arXiv subjects

Joey Tianyi Zhou

Publications and source records attributed to Joey Tianyi Zhou.

At least 127 records · Page 7Linked to original sources

arXiv2021

Towards Debiasing Temporal Sentence Grounding in Video

The temporal sentence grounding in video (TSGV) task is to locate a temporal moment from an untrimmed video, to match a language query, i.e., a sentence. Without considering bias in moment annotations (e.g., start and end positions in a video), many models tend to capture statistical regularities of the moment annotations, and do not well learn cross-modal reasoning between video and language query. In this paper, we propose two debiasing strategies, data debiasing and model debiasing, to "force" a TSGV model to capture cross-modal interactions. Data debiasing performs data oversampling through video truncation to balance moment temporal distribution in train set. Model debiasing leverages video-only and query-only models to capture the distribution bias, and forces the model to learn cross-modal interactions. Using VSLNet as the base model, we evaluate impact of the two strategies on two datasets that contain out-of-distribution test instances. Results show that both strategies are effective in improving model generalization capability. Equipped with both debiasing strategies, VSLNet achieves best results on both datasets.

cs.CV↗

arXiv2021

Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation

Convolutional neural networks typically perform poorly when the test (target domain) and training (source domain) data have significantly different distributions. While this problem can be mitigated by using the target domain data to align the source and target domain feature representations, the target domain data may be unavailable due to privacy concerns. Consequently, there is a need for methods that generalize well despite restricted access to target domain data during training. In this work, we propose an adversarial semantic hallucination approach (ASH), which combines a class-conditioned hallucination module and a semantic segmentation module. Since the segmentation performance varies across different classes, we design a semantic-conditioned style hallucination module to generate affine transformation parameters from semantic information in the segmentation probability maps of the source domain image. Unlike previous adaptation approaches, which treat all classes equally, ASH considers the class-wise differences. The segmentation module and the hallucination module compete adversarially, with the hallucination module generating increasingly "difficult" stylized images to challenge the segmentation module. In response, the segmentation module improves as it is trained with generated samples at an appropriate class-wise difficulty level. Our results on the Cityscapes and Mapillary benchmark datasets show that our method is competitive with state of the art work. Code is made available at https://github.com/gabriel-tjio/ASH.

cs.CV↗

arXiv2021

Simultaneously Transmitting and Reflecting (STAR) Intelligent Omni-Surfaces, Their Modeling and Implementation

With the rapid development of advanced electromagnetic manipulation technologies, researchers and engineers are starting to study smart surfaces that can achieve enhanced coverages, high reconfigurability, and are easy to deploy. Among these efforts, simultaneously transmitting and reflecting intelligent omni-surface (STAR-IOS) is one of the most promising categories. Although pioneering works have demonstrated the benefits of STAR-IOSs in terms of its wireless communication performance gain, several important issues remain unclear including practical hardware implementations and physics-compliant models for STAR-IOSs. In this paper, we answer these pressing questions of STAR-IOSs by discussing four practical hardware implementations of STAR-IOSs, as well as three hardware modelling methods and five channel modelling methods. These discussions not only categorize existing smart surface technologies but also serve as a physicscompliant pipeline for further investigating the STAR-IOSs.

eess.SP↗

arXiv2021

Automated Deepfake Detection

In this paper, we propose to utilize Automated Machine Learning to adaptively search a neural architecture for deepfake detection. This is the first time to employ automated machine learning for deepfake detection. Based on our explored search space, our proposed method achieves competitive prediction accuracy compared to previous methods. To improve the generalizability of our method, especially when training data and testing data are manipulated by different methods, we propose a simple yet effective strategy in our network learning process: making it to estimate potential manipulation regions besides predicting the real/fake labels. Unlike previous works manually design neural networks, our method can relieve us from the high labor cost in network construction. More than that, compared to previous works, our method depends much less on prior knowledge, e.g., which manipulation method is utilized or where exactly the fake image is manipulated. Extensive experimental results on two benchmark datasets demonstrate the effectiveness of our proposed method for deepfake detection.

cs.CV↗

arXiv2021

Word2Pix: Word to Pixel Cross Attention Transformer in Visual Grounding

Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual feature. Such a formulation does not treat each word of a query sentence on par when modeling language to visual attention, therefore prone to neglect words which are less important for sentence embedding but critical for visual grounding. In this paper we propose Word2Pix: a one-stage visual grounding network based on encoder-decoder transformer architecture that enables learning for textual to visual feature correspondence via word to pixel attention. The embedding of each word from the query sentence is treated alike by attending to visual pixels individually instead of single holistic sentence embedding. In this way, each word is given equivalent opportunity to adjust the language to vision attention towards the referent target through multiple stacks of transformer decoder layers. We conduct the experiments on RefCOCO, RefCOCO+ and RefCOCOg datasets and the proposed Word2Pix outperforms existing one-stage methods by a notable margin. The results obtained also show that Word2Pix surpasses two-stage visual grounding models, while at the same time keeping the merits of one-stage paradigm namely end-to-end training and real-time inference speed intact.

cs.CV↗

arXiv2021

Utility Optimal Thread Assignment and Resource Allocation in Multi-Server Systems

Achieving high performance in many multi-server systems requires finding a good assignment of worker threads to servers and also effectively allocating each server's resources to its assigned threads. The assignment and allocation components of this problem have been studied extensively but largely separately in the literature. In this paper, we introduce the assign and allocate (AA) problem, which seeks to simultaneously find an assignment and allocation that maximizes the total utility of the threads. Assigning and allocating the threads together can result in substantially better overall utility than performing the steps separately, as is traditionally done. We model each thread by a utility function giving its performance as a function of its assigned resources. We first prove that the AA problem is NP-hard. We then present a $2 (\sqrt{2}-1) > 0.828$ factor approximation algorithm for concave utility functions, which runs in $O(mn^2 + n (\log mC)^2)$ time for $n$ threads and $m$ servers with $C$ amount of resources each. We also give a faster algorithm with the same approximation ratio and $O(n (\log mC)^2)$ time complexity. We then extend the problem to two more general settings. First, we consider threads with nonconcave utility functions, and give a 1/2 factor approximation algorithm. Next, we give an algorithm for threads using multiple types of resources, and show the algorithm achieves good empirical performance. We conduct extensive experiments to test the performance of our algorithms on threads with both synthetic and realistic utility functions, and find that they achieve over 92\% of the optimal utility on average. We also compare our algorithms with a number of practical heuristics, and find that our algorithms achieve up to 9 times higher total utility.

cs.DC↗

arXiv2021

Parallel Attention Network with Sequence Matching for Video Grounding

Given a video, video grounding aims to retrieve a temporal moment that semantically corresponds to a language query. In this work, we propose a Parallel Attention Network with Sequence matching (SeqPAN) to address the challenges in this task: multi-modal representation learning, and target moment boundary prediction. We design a self-guided parallel attention module to effectively capture self-modal contexts and cross-modal attentive information between video and text. Inspired by sequence labeling tasks in natural language processing, we split the ground truth moment into begin, inside, and end regions. We then propose a sequence matching strategy to guide start/end boundary predictions using region labels. Experimental results on three datasets show that SeqPAN is superior to state-of-the-art methods. Furthermore, the effectiveness of the self-guided parallel attention module and the sequence matching module is verified.

cs.CL↗

arXiv2021

Video Corpus Moment Retrieval with Contrastive Learning

Given a collection of untrimmed and unsegmented videos, video corpus moment retrieval (VCMR) is to retrieve a temporal moment (i.e., a fraction of a video) that semantically corresponds to a given text query. As video and text are from two distinct feature spaces, there are two general approaches to address VCMR: (i) to separately encode each modality representations, then align the two modality representations for query processing, and (ii) to adopt fine-grained cross-modal interaction to learn multi-modal representations for query processing. While the second approach often leads to better retrieval accuracy, the first approach is far more efficient. In this paper, we propose a Retrieval and Localization Network with Contrastive Learning (ReLoCLNet) for VCMR. We adopt the first approach and introduce two contrastive learning objectives to refine video encoder and text encoder to learn video and text representations separately but with better alignment for VCMR. The video contrastive learning (VideoCL) is to maximize mutual information between query and candidate video at video-level. The frame contrastive learning (FrameCL) aims to highlight the moment region corresponds to the query at frame-level, within a video. Experimental results show that, although ReLoCLNet encodes text and video separately for efficiency, its retrieval accuracy is comparable with baselines adopting cross-modal interaction learning.

cs.CL↗

arXiv2021

Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition

In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition. Unlike previous works focusing on designing specific architectures or loss functions to solve this problem, PASM boosts the network capability by simulating human learning processes: providing updated learning materials and guidance from more capable teachers. Specifically, to generate new learning materials, PASM leverages a point adversarial attack method and a trained teacher network to locate the most informative position related to the target task, generating harder learning samples to refine the network. The searched position is highly adaptive since it considers both the statistical information of each sample and the teacher network capability. Other than being provided new learning materials, the student network also receives guidance from the teacher network. After the student network finishes training, the student network changes its role and acts as a teacher, generating new learning materials and providing stronger guidance to train a better student network. The adaptive learning materials generation and teacher/student update can be conducted more than one time, improving the network capability iteratively. Extensive experimental results validate the efficacy of our method over the existing state of the arts for facial expression recognition.

cs.CV↗

arXiv2021

RCT: Resource Constrained Training for Edge AI

Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devices, but existing training methods for these compact models are designed to run on powerful servers with abundant memory and energy budget. For example, quantisation-aware training (QAT) method involves two copies of model parameters, which is usually beyond the capacity of on-chip memory in edge devices. Data movement between off-chip and on-chip memory is energy demanding as well. The resource requirements are trivial for powerful servers, but critical for edge devices. To mitigate these issues, We propose Resource Constrained Training (RCT). RCT only keeps a quantised model throughout the training, so that the memory requirements for model parameters in training is reduced. It adjusts per-layer bitwidth dynamically in order to save energy when a model can learn effectively with lower precision. We carry out experiments with representative models and tasks in image application and natural language processing. Experiments show that RCT saves more than 86\% energy for General Matrix Multiply (GEMM) and saves more than 46\% memory for model parameters, with limited accuracy loss. Comparing with QAT-based method, RCT saves about half of energy on moving model parameters.

cs.LG↗

arXiv2021

Natural Language Video Localization: A Revisit in Span-based Question Answering Framework

Natural Language Video Localization (NLVL) aims to locate a target moment from an untrimmed video that semantically corresponds to a text query. Existing approaches mainly solve the NLVL problem from the perspective of computer vision by formulating it as ranking, anchor, or regression tasks. These methods suffer from large performance degradation when localizing on long videos. In this work, we address the NLVL from a new perspective, i.e., span-based question answering (QA), by treating the input video as a text passage. We propose a video span localizing network (VSLNet), on top of the standard span-based QA framework (named VSLBase), to address NLVL. VSLNet tackles the differences between NLVL and span-based QA through a simple yet effective query-guided highlighting (QGH) strategy. QGH guides VSLNet to search for the matching video span within a highlighted region. To address the performance degradation on long videos, we further extend VSLNet to VSLNet-L by applying a multi-scale split-and-concatenation strategy. VSLNet-L first splits the untrimmed video into short clip segments; then, it predicts which clip segment contains the target moment and suppresses the importance of other segments. Finally, the clip segments are concatenated, with different confidences, to locate the target moment accurately. Extensive experiments on three benchmark datasets show that the proposed VSLNet and VSLNet-L outperform the state-of-the-art methods; VSLNet-L addresses the issue of performance degradation on long videos. Our study suggests that the span-based QA framework is an effective strategy to solve the NLVL problem.

cs.CL↗

arXiv2021

Trusted Multi-View Classification

Multi-view classification (MVC) generally focuses on improving classification accuracy by using information from different views, typically integrating them into a unified comprehensive representation for downstream tasks. However, it is also crucial to dynamically assess the quality of a view for different samples in order to provide reliable uncertainty estimations, which indicate whether predictions can be trusted. To this end, we propose a novel multi-view classification method, termed trusted multi-view classification, which provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The algorithm jointly utilizes multiple views to promote both classification reliability and robustness by integrating evidence from each view. To achieve this, the Dirichlet distribution is used to model the distribution of the class probabilities, parameterized with evidence from different views and integrated with the Dempster-Shafer theory. The unified learning framework induces accurate uncertainty and accordingly endows the model with both reliability and robustness for out-of-distribution samples. Extensive experimental results validate the effectiveness of the proposed model in accuracy, reliability and robustness.

cs.LG↗

arXiv2021

Deep Learning for Latent Events Forecasting in Twitter Aided Caching Networks

A novel Twitter context aided content caching (TAC) framework is proposed for enhancing the caching efficiency by taking advantage of the legibility and massive volume of Twitter data. For the purpose of promoting the caching efficiency, three machine learning models are proposed to predict latent events and events popularity, utilizing collect Twitter data with geo-tags and geographic information of the adjacent base stations (BSs). Firstly, we propose a latent Dirichlet allocation (LDA) model for latent events forecasting taking advantage of the superiority of the LDA model in natural language processing (NLP). Then, we conceive long short-term memory (LSTM) with skip-gram embedding approach and LSTM with continuous skip-gram-Geo-aware embedding approach for the events popularity forecasting. Lastly, we associate the predicted latent events and the popularity of the events with the caching strategy. Extensive practical experiments demonstrate that: (1) The proposed TAC framework outperforms the conventional caching framework and is capable of being employed in practical applications thanks to the associating ability with public interests. (2) The proposed LDA approach conserves superiority for natural language processing (NLP) in Twitter data. (3) The perplexity of the proposed skip-gram-based LSTM is lower compared with the conventional LDA approach. (4) Evaluation of the model demonstrates that the hit rates of tweets of the model vary from 50% to 65% and the hit rate of the caching contents is up to approximately 75\% with smaller caching space compared to conventional algorithms.

eess.SP↗

arXiv2020

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games

We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language. While different methods have been developed to represent the environment information and language actions, existing RL agents are not empowered with any reasoning capabilities to deal with textual games. In this work, we aim to conduct explicit reasoning with knowledge graphs for decision making, so that the actions of an agent are generated and supported by an interpretable inference procedure. We propose a stacked hierarchical attention mechanism to construct an explicit representation of the reasoning process by exploiting the structure of the knowledge graph. We extensively evaluate our method on a number of man-made benchmark games, and the experimental results demonstrate that our method performs better than existing text-based agents.

cs.LG↗

arXiv2020

Adaptive Precision Training for Resource Constrained Devices

Learn in-situ is a growing trend for Edge AI. Training deep neural network (DNN) on edge devices is challenging because both energy and memory are constrained. Low precision training helps to reduce the energy cost of a single training iteration, but that does not necessarily translate to energy savings for the whole training process, because low precision could slows down the convergence rate. One evidence is that most works for low precision training keep an fp32 copy of the model during training, which in turn imposes memory requirements on edge devices. In this work we propose Adaptive Precision Training. It is able to save both total training energy cost and memory usage at the same time. We use model of the same precision for both forward and backward pass in order to reduce memory usage for training. Through evaluating the progress of training, APT allocates layer-wise precision dynamically so that the model learns quicker for longer time. APT provides an application specific hyper-parameter for users to play trade-off between training energy cost, memory usage and accuracy. Experiment shows that APT achieves more than 50% saving on training energy and memory usage with limited accuracy loss. 20% more savings of training energy and memory usage can be achieved in return for a 1% sacrifice in accuracy loss.

cs.LG↗

arXiv2020

Deep N-ary Error Correcting Output Codes

Ensemble learning consistently improves the performance of multi-class classification through aggregating a series of base classifiers. To this end, data-independent ensemble methods like Error Correcting Output Codes (ECOC) attract increasing attention due to its easiness of implementation and parallelization. Specifically, traditional ECOCs and its general extension N-ary ECOC decompose the original multi-class classification problem into a series of independent simpler classification subproblems. Unfortunately, integrating ECOCs, especially N-ary ECOC with deep neural networks, termed as deep N-ary ECOC, is not straightforward and yet fully exploited in the literature, due to the high expense of training base learners. To facilitate the training of N-ary ECOC with deep learning base learners, we further propose three different variants of parameter sharing architectures for deep N-ary ECOC. To verify the generalization ability of deep N-ary ECOC, we conduct experiments by varying the backbone with different deep neural network architectures for both image and text classification tasks. Furthermore, extensive ablation studies on deep N-ary ECOC show its superior performance over other deep data-independent ensemble methods.

cs.CV↗

arXiv2020

Deep Partial Multi-View Learning

Although multi-view learning has made signifificant progress over the past few decades, it is still challenging due to the diffificulty in modeling complex correlations among different views, especially under the context of view missing. To address the challenge, we propose a novel framework termed Cross Partial Multi-View Networks (CPM-Nets), which aims to fully and flflexibly take advantage of multiple partial views. We fifirst provide a formal defifinition of completeness and versatility for multi-view representation and then theoretically prove the versatility of the learned latent representations. For completeness, the task of learning latent multi-view representation is specififically translated to a degradation process by mimicking data transmission, such that the optimal tradeoff between consistency and complementarity across different views can be implicitly achieved. Equipped with adversarial strategy, our model stably imputes missing views, encoding information from all views for each sample to be encoded into latent representation to further enhance the completeness. Furthermore, a nonparametric classifification loss is introduced to produce structured representations and prevent overfifitting, which endows the algorithm with promising generalization under view-missing cases. Extensive experimental results validate the effectiveness of our algorithm over existing state of the arts for classifification, representation learning and data imputation.

cs.LG↗

arXiv2020

RAIN: A Simple Approach for Robust and Accurate Image Classification Networks

It has been shown that the majority of existing adversarial defense methods achieve robustness at the cost of sacrificing prediction accuracy. The undesirable severe drop in accuracy adversely affects the reliability of machine learning algorithms and prohibits their deployment in realistic applications. This paper aims to address this dilemma by proposing a novel preprocessing framework, which we term Robust and Accurate Image classificatioN(RAIN), to improve the robustness of given CNN classifiers and, at the same time, preserve their high prediction accuracies. RAIN introduces a new randomization-enhancement scheme. It applies randomization over inputs to break the ties between the model forward prediction path and the backward gradient path, thus improving the model robustness. However, similar to existing preprocessing-based methods, the randomized process will degrade the prediction accuracy. To understand why this is the case, we compare the difference between original and processed images, and find it is the loss of high-frequency components in the input image that leads to accuracy drop of the classifier. Based on this finding, RAIN enhances the input's high-frequency details to retain the CNN's high prediction accuracy. Concretely, RAIN consists of two novel randomization modules: randomized small circular shift (RdmSCS) and randomized down-upsampling (RdmDU). The RdmDU module randomly downsamples the input image, and then the RdmSCS module circularly shifts the input image along a randomly chosen direction by a small but random number of pixels. Finally, the RdmDU module performs upsampling with a detail-enhancement model, such as deep super-resolution networks. We conduct extensive experiments on the STL10 and ImageNet datasets to verify the effectiveness of RAIN against various types of adversarial attacks.

cs.CR↗