arXiv subjects

Tao Xiang

Publications and source records attributed to Tao Xiang.

At least 217 records · Page 12Linked to original sources

arXiv2021

Topology-aware Differential Privacy for Decentralized Image Classification

In this paper, we design Top-DP, a novel solution to optimize the differential privacy protection of decentralized image classification systems. The key insight of our solution is to leverage the unique features of decentralized communication topologies to reduce the noise scale and improve the model usability. (1) We enhance the DP-SGD algorithm with this topology-aware noise reduction strategy, and integrate the time-aware noise decay technique. (2) We design two novel learning protocols (synchronous and asynchronous) to protect systems with different network connectivities and topologies. We formally analyze and prove the DP requirement of our proposed solutions. Experimental evaluations demonstrate that our solution achieves a better trade-off between usability and privacy than prior works. To the best of our knowledge, this is the first DP optimization work from the perspective of network topologies.

cs.CR↗

arXiv2021

Entanglement Entropy of Non-Hermitian Free Fermions

We study the entanglement properties of non-Hermitian free fermionic models with translation symmetry using the correlation matrix technique. Our results show that the entanglement entropy has a logarithmic correction to the area law in both one-dimensional and two-dimensional systems. For any one-dimensional one-band system, we prove that each Fermi point of the system contributes exactly 1/2 to the coefficient c of the logarithmic correction. Moreover, this relation between c and Fermi point is verified for more general one-dimensional and two-dimensional cases by numerical calculations and finite-size scaling analysis. In addition, we also study the single-particle and density-density correlation functions.

cond-mat.mes-hall↗

arXiv2021

Disentangled Lifespan Face Synthesis

A lifespan face synthesis (LFS) model aims to generate a set of photo-realistic face images of a person's whole life, given only one snapshot as reference. The generated face image given a target age code is expected to be age-sensitive reflected by bio-plausible transformations of shape and texture, while being identity preserving. This is extremely challenging because the shape and texture characteristics of a face undergo separate and highly nonlinear transformations w.r.t. age. Most recent LFS models are based on generative adversarial networks (GANs) whereby age code conditional transformations are applied to a latent face representation. They benefit greatly from the recent advancements of GANs. However, without explicitly disentangling their latent representations into the texture, shape and identity factors, they are fundamentally limited in modeling the nonlinear age-related transformation on texture and shape whilst preserving identity. In this work, a novel LFS model is proposed to disentangle the key face characteristics including shape, texture and identity so that the unique shape and texture age transformations can be modeled effectively. This is achieved by extracting shape, texture and identity features separately from an encoder. Critically, two transformation modules, one conditional convolution based and the other channel attention based, are designed for modeling the nonlinear shape and texture feature transformations respectively. This is to accommodate their rather distinct aging processes and ensure that our synthesized images are both age-sensitive and identity preserving. Extensive experiments show that our LFS model is clearly superior to the state-of-the-art alternatives. Codes and demo are available on our project website: \url{https://senhe.github.io/projects/iccv_2021_lifespan_face}.

cs.CV↗

arXiv2021

Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer

A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier (separating foreground and background pixels). Most existing methods meta-learn all three model components for fast adaptation to a new class. However, given that as few as a single support set image is available, effective model adaption of all three components to the new class is extremely challenging. In this work we propose to simplify the meta-learning task by focusing solely on the simplest component, the classifier, whilst leaving the encoder and decoder to pre-training. We hypothesize that if we pre-train an off-the-shelf segmentation model over a set of diverse training classes with sufficient annotations, the encoder and decoder can capture rich discriminative features applicable for any unseen classes, rendering the subsequent meta-learning stage unnecessary. For the classifier meta-learning, we introduce a Classifier Weight Transformer (CWT) designed to dynamically adapt the supportset trained classifier's weights to each query image in an inductive way. Extensive experiments on two standard benchmarks show that despite its simplicity, our method outperforms the state-of-the-art alternatives, often by a large margin.Code is available on https://github.com/zhiheLu/CWT-for-FSS.

cs.CV↗

arXiv2021

Global Aggregation then Local Distribution for Scene Parsing

Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherently limited to model such dependencies due to the naive structure in its building modules (\eg, local convolution kernel). While recent global aggregation methods are beneficial for long-range structure information modelling, they would oversmooth and bring noise to the regions containing fine details (\eg,~boundaries and small objects), which are very much cared for the semantic segmentation task. To alleviate this problem, we propose to explore the local context for making the aggregated long-range relationship being distributed more accurately in local regions. In particular, we design a novel local distribution module which models the affinity map between global and local relationship for each pixel adaptively. Integrating existing global aggregation modules, we show that our approach can be modularized as an end-to-end trainable block and easily plugged into existing semantic segmentation networks, giving rise to the \emph{GALD} networks. Despite its simplicity and versatility, our approach allows us to build new state of the art on major semantic segmentation benchmarks including Cityscapes, ADE20K, Pascal Context, Camvid and COCO-stuff. Code and trained models are released at \url{https://github.com/lxtGH/GALD-DGCNet} to foster further research.

cs.CV↗

arXiv2021

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (ie, without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission.

cs.CV↗

arXiv2021

Long-Time Magnetic Relaxation in Antiferromagnetic Topological Material EuCd$_2$As$_2$

Magnetic topological materials have attracted much attention due to the correlation between topology and magnetism. Recent studies suggest that EuCd$_2$As$_2$ is an antiferromagnetic topological material. Here by carrying out thorough magnetic, electrical and thermodynamic property measurements, we discover a long time relaxation of the magnetic susceptibility in EuCd$_2$As$_2$. The (001) in-plane magnetic susceptibility at 5 K is found to continuously increase up to $\sim$10% over the time of $\sim$14 hours. The magnetic relaxation is anisotropic and strongly depends on the temperature and the applied magnetic field. These results will stimulate further theoretical and experimental studies to understand the origin of the relaxation process and its effect on the electronic structure and physical properties of the magnetic topological materials.

cond-mat.mtrl-sci↗

arXiv2021

Universal quantum transition from superconducting to insulating states in pressurized Bi2Sr2CaCu2O8+δ superconductors

Copper oxide superconductors have continually fascinated the communities of condensed matter physics and material sciences because they host the highest ambient-pressure superconducting transition temperature (Tc) and mysterious physics. Searching for the universal correlation between the superconducting state and its normal state or neighboring ground state is believed to be an effective way for finding clues to elucidate the underlying mechanism of the superconductivity. One of the common pictures for the copper oxide superconductors is that a well-behaved metallic phase will present after the superconductivity is entirely suppressed by chemical doping or application of the magnetic field. Here, we report a different observation of universal quantum transition from superconducting state to insulating-like state under pressure in the under-, optimally- and over-doped Bi2212 superconductors with two CuO2 planes in a unit cell. The same phenomenon has been also found in the Bi2201 superconductor with one CuO2 plane and the Bi2223 superconductor with three CuO2 planes in a unit cell. These results not only provide fresh information but also pose a new challenge for achieving a unified understanding on the underlying physics of the high-Tc superconductivity.

cond-mat.supr-con↗

arXiv2021

Phonon-mediated high-temperature superconductivity in ternary borohydride KB$_2$H$_8$ around 12 GPa

Discovery of high-temperature superconductivity in hydrogen-rich compounds has fuelled the enthusiasm for finding materials with more promising superconducting properties among hydrides. However, the ultrahigh pressure needed to synthesize and maintain high-temperature hydrogen-rich superconductors hinders the experimental investigation of these materials. For practical applications, it is also highly desired to find more hydrogen-rich materials that superconduct at high temperatures but under relatively lower pressures. Based on first-principles density functional theory, we calculate the electronic and phonon band structures for a ternary borohydride formed by intercalating BH$_4$ tetrahedrons into a face-centered-cubic potassium lattice, KB$_2$H$_8$. Remarkably, we find that this material is dynamically stable and one of its $sp^3$-hybridized $σ$-bonding bands is metallized (i.e. partially filled) above a moderate high pressure. This metallized $σ$-bonding band couples strongly with phonons, giving rise to a strong superconducting pairing potential. By solving the anisotropic Eliashberg equations, we predict that the superconducting transition temperature of this compound is 134-146 K around 12 GPa.

cond-mat.supr-con↗

arXiv2021

PEEL: A Provable Removal Attack on Deep Hiding

Deep hiding, embedding images into another using deep neural networks, has shown its great power in increasing the message capacity and robustness. In this paper, we conduct an in-depth study of state-of-the-art deep hiding schemes and analyze their hidden vulnerabilities. Then, according to our observations and analysis, we propose a novel ProvablE rEmovaL attack (PEEL) using image inpainting to remove secret images from containers without any prior knowledge about the deep hiding scheme. We also propose a systemic methodology to improve the efficiency and image quality of PEEL by carefully designing a removal strategy and fully utilizing the visual information of containers. Extensive evaluations show our attacks can completely remove secret images and has negligible impact on the quality of containers.

cs.CR↗

arXiv2021

Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models

Watermarking has become the tendency in protecting the intellectual property of DNN models. Recent works, from the adversary's perspective, attempted to subvert watermarking mechanisms by designing watermark removal attacks. However, these attacks mainly adopted sophisticated fine-tuning techniques, which have certain fatal drawbacks or unrealistic assumptions. In this paper, we propose a novel watermark removal attack from a different perspective. Instead of just fine-tuning the watermarked models, we design a simple yet powerful transformation algorithm by combining imperceptible pattern embedding and spatial-level transformations, which can effectively and blindly destroy the memorization of watermarked models to the watermark samples. We also introduce a lightweight fine-tuning strategy to preserve the model performance. Our solution requires much less resource or knowledge about the watermarking scheme than prior works. Extensive experimental results indicate that our attack can bypass state-of-the-art watermarking solutions with very high success rates. Based on our attack, we propose watermark augmentation techniques to enhance the robustness of existing watermarks.

cs.CR↗

arXiv2021

Observation of nearly identical superconducting transition temperatures in pressurized Weyl semimetal MIrTe4 (M=Nb and Ta)

Here we report the observation of pressure-induced superconductivity in type-II Weyl semimetal (WSM) candidate NbIrTe4 and the evolution of its Hall coefficient (RH), magnetoresistance (MR), and lattice with increasing pressure to ~57 GPa. These results provide a significant opportunity to investigate the universal high-pressure behavior of ternary WSMs, including the sister compound TaIrTe4 that has been known through our previous studies. We find that the pressure-tuned evolution from the WSM to the superconducting (SC) state in these two compounds exhibit the same trend, i.e., a pressure-induced SC state emerges from the matrix of the non-superconducting WSM state at ~ 27 GPa, and then the WSM state and the SC state coexist up to 40 GPa. Above this pressure, an identical high-pressure behavior, characterized by almost the same value of RH and MR in its normal state and the same value of Tc in its SC state, appears in both compounds. Our results not only reveal a universal connection between the WSM state and SC state, but also demonstrate that NbIrTe4 and TaIrTe4 can make the same contribution to the normal and SC states that inhabit in the high-pressure phase, although these two compounds have dramatically different topological band structure at ambient pressure.

cond-mat.supr-con↗

arXiv2021

Learning Generalisable Omni-Scale Representations for Person Re-Identification

An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation. In this paper, we develop novel CNN architectures to address both challenges. First, we present a re-ID CNN termed omni-scale network (OSNet) to learn features that not only capture different spatial scales but also encapsulate a synergistic combination of multiple scales, namely omni-scale features. The basic building block consists of multiple convolutional streams, each detecting features at a certain scale. For omni-scale feature learning, a unified aggregation gate is introduced to dynamically fuse multi-scale features with channel-wise weights. OSNet is lightweight as its building blocks comprise factorised convolutions. Second, to improve generalisable feature learning, we introduce instance normalisation (IN) layers into OSNet to cope with cross-dataset discrepancies. Further, to determine the optimal placements of these IN layers in the architecture, we formulate an efficient differentiable architecture search algorithm. Extensive experiments show that, in the conventional same-dataset setting, OSNet achieves state-of-the-art performance, despite being much smaller than existing re-ID models. In the more challenging yet practical cross-dataset setting, OSNet beats most recent unsupervised domain adaptation methods without using any target data. Our code and models are released at \texttt{https://github.com/KaiyangZhou/deep-person-reid}.

cs.CV↗

arXiv2021

Domain Generalization with MixStyle

Though convolutional neural networks (CNNs) have demonstrated remarkable ability in learning discriminative features, they often generalize poorly to unseen domains. Domain generalization aims to address this problem by learning from a set of source domains a model that is generalizable to any unseen domain. In this paper, a novel approach is proposed based on probabilistically mixing instance-level feature statistics of training samples across source domains. Our method, termed MixStyle, is motivated by the observation that visual domain is closely related to image style (e.g., photo vs.~sketch images). Such style information is captured by the bottom layers of a CNN where our proposed style-mixing takes place. Mixing styles of training instances results in novel domains being synthesized implicitly, which increase the domain diversity of the source domains, and hence the generalizability of the trained model. MixStyle fits into mini-batch training perfectly and is extremely easy to implement. The effectiveness of MixStyle is demonstrated on a wide range of tasks including category classification, instance retrieval and reinforcement learning.

cs.CV↗

arXiv2021

StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval

Sketch-based image retrieval (SBIR) is a cross-modal matching problem which is typically solved by learning a joint embedding space where the semantic content shared between photo and sketch modalities are preserved. However, a fundamental challenge in SBIR has been largely ignored so far, that is, sketches are drawn by humans and considerable style variations exist amongst different users. An effective SBIR model needs to explicitly account for this style diversity, crucially, to generalise to unseen user styles. To this end, a novel style-agnostic SBIR model is proposed. Different from existing models, a cross-modal variational autoencoder (VAE) is employed to explicitly disentangle each sketch into a semantic content part shared with the corresponding photo, and a style part unique to the sketcher. Importantly, to make our model dynamically adaptable to any unseen user styles, we propose to meta-train our cross-modal VAE by adding two style-adaptive components: a set of feature transformation layers to its encoder and a regulariser to the disentangled semantic content latent code. With this meta-learning framework, our model can not only disentangle the cross-modal shared semantic content for SBIR, but can adapt the disentanglement to any unseen user style as well, making the SBIR model truly style-agnostic. Extensive experiments show that our style-agnostic model yields state-of-the-art performance for both category-level and instance-level SBIR.

cs.CV↗

arXiv2021

Cloud2Curve: Generation and Vectorization of Parametric Sketches

Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketches as a sequence of low-dimensional parametric curves. To this end, we propose an inverse graphics framework capable of approximating a raster or waypoint based stroke encoded as a point-cloud with a variable-degree Bézier curve. Building on this module, we present Cloud2Curve, a generative model for scalable high-resolution vector sketches that can be trained end-to-end using point-cloud data alone. As a consequence, our model is also capable of deterministic vectorization which can map novel raster or waypoint based sketches to their corresponding high-resolution scalable Bézier equivalent. We evaluate the generation and vectorization capabilities of our model on Quick, Draw! and K-MNIST datasets.

cs.CV↗

arXiv2021

Few-shot Action Recognition with Prototype-centered Attentive Learning

Few-shot action recognition aims to recognize action classes with few training samples. Most existing methods adopt a meta-learning approach with episodic training. In each episode, the few samples in a meta-training task are split into support and query sets. The former is used to build a classifier, which is then evaluated on the latter using a query-centered loss for model updating. There are however two major limitations: lack of data efficiency due to the query-centered only loss design and inability to deal with the support set outlying samples and inter-class distribution overlapping problems. In this paper, we overcome both limitations by proposing a new Prototype-centered Attentive Learning (PAL) model composed of two novel components. First, a prototype-centered contrastive learning loss is introduced to complement the conventional query-centered learning objective, in order to make full use of the limited training samples in each episode. Second, PAL further integrates a hybrid attentive learning mechanism that can minimize the negative impacts of outliers and promote class separation. Extensive experiments on four standard few-shot action benchmarks show that our method clearly outperforms previous state-of-the-art methods, with the improvement particularly significant (10+\%) on the most challenging fine-grained action recognition benchmark.

cs.CV↗

arXiv2021

Boundary-sensitive Pre-training for Temporal Localization in Videos

Many video analysis tasks require temporal localization thus detection of content changes. However, most existing models developed for these tasks are pre-trained on general video action classification tasks. This is because large scale annotation of temporal boundaries in untrimmed videos is expensive. Therefore no suitable datasets exist for temporal boundary-sensitive pre-training. In this paper for the first time, we investigate model pre-training for temporal localization by introducing a novel boundary-sensitive pretext (BSP) task. Instead of relying on costly manual annotations of temporal boundaries, we propose to synthesize temporal boundaries in existing video action classification datasets. With the synthesized boundaries, BSP can be simply conducted via classifying the boundary types. This enables the learning of video representations that are much more transferable to downstream temporal localization tasks. Extensive experiments show that the proposed BSP is superior and complementary to the existing action classification based pre-training counterpart, and achieves new state-of-the-art performance on several temporal localization tasks.

cs.CV↗