arXiv subjects

Qi Wu

Publications and source records attributed to Qi Wu.

At least 289 records · Page 16Linked to original sources

arXiv2022

Moderately-Balanced Representation Learning for Treatment Effects with Orthogonality Information

Estimating the average treatment effect (ATE) from observational data is challenging due to selection bias. Existing works mainly tackle this challenge in two ways. Some researchers propose constructing a score function that satisfies the orthogonal condition, which guarantees that the established ATE estimator is "orthogonal" to be more robust. The others explore representation learning models to achieve a balanced representation between the treated and the controlled groups. However, existing studies fail to 1) discriminate treated units from controlled ones in the representation space to avoid the over-balanced issue; 2) fully utilize the "orthogonality information". In this paper, we propose a moderately-balanced representation learning (MBRL) framework based on recent covariates balanced representation learning methods and orthogonal machine learning theory. This framework protects the representation from being over-balanced via multi-task learning. Simultaneously, MBRL incorporates the noise orthogonality information in the training and validation stages to achieve a better ATE estimation. The comprehensive experiments on benchmark and simulated datasets show the superiority and robustness of our method on treatment effect estimations compared with existing state-of-the-art methods.

cs.LG↗

arXiv2022

ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers

Although Transformers have successfully transitioned from their language modelling origins to image-based applications, their quadratic computational complexity remains a challenge, particularly for dense prediction. In this paper we propose a content-based sparse attention method, as an alternative to dense self-attention, aiming to reduce the computation complexity while retaining the ability to model long-range dependencies. Specifically, we cluster and then aggregate key and value tokens, as a content-based method of reducing the total token count. The resulting clustered-token sequence retains the semantic diversity of the original signal, but can be processed at a lower computational cost. Besides, we further extend the clustering-guided attention from single-scale to multi-scale, which is conducive to dense prediction tasks. We label the proposed Transformer architecture ClusTR, and demonstrate that it achieves state-of-the-art performance on various vision tasks but at lower computational cost and with fewer parameters. For instance, our ClusTR small model with 22.7M parameters achieves 83.2\% Top-1 accuracy on ImageNet. Source code and ImageNet models will be made publicly available.

cs.CV↗

arXiv2022

Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution

Deep learning-based single image super-resolution (SISR) approaches have drawn much attention and achieved remarkable success on modern advanced GPUs. However, most state-of-the-art methods require a huge number of parameters, memories, and computational resources, which usually show inferior inference times when applying them to current mobile device CPUs/NPUs. In this paper, we propose a simple plain convolution network with a fast nearest convolution module (NCNet), which is NPU-friendly and can perform a reliable super-resolution in real-time. The proposed nearest convolution has the same performance as the nearest upsampling but is much faster and more suitable for Android NNAPI. Our model can be easily deployed on mobile devices with 8-bit quantization and is fully compatible with all major mobile AI accelerators. Moreover, we conduct comprehensive experiments on different tensor operations on a mobile device to illustrate the efficiency of our network architecture. Our NCNet is trained and validated on the DIV2K 3x dataset, and the comparison with other efficient SR methods demonstrated that the NCNet can achieve high fidelity SR results while using fewer inference times. Our codes and pretrained models are publicly available at \url{https://github.com/Algolzw/NCNet}.

eess.IV↗

arXiv2022

UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barrier

Self-supervised learning (SSL) opens up huge opportunities for medical image analysis that is well known for its lack of annotations. However, aggregating massive (unlabeled) 3D medical images like computerized tomography (CT) remains challenging due to its high imaging cost and privacy restrictions. In this paper, we advocate bringing a wealth of 2D images like chest X-rays as compensation for the lack of 3D data, aiming to build a universal medical self-supervised representation learning framework, called UniMiSS. The following problem is how to break the dimensionality barrier, \ie, making it possible to perform SSL with both 2D and 3D images? To achieve this, we design a pyramid U-like medical Transformer (MiT). It is composed of the switchable patch embedding (SPE) module and Transformers. The SPE module adaptively switches to either 2D or 3D patch embedding, depending on the input dimension. The embedded patches are converted into a sequence regardless of their original dimensions. The Transformers model the long-term dependencies in a sequence-to-sequence manner, thus enabling UniMiSS to learn representations from both 2D and 3D images. With the MiT as the backbone, we perform the UniMiSS in a self-distillation manner. We conduct expensive experiments on six 3D/2D medical image analysis tasks, including segmentation and classification. The results show that the proposed UniMiSS achieves promising performance on various downstream tasks, outperforming the ImageNet pre-training and other advanced SSL counterparts substantially. Code is available at \def\UrlFont{\rm\small\ttfamily} \url{https://github.com/YtongXie/UniMiSS-code}.

cs.CV↗

arXiv2022

Flipping of antiferromagnetic to superconducting states in pressurized quasi-one-dimensional manganese-based compounds

One of the universal features of unconventional superconductors is that the superconducting (SC) state is developed in the proximity of an antiferromagnetic (AFM) state. Understanding the interplay between these two states is one of the key issues to uncover the underlying physics of unconventional SC mechanism. Here, we report a pressure-induced flipping of the AFM state to SC state in the quasi-one-dimensional AMn6Bi5 (A = K, Rb, and Cs) compounds. We find that at a critical pressure the AFM state suddenly disappears at a finite temperature and a SC state simultaneously emerges at a lower temperature without detectable structural changes. Intriguingly, all members of the family present the AFM-SC transition at almost the same critical pressures (Pc), though their ambient-pressure unit-cell volumes vary substantially. Our theoretical calculations indicate that the increasing weight of dxz orbital electrons near Fermi energy under the pressure may be the origin of the flipping. These results reveal a diversity of competing nature between the AFM and SC states among the 3d-transition-metal compounds.

cond-mat.supr-con↗

arXiv2022

Quasi-uniaxial pressure induced superconductivity in stoichiometric compound UTe$_2$

The recent discovery of superconductivity in heavy Fermion compound UTe2, a candidate topological and triplet-paired superconductor, has aroused widespread interest. However, to date, there is no consensus on whether the stoichiometric sample of UTe2 is superconducting or not due to lack of reliable evidence to distinguish the difference between the nominal and real compositions of samples. Here, we are the first to clarify that the stoichiometric UT2 is non-superconducting at ambient pressure and under hydrostatic pressure up to 6 GPa, however we find that it can be compressed into superconductivity by application of quasi-uniaxial pressure. Measurements of resistivity, magnetoresistance and susceptibility reveal that the quasi-uniaxial pressure results in a suppression of the Kondo coherent state seen at ambient pressure, and then leads to a superconductivity initially emerged on the ab-plane at 1.5 GPa. At 4.8 GPa, the superconductivity is developed in three crystallographic directions. The superconducting state coexists with an exotic magnetic ordered state that develops just below the onset temperature of the superconducting transition. The discovery of the quasi-uniaxial-pressure-induced superconductivity with exotic magnetic state in the stoichiometric UTe2 not only provide new understandings on this compound, but also highlight the vital role of Te deficiency in developing the superconductivity at ambient pressures.

cond-mat.supr-con↗

arXiv2022

Optical Field Recovery in Jones Space

Optical full-field recovery makes it possible to compensate for fiber impairments such as chromatic dispersion and polarization mode dispersion (PMD) in the digital signal processing. For cost-sensitive short-reach optical networks, some advanced single-polarization (SP) optical field recovery schemes are recently proposed to avoid chromatic dispersion-induced power fading effect, and improve the spectral efficiency for larger potential capacity. Polarization division multiplexing (PDM) can further double both the spectral efficiency and the system capacity of these SP carrier-assisted direct detection (DD) schemes. However, the so-called polarization fading phenomenon induced by random polarization rotation is a fundamental obstacle which prevents SP carrier-assisted DD systems from polarization diversity. In this paper, we propose a receiver of Jones-space field recovery (JSFR) to realize polarization diversity with SP carrier-assisted DD schemes in Jones space. Different receiver structures and simplified recovery procedures for JSFR are explored theoretically. The proposed JSFR pushes the SP DD schemes towards PDM without extra optical signal-to-noise ratio (OSNR) penalty. In addition, the JSFR shows good tolerance to PMD since the optical field recovery is conducted before polarization recovery. In the concept-of-proof experiment, we demonstrate 448-Gb/s reception over 80-km single-mode fiber using the proposed JSFR based on 22 couplers. Furthermore, we qualitatively compare the optical field recovery in Jones space and Stokes space from the perspective of the modulation dimension. Qualitatively, we compare the optical field recovery in the Jones space and Stokes space from the perspective of the modulation dimension.

eess.SP↗

arXiv2022

BERT-based Financial Sentiment Index and LSTM-based Stock Return Predictability

Traditional sentiment construction in finance relies heavily on the dictionary-based approach, with a few exceptions using simple machine learning techniques such as Naive Bayes classifier. While the current literature has not yet invoked the rapid advancement in the natural language processing, we construct in this research a textual-based sentiment index using a well-known pre-trained model BERT developed by Google, especially for three actively trading individual stocks in Hong Kong market with at the same time the hot discussion on Weibo.com. On the one hand, we demonstrate a significant enhancement of applying BERT in financial sentiment analysis when compared with the existing models. On the other hand, by combining with the other two commonly-used methods when it comes to building the sentiment index in the financial literature, i.e., the option-implied and the market-implied approaches, we propose a more general and comprehensive framework for the financial sentiment analysis, and further provide convincing outcomes for the predictability of individual stock return by combining LSTM (with a feature of a nonlinear mapping). It is significantly distinct with the dominating econometric methods in sentiment influence analysis which are all of a nature of linear regression.

q-fin.ST↗

arXiv2022

Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions

A long-term goal of AI research is to build intelligent agents that can communicate with humans in natural language, perceive the environment, and perform real-world tasks. Vision-and-Language Navigation (VLN) is a fundamental and interdisciplinary research topic towards this goal, and receives increasing attention from natural language processing, computer vision, robotics, and machine learning communities. In this paper, we review contemporary studies in the emerging field of VLN, covering tasks, evaluation metrics, methods, etc. Through structured analysis of current progress and challenges, we highlight the limitations of current VLN and opportunities for future work. This paper serves as a thorough reference for the VLN research community.

cs.CV↗

arXiv2022

Observation of three superconducting transitions in the pressurized CDW-bearing compound TaTe2

Transition metal dichalcogenides host a wide variety of lattice and electronic structures, as well as corresponding exotic physical properties, especially under certain tuning conditions. Here, we are the first to report the observation of pressure-induced three superconducting transitions in TaTe2, a charge density wave (CDW) - bearing layered transition-metal dichalcogenide that is metallic but not superconducting at ambient pressure. We find that its CDW state can be easily suppressed upon increasing pressure up to ~ 1 GPa. A superconducting state then emerges from the suppressed CDW state and persists to the pressure about 7 GPa. Unexpectedly, another superconducting state appears at ~ 11 GPa within the same monoclinic (M) structure of its ambient-pressure one. Upon further compression to 21 GPa, a third superconducting state with higher Tc appears from a high-pressure (HP) phase. Our experimental results suggest that the pressure-induced three superconducting transitions in TaTe2 are respectively driven by the suppression of the CDW state, the change of the angle in the M phase and the transition of M-to-HP phase. These results demonstrate not only the versatile nature of this correlated electron system, but also the first experimental example that shows the pressure-induced evolution from a CDW state to three superconducting states driven by different mechanisms.

cond-mat.supr-con↗

arXiv2022

Custom Sine Waves Are Enough for Imitation Learning of Bipedal Gaits with Different Styles

Not until recently, robust bipedal locomotion has been achieved through reinforcement learning. However, existing implementations rely heavily on insights and efforts from human experts, which is costly for the iterative design of robot systems. Also, styles of the learned motion are strictly limited to that of the reference. In this paper, we propose a new way to learn bipedal locomotion from a simple sine wave as the reference for foot heights. With the naive human insight that the two feet should be lifted up alternatively and periodically, we experimentally demonstrate on the Cassie robot that, a simple reward function is able to make the robot learn to walk end-to-end and efficiently without any explicit knowledge of the model. With custom sine waves, the learned gait pattern can also have customized styles. Codes are released at github.com/WooQi57/sin-cassie-rl.

cs.RO↗

arXiv2022

Attract me to Buy: Advertisement Copywriting Generation with Multimodal Multi-structured Information

Recently, online shopping has gradually become a common way of shopping for people all over the world. Wonderful merchandise advertisements often attract more people to buy. These advertisements properly integrate multimodal multi-structured information of commodities, such as visual spatial information and fine-grained structure information. However, traditional multimodal text generation focuses on the conventional description of what existed and happened, which does not match the requirement of advertisement copywriting in the real world. Because advertisement copywriting has a vivid language style and higher requirements of faithfulness. Unfortunately, there is a lack of reusable evaluation frameworks and a scarcity of datasets. Therefore, we present a dataset, E-MMAD (e-commercial multimodal multi-structured advertisement copywriting), which requires, and supports much more detailed information in text generation. Noticeably, it is one of the largest video captioning datasets in this field. Accordingly, we propose a baseline method and faithfulness evaluation metric on the strength of structured information reasoning to solve the demand in reality on this dataset. It surpasses the previous methods by a large margin on all metrics. The dataset and method are coming soon on \url{https://e-mmad.github.io/e-mmad.net/index.html}.

cs.CL↗

arXiv2022

Diagnosing Vision-and-Language Navigation: What Really Matters

Vision-and-language navigation (VLN) is a multimodal task where an agent follows natural language instructions and navigates in visual environments. Multiple setups have been proposed, and researchers apply new model architectures or training techniques to boost navigation performance. However, there still exist non-negligible gaps between machines' performance and human benchmarks. Moreover, the agents' inner mechanisms for navigation decisions remain unclear. To the best of our knowledge, how the agents perceive the multimodal input is under-studied and needs investigation. In this work, we conduct a series of diagnostic experiments to unveil agents' focus during navigation. Results show that indoor navigation agents refer to both object and direction tokens when making decisions. In contrast, outdoor navigation agents heavily rely on direction tokens and poorly understand the object tokens. Transformer-based agents acquire a better cross-modal understanding of objects and display strong numerical reasoning ability than non-Transformer-based agents. When it comes to vision-and-language alignments, many models claim that they can align object tokens with specific visual targets. We find unbalanced attention on the vision and text input and doubt the reliability of such cross-modal alignments.

cs.CV↗

arXiv2022

BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment

This work addresses the Burst Super-Resolution (BurstSR) task using a new architecture, which requires restoring a high-quality image from a sequence of noisy, misaligned, and low-resolution RAW bursts. To overcome the challenges in BurstSR, we propose a Burst Super-Resolution Transformer (BSRT), which can significantly improve the capability of extracting inter-frame information and reconstruction. To achieve this goal, we propose a Pyramid Flow-Guided Deformable Convolution Network (Pyramid FG-DCN) and incorporate Swin Transformer Blocks and Groups as our main backbone. More specifically, we combine optical flows and deformable convolutions, hence our BSRT can handle misalignment and aggregate the potential texture information in multi-frames more efficiently. In addition, our Transformer-based structure can capture long-range dependency to further improve the performance. The evaluation on both synthetic and real-world tracks demonstrates that our approach achieves a new state-of-the-art in BurstSR task. Further, our BSRT wins the championship in the NTIRE2022 Burst Super-Resolution Challenge.

cs.CV↗

arXiv2022

An Automated FPGA-based Framework for Rapid Prototyping of Nonbinary LDPC Codes

Nonbinary LDPC codes have shown superior performance close to the Shannon limit. Compared to binary LDPC codes of similar lengths, they can reach orders of magnitudes lower error rate. However, multitude of design freedoms of nonbinary LDPC codes complicates the practical code and decoder design process. Fast simulations are critically important to evaluate the pros and cons. Rapid prototyping on FPGA is attractive but takes significant design efforts due to its high design complexity. We propose a high-throughput reconfigurable hardware emulation architecture with decoder and peripheral co-design. The architecture enables a library and script-based framework that automates the construction of FPGA emulations. Code and decoder design parameters are programmed either during run time or by script in design time. We demonstrate the capability of the framework in evaluating practical code and decoder design by experimenting with two popular nonbinary LDPC codes, regular (2, dc) codes and quasi-cyclic codes: each emulation model can be auto-constructed within hours and the decoder delivers excellent error-correcting performance on a Xilinx Virtex-5 FPGA with throughput of up to hundreds of Mbps.

cs.IT↗

arXiv2022

HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation

Pre-training has been adopted in a few of recent works for Vision-and-Language Navigation (VLN). However, previous pre-training methods for VLN either lack the ability to predict future actions or ignore the trajectory contexts, which are essential for a greedy navigation process. In this work, to promote the learning of spatio-temporal visual-textual correspondence as well as the agent's capability of decision making, we propose a novel history-and-order aware pre-training paradigm (HOP) with VLN-specific objectives that exploit the past observations and support future action prediction. Specifically, in addition to the commonly used Masked Language Modeling (MLM) and Trajectory-Instruction Matching (TIM), we design two proxy tasks to model temporal order information: Trajectory Order Modeling (TOM) and Group Order Modeling (GOM). Moreover, our navigation action prediction is also enhanced by introducing the task of Action Prediction with History (APH), which takes into account the history visual perceptions. Extensive experimental results on four downstream VLN tasks (R2R, REVERIE, NDH, RxR) demonstrate the effectiveness of our proposed method compared against several state-of-the-art agents.

cs.CV↗

arXiv2022

MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering

Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding. One limitation of existing solutions is that they capture relevant knowledge from text-only knowledge bases, which merely contain facts expressed by first-order predicates or language descriptions while lacking complex but indispensable multimodal knowledge for visual understanding. How to construct vision-relevant and explainable multimodal knowledge for the VQA scenario has been less studied. In this paper, we propose MuKEA to represent multimodal knowledge by an explicit triplet to correlate visual objects and fact answers with implicit relations. To bridge the heterogeneous gap, we propose three objective losses to learn the triplet representations from complementary views: embedding structure, topological relation and semantic space. By adopting a pre-training and fine-tuning learning strategy, both basic and domain-specific multimodal knowledge are progressively accumulated for answer prediction. We outperform the state-of-the-art by 3.35% and 6.08% respectively on two challenging knowledge-required datasets: OK-VQA and KRVQA. Experimental results prove the complementary benefits of the multimodal knowledge with existing knowledge bases and the advantages of our end-to-end framework over the existing pipeline methods. The code is available at https://github.com/AndersonStra/MuKEA.

cs.CV↗

arXiv2022

Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation

Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments, training agents that cannot generalize across the two. The fundamental difference between the two setups is that discrete navigation assumes prior knowledge of the connectivity graph of the environment, so that the agent can effectively transfer the problem of navigation with low-level controls to jumping from node to node with high-level actions by grounding to an image of a navigable direction. To bridge the discrete-to-continuous gap, we propose a predictor to generate a set of candidate waypoints during navigation, so that agents designed with high-level actions can be transferred to and trained in continuous environments. We refine the connectivity graph of Matterport3D to fit the continuous Habitat-Matterport3D, and train the waypoints predictor with the refined graphs to produce accessible waypoints at each time step. Moreover, we demonstrate that the predicted waypoints can be augmented during training to diversify the views and paths, and therefore enhance agent's generalization ability. Through extensive experiments we show that agents navigating in continuous environments with predicted waypoints perform significantly better than agents using low-level actions, which reduces the absolute discrete-to-continuous gap by 11.76% Success Weighted by Path Length (SPL) for the Cross-Modal Matching Agent and 18.24% SPL for the Recurrent VLN-BERT. Our agents, trained with a simple imitation learning objective, outperform previous methods by a large margin, achieving new state-of-the-art results on the testing environments of the R2R-CE and the RxR-CE datasets.

cs.CV↗