arXiv subjects

Shiqi Yang

Publications and source records attributed to Shiqi Yang.

63 records · Page 4Linked to original sources

arXiv2021

Generalized Source-free Domain Adaptation

Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain. Some recent works tackle source-free domain adaptation (SFDA) where only a source pre-trained model is available for adaptation to the target domain. However, those methods do not consider keeping source performance which is of high practical value in real world applications. In this paper, we propose a new domain adaptation paradigm called Generalized Source-free Domain Adaptation (G-SFDA), where the learned model needs to perform well on both the target and source domains, with only access to current unlabeled target data during adaptation. First, we propose local structure clustering (LSC), aiming to cluster the target features with its semantically similar neighbors, which successfully adapts the model to the target domain in the absence of source data. Second, we propose sparse domain attention (SDA), it produces a binary domain specific attention to activate different feature channels for different domains, meanwhile the domain attention will be utilized to regularize the gradient during adaptation to keep source information. In the experiments, for target performance our method is on par with or better than existing DA and SFDA methods, specifically it achieves state-of-the-art performance (85.4%) on VisDA, and our method works well for all domains after adapting to single or multiple target domains. Code is available in https://github.com/Albert0147/G-SFDA.

cs.CV↗

arXiv2021

Optically and magnetically addressable valley pseudospin of interlayer excitons in bilayer MoS2

Interlayer valley excitons in bilayer MoS2 feature concurrently large oscillator strength and long lifetime, and hence represent an advantageous scenario for valleytronic applications. However, control of valley pseudospin of interlayer excitons in pristine bilayer MoS2, which lies at the heart of valleytronics, has remained elusive. Here we report the observation of highly circularly polarized photoluminescence from interlayer excitons of bilayer MoS2 with both optical and magnetic addressability. Under excitation of circularly polarized light near exciton resonance, interlayer excitons of bilayer MoS2 show a near-unity, but negative circular polarization. Significantly, by breaking time-reversal symmetry with an out-of-plane magnetic field, a record level of spontaneous valley polarization (7.7%/Tesla) is identified for interlayer excitons in bilayer MoS2. The giant valley polarization of the interlayer excitons in bilayer MoS2, together with the feasibility of electrical/optical/magnetic control and strong oscillator strength, provides a firm basis for the development of next-generation electronic and optoelectronic applications.

cond-mat.mes-hall↗

arXiv2021

Simple and effective localized attribute representations for zero-shot learning

Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions. Some recent papers have shown the importance of localized features together with fine-tuning the feature extractor to obtain discriminative and transferable features. However, these methods require complex attention or part detection modules to perform explicit localization in the visual space. In contrast, in this paper we propose localizing representations in the semantic/attribute space, with a simple but effective pipeline where localization is implicit. Focusing on attribute representations, we show that our method obtains state-of-the-art performance on CUB and SUN datasets, and also achieves competitive results on AWA2 dataset, outperforming generally more complex methods with explicit localization in the visual space. Our method can be implemented easily, which can be used as a new baseline for zero shot-learning. In addition, our localized representations are highly interpretable as attribute-specific heatmaps.

cs.CV↗

arXiv2021

On Implicit Attribute Localization for Generalized Zero-Shot Learning

Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions. Since attributes are often related to specific parts of objects, many recent works focus on discovering discriminative regions. However, these methods usually require additional complex part detection modules or attention mechanisms. In this paper, 1) we show that common ZSL backbones (without explicit attention nor part detection) can implicitly localize attributes, yet this property is not exploited. 2) Exploiting it, we then propose SELAR, a simple method that further encourages attribute localization, surprisingly achieving very competitive generalized ZSL (GZSL) performance when compared with more complex state-of-the-art methods. Our findings provide useful insight for designing future GZSL methods, and SELAR provides an easy to implement yet strong baseline.

cs.CV↗

arXiv2020

Odd-even layer-number effect and layer-dependent magnetic phase diagrams in MnBi2Te4

The intrinsic magnetic layered topological insulator MnBi2Te4 with nontrivial topological properties and magnetic order has become a promising system for exploring exotic quantum phenomena such as quantum anomalous Hall effect. However, the layer-dependent magnetism of MnBi2Te4, which is fundamental and crucial for further exploration of quantum phenomena in this system, remains elusive. Here, we use polar reflective magnetic circular dichroism spectroscopy, combined with theoretical calculations, to obtain an in-depth understanding of the layer-dependent magnetic properties in MnBi2Te4. The magnetic behavior of MnBi2Te4 exhibits evident odd-even layer-number effect, i.e. the oscillations of the coercivity of the hysteresis loop (at μ0Hc) and the spin-flop transition (at μ0H1), concerning the Zeeman energy and magnetic anisotropy energy. In the even-number septuple layers, an anomalous magnetic hysteresis loop is observed, which is attributed to the thickness-independent surface-related magnetization. Through the linear-chain model, we can clarify the odd-even effect of the spin-flop field and determine the evolution of magnetic states under the external magnetic field. The mean-field method also allows us to trace the experimentally observed magnetic phase diagrams to the magnetic fields, layer numbers and especially, temperature. Overall, by harnessing the unusual layer-dependent magnetic properties, our work paves the way for further study of quantum properties of MnBi2Te4.

cond-mat.mtrl-sci↗

arXiv2019

Scaling-up atomically thin coplanar semiconductor-metal circuitry via phase engineered chemical assembly

Two-dimensional (2D) layered semiconductors, with their ultimate atomic thickness, have shown promise to scale down transistors for modern integrated circuitry. However, the electrical contacts that connect these materials with external bulky metals are usually unsatisfactory, which limits the transistor performance. Recently, contacting 2D semiconductors using coplanar 2D conductors has shown promise in reducing the problematic high resistance contacts. However, many of these methods are not ideal for scaled production. Here, we report on the large-scale, spatially controlled chemical assembly of the integrated 2H-MoTe2 field-effect transistors (FETs) with coplanar metallic 1T' MoTe2 contacts via phase engineered approaches. We demonstrate that the heterophase FETs exhibit ohmic contact behavior with low contact resistance, resulting from the coplanar seamless contact between 2H and 1T' MoTe2 confirmed by transmission electron microscopy characterizations. The average mobility of the heterophase FETs was measured to be as high as 23 cm2 V-1 s-1 (comparable with those of exfoliated single crystals), due to the large 2H MoTe2 single-crystalline domain (486μm). By developing a patterned growth method, we realize the 1T' MoTe2 gated heterophase FET array whose components of channel, gate, and contacts are all 2D materials. Finally, we transfer the heterophase device array onto a flexible substrate and demonstrate the near-infrared photoresponse with high photoresponsivity (~1.02 A/W). Our study provides a basis for the large-scale application of phase-engineered coplanar MoTe2 semiconductors-meter structure in advanced electronics and optoelectronics.

cond-mat.mtrl-sci↗

arXiv2018

Parallel Convolutional Networks for Image Recognition via a Discriminator

In this paper, we introduce a simple but quite effective recognition framework dubbed D-PCN, aiming at enhancing feature extracting ability of CNN. The framework consists of two parallel CNNs, a discriminator and an extra classifier which takes integrated features from parallel networks and gives final prediction. The discriminator is core which drives parallel networks to focus on different regions and learn different representations. The corresponding training strategy is introduced to ensures utilization of discriminator. We validate D-PCN with several CNN models on benchmark datasets: CIFAR-100, and ImageNet, D-PCN enhances all models. In particular it yields state of the art performance on CIFAR-100 compared with related works. We also conduct visualization experiment on fine-grained Stanford Dogs dataset to verify our motivation. Additionally, we apply D-PCN for segmentation on PASCAL VOC 2012 and also find promotion.

cs.CV↗

arXiv2018

Attention to Refine through Multi-Scales for Semantic Segmentation

This paper proposes a novel attention model for semantic segmentation, which aggregates multi-scale and context features to refine prediction. Specifically, the skeleton convolutional neural network framework takes in multiple different scales inputs, by which means the CNN can get representations in different scales. The proposed attention model will handle the features from different scale streams respectively and integrate them. Then location attention branch of the model learns to softly weight the multi-scale features at each pixel location. Moreover, we add an recalibrating branch, parallel to where location attention comes out, to recalibrate the score map per class. We achieve quite competitive results on PASCAL VOC 2012 and ADE20K datasets, which surpass baseline and related works.

cs.CV↗

arXiv2018

D-PCN: Parallel Convolutional Networks for Image Recognition via a Discriminator

In this paper, we introduce a simple but quite effective recognition framework dubbed D-PCN, aiming at enhancing feature extracting ability of CNN. The framework consists of two parallel CNNs, a discriminator and an extra classifier which takes integrated features from parallel networks and gives final prediction. The discriminator is core which drives parallel networks to focus on different regions and learn complementary representations. The corresponding joint training strategy is introduced which ensures the utilization of discriminator. We validate D-PCN with several CNN models on two benchmark datasets: CIFAR-100 and ImageNet32x32, D-PCN enhances all models. In particular it yields state of the art performance on CIFAR-100 compared with related works. We also conduct visualization experiment on fine-grained Stanford Dogs dataset and verify our motivation. Additionally, we apply D-PCN for segmentation on PASCAL VOC 2012 and also find promotion.

cs.CV↗