs.CV↗

arXiv2020

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to facilitate rapid prototyping and promote reproducible research. We also provide modular APIs with flexible building blocks to enable efficient customization. Leveraging the MXNet ecosystem, the deep learning models in GluonCV and GluonNLP can be deployed onto a variety of platforms with different programming languages. The Apache 2.0 license has been adopted by GluonCV and GluonNLP to allow for software distribution, modification, and usage.

cs.LG↗

arXiv2019

Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks

This work corroborates a run-time Trojan detection method exploiting STRong Intentional Perturbation of inputs, is a multi-domain Trojan detection defence across Vision, Text and Audio domains---thus termed as STRIP-ViTA. Specifically, STRIP-ViTA is the first confirmed Trojan detection method that is demonstratively independent of both the task domain and model architectures. We have extensively evaluated the performance of STRIP-ViTA over: i) CIFAR10 and GTSRB datasets using 2D CNNs, and a public third party Trojaned model for vision tasks; ii) IMDB and consumer complaint datasets using both LSTM and 1D CNNs for text tasks; and speech command dataset using both 1D CNNs and 2D CNNs for audio tasks. Experimental results based on 28 tested Trojaned models demonstrate that STRIP-ViTA performs well across all nine architectures and five datasets. In general, STRIP-ViTA can effectively detect Trojan inputs with small false acceptance rate (FAR) with an acceptable preset false rejection rate (FRR). In particular, for vision tasks, we can always achieve a 0% FRR and FAR. By setting FRR to be 3%, average FAR of 1.1% and 3.55% are achieved for text and audio tasks, respectively. Moreover, we have evaluated and shown the effectiveness of STRIP-ViTA against a number of advanced backdoor attacks whilst other state-of-the-art methods lose effectiveness in front of one or all of these advanced backdoor attacks.

cs.CR↗