arXiv subjects

Xi Shen

Publications and source records attributed to Xi Shen.

At least 55 records · Page 3Linked to original sources

arXiv2023

Tunable magnetism and electron correlation in Titanium-based Kagome metals RETi3Bi4 (RE = Yb, Pr, and Nd) by rare-earth engineering

Rare-earth engineering is an effective way to introduce and tune the magnetism in topological Kagome magnets, which has been acting as a fertile platform to investigate the quantum interactions between geometry, topology, spin, and correlation. Here we report the structure and properties of three newly discovered Titanium-based Kagome metals RETi3Bi4 (RE = Yb, Pr, and Nd) with various magnetic states. They crystalize in the orthogonal space group Fmmm (No.69), where slightly distorted Ti Kagome lattice, RE triangular lattice, Bi honeycomb and triangular lattices stack along the a axis. By changing the rare earth atoms on RE zag-zig chains, the magnetism can be tuned from nonmagnetic YbTi3Bi4 to short-range ordered PrTi3Bi4 (Tanomaly ~ 8.2 K), and finally to ferromagnetic NdTi3Bi4 (Tc ~ 8.5 K). The measurements of resistivity and specific heat capacity demonstrate an evolution of electron correlation and density of states near the Fermi level with different rare earth atoms. In-situ resistance measurements of NdTi3Bi4 under high pressure further reveal a potential relationship between the electron correlation and ferromagnetic ordering temperature. These results highlight RETi3Bi4 as another family of topological Kagome magnets to explore nontrivial band topology and exotic phases in Kagome materials.

cond-mat.str-el↗

arXiv2023

Explicit Visual Prompting for Universal Foreground Segmentations

Foreground segmentation is a fundamental problem in computer vision, which includes salient object detection, forgery detection, defocus blur detection, shadow detection, and camouflage object detection. Previous works have typically relied on domain-specific solutions to address accuracy and robustness issues in those applications. In this paper, we present a unified framework for a number of foreground segmentation tasks without any task-specific designs. We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP). Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i.e., the features from frozen patch embeddings and high-frequency components. Our method freezes a pre-trained model and then learns task-specific knowledge using a few extra parameters. Despite introducing only a small number of tunable parameters, EVP achieves superior performance than full fine-tuning and other parameter-efficient fine-tuning methods. Experiments in fourteen datasets across five tasks show the proposed method outperforms other task-specific methods while being considerably simple. The proposed method demonstrates the scalability in different architectures, pre-trained weights, and tasks. The code is available at: https://github.com/NiFangBaAGe/Explicit-Visual-Prompt.

cs.CV↗

arXiv2023

Explicit Visual Prompting for Low-Level Structure Segmentations

We consider the generic problem of detecting low-level structures in images, which includes segmenting the manipulated parts, identifying out-of-focus pixels, separating shadow regions, and detecting concealed objects. Whereas each such topic has been typically addressed with a domain-specific solution, we show that a unified approach performs well across all of them. We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP). Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i.e., the features from frozen patch embeddings and the input's high-frequency components. The proposed EVP significantly outperforms other parameter-efficient tuning protocols under the same amount of tunable parameters (5.7% extra trainable parameters of each task). EVP also achieves state-of-the-art performances on diverse low-level structure segmentation tasks compared to task-specific solutions. Our code is available at: https://github.com/NiFangBaAGe/Explicit-Visual-Prompt.

cs.CV↗

arXiv2023

SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Generating talking head videos through a face image and a piece of speech audio still contains many challenges. ie, unnatural head movement, distorted expression, and identity modification. We argue that these issues are mainly because of learning from the coupled 2D motion fields. On the other hand, explicitly using 3D information also suffers problems of stiff expression and incoherent video. We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation. To learn the realistic motion coefficients, we explicitly model the connections between audio and different types of motion coefficients individually. Precisely, we present ExpNet to learn the accurate facial expression from audio by distilling both coefficients and 3D-rendered faces. As for the head pose, we design PoseVAE via a conditional VAE to synthesize head motion in different styles. Finally, the generated 3D motion coefficients are mapped to the unsupervised 3D keypoints space of the proposed face render, and synthesize the final video. We conducted extensive experiments to demonstrate the superiority of our method in terms of motion and video quality.

cs.CV↗

arXiv2023

Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer

The success of Vision Transformer (ViT) in various computer vision tasks has promoted the ever-increasing prevalence of this convolution-free network. The fact that ViT works on image patches makes it potentially relevant to the problem of jigsaw puzzle solving, which is a classical self-supervised task aiming at reordering shuffled sequential image patches back to their natural form. Despite its simplicity, solving jigsaw puzzle has been demonstrated to be helpful for diverse tasks using Convolutional Neural Networks (CNNs), such as self-supervised feature representation learning, domain generalization, and fine-grained classification. In this paper, we explore solving jigsaw puzzle as a self-supervised auxiliary loss in ViT for image classification, named Jigsaw-ViT. We show two modifications that can make Jigsaw-ViT superior to standard ViT: discarding positional embeddings and masking patches randomly. Yet simple, we find that Jigsaw-ViT is able to improve both in generalization and robustness over the standard ViT, which is usually rather a trade-off. Experimentally, we show that adding the jigsaw puzzle branch provides better generalization than ViT on large-scale image classification on ImageNet. Moreover, the auxiliary task also improves robustness to noisy labels on Animal-10N, Food-101N, and Clothing1M as well as adversarial examples. Our implementation is available at https://yingyichen-cyy.github.io/Jigsaw-ViT/.

cs.CV↗

arXiv2022

Ultrafast Image Retrieval from a Holographic Memory Disc for High-Speed Operation of a Shift, Scale, and Rotation Invariant Target Recognition System

The hybrid opto-electronic correlator (HOC) architecture has been shown to be able to detect matches in a shift, scale, and rotation invariant (SSRI) manner by incorporating a polar Mellin transform (PMT) pre-processing step. Here we demonstrate the design and use of a thick holographic memory disc (HMD) for high-speed SSRI correlation employing an HOC. The HMD was written to have 1,320 stored images, including both unprocessed images and their PMTs. We further propose and demonstrate a novel approach whereby the HOC inputs are spatially shifted to produce correlation signals without requiring stabilization of optical phases, yielding results that are in good agreement with the theory. Use of this approach vastly simplifies the design and operation of the HOC, while improving its stability significantly. Finally, a real-time opto-electronic PMT pre-processor utilizing an FPGA is proposed and prototyped, allowing for the automatic conversion of images into their PMTs without additional processing delay.

physics.optics↗

arXiv2022

Back to MLP: A Simple Baseline for Human Motion Prediction

This paper tackles the problem of human motion prediction, consisting in forecasting future body poses from historically observed sequences. State-of-the-art approaches provide good results, however, they rely on deep learning architectures of arbitrary complexity, such as Recurrent Neural Networks(RNN), Transformers or Graph Convolutional Networks(GCN), typically requiring multiple training stages and more than 2 million parameters. In this paper, we show that, after combining with a series of standard practices, such as applying Discrete Cosine Transform(DCT), predicting residual displacement of joints and optimizing velocity as an auxiliary loss, a light-weight network based on multi-layer perceptrons(MLPs) with only 0.14 million parameters can surpass the state-of-the-art performance. An exhaustive evaluation on the Human3.6M, AMASS, and 3DPW datasets shows that our method, named siMLPe, consistently outperforms all other approaches. We hope that our simple method could serve as a strong baseline for the community and allow re-thinking of the human motion prediction problem. The code is publicly available at \url{https://github.com/dulucas/siMLPe}.

cs.CV↗

arXiv2022

Compressing Features for Learning with Noisy Labels

Supervised learning can be viewed as distilling relevant information from input data into feature representations. This process becomes difficult when supervision is noisy as the distilled information might not be relevant. In fact, recent research shows that networks can easily overfit all labels including those that are corrupted, and hence can hardly generalize to clean datasets. In this paper, we focus on the problem of learning with noisy labels and introduce compression inductive bias to network architectures to alleviate this over-fitting problem. More precisely, we revisit one classical regularization named Dropout and its variant Nested Dropout. Dropout can serve as a compression constraint for its feature dropping mechanism, while Nested Dropout further learns ordered feature representations w.r.t. feature importance. Moreover, the trained models with compression regularization are further combined with Co-teaching for performance boost. Theoretically, we conduct bias-variance decomposition of the objective function under compression regularization. We analyze it for both single model and Co-teaching. This decomposition provides three insights: (i) it shows that over-fitting is indeed an issue for learning with noisy labels; (ii) through an information bottleneck formulation, it explains why the proposed feature compression helps in combating label noise; (iii) it gives explanations on the performance boost brought by incorporating compression regularization into Co-teaching. Experiments show that our simple approach can have comparable or even better performance than the state-of-the-art methods on benchmarks with real-world label noise including Clothing1M and ANIMAL-10N. Our implementation is available at https://yingyichen-cyy.github.io/CompressFeatNoisyLabels/.

cs.LG↗

arXiv2022

Learning Co-segmentation by Segment Swapping for Retrieval and Discovery

The goal of this work is to efficiently identify visually similar patterns in images, e.g. identifying an artwork detail copied between an engraving and an oil painting, or recognizing parts of a night-time photograph visible in its daytime counterpart. Lack of training data is a key challenge for this co-segmentation task. We present a simple yet surprisingly effective approach to overcome this difficulty: we generate synthetic training pairs by selecting segments in an image and copy-pasting them into another image. We then learn to predict the repeated region masks. We find that it is crucial to predict the correspondences as an auxiliary task and to use Poisson blending and style transfer on the training pairs to generalize on real data. We analyse results with two deep architectures relevant to our joint image analysis task: a transformer-based architecture and Sparse Nc-Net, a recent network designed to predict coarse correspondences using 4D convolutions. We show our approach provides clear improvements for artwork details retrieval on the Brueghel dataset and achieves competitive performance on two place recognition benchmarks, Tokyo247 and Pitts30K. We also demonstrate the potential of our approach for unsupervised image collection analysis by introducing a spectral graph clustering approach to object discovery and demonstrating it on the object discovery dataset of \cite{rubinstein2013unsupervised} and the Brueghel dataset. Our code and data are available at http://imagine.enpc.fr/~shenx/SegSwap/.

cs.CV↗

arXiv2022

Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut

Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based approach that uses the self-supervised transformer features to discover an object from an image. Visual tokens are viewed as nodes in a weighted graph with edges representing a connectivity score based on the similarity of tokens. Foreground objects can then be segmented using a normalized graph-cut to group self-similar regions. We solve the graph-cut problem using spectral clustering with generalized eigen-decomposition and show that the second smallest eigenvector provides a cutting solution since its absolute value indicates the likelihood that a token belongs to a foreground object. Despite its simplicity, this approach significantly boosts the performance of unsupervised object discovery: we improve over the recent state of the art LOST by a margin of 6.9%, 8.1%, and 8.1% respectively on the VOC07, VOC12, and COCO20K. The performance can be further improved by adding a second stage class-agnostic detector (CAD). Our proposed method can be easily extended to unsupervised saliency detection and weakly supervised object detection. For unsupervised saliency detection, we improve IoU for 4.9%, 5.2%, 12.9% on ECSSD, DUTS, DUT-OMRON respectively compared to previous state of the art. For weakly supervised object detection, we achieve competitive performance on CUB and ImageNet.

cs.CV↗

arXiv2022

A ferrotoroidic candidate with well-separated spin chains

The search of novel quasi one-dimensional (1D) materials is one of the important aspects in the field of material science. Toroidal moment, the order parameter of ferrotoroidic order, can be generated by a head-to-tail configuration of magnetic moment. It has been theoretically proposed that one-dimensional (1D) dimerized and antiferromagnetic-like spin chain hosts ferrotoroidicity and has the toroidal moment composed of only two antiparallel spins. Here, we report a ferrotoroidic candidate of Ba6Cr2S10 with such a theoretical model of spin chain. The structure consists of unique dimerized face-sharing CrS6 octahedral chains along the c axis. An antiferromagnetic-like ordering at ~10 K breaks both space- and time-reversal symmetries and the magnetic point group of mm'2' allows three ferroic orders in Ba6Cr2S10: (anti)ferromagnetic, ferroelectric and ferrotoroidic orders. Our investigation reveals that Ba6Cr2S10 is a rare ferrotoroidic candidate with quasi 1D spin chain, which can be considered as a starting point for the further exploration of the physics and applications of ferrotoroidicity.

cond-mat.str-el↗

arXiv2022

A special cross-tie domain wall in helimagnet

A special cross-tie (SCT) domain wall was discovered in the helimagnet MnCoSi alloy via the magnetic vector field tomography in Lorentz transmission electron microscopy (LTEM). Different to the traditional cross-tie (TCT) domain wall where the convergent/divergent magnetic moment configuration line up one by one, the relative large Bloch type sub-walls emerge in this brand-new SCT domain wall and two mutually perpendicular rotation axes coexist in this special feature. The straight magnetic stripes accompanied with the unraveled domain walls hint the complex mechanism to form this SCT structure. Interestingly, different orientation of this domain wall in LTEM can easily exhibit various magnetic features, including meron/antimeron chains or bimeron strings.

cond-mat.mtrl-sci↗

arXiv2021

The dynamic chirality flips of Skyrmion bubbles

Magnetic skyrmion, a topological magnetic domain with complex non-coplanar spin texture, appears a disk-like structure in two dimensions. Exploring three-dimensional spin texture and related chirality switching has drawn enormous interests from the perspective of fundamental research. Here, the three-dimensional magnetic moment of the skyrmion bubbles in centrosymmetric Mn-Ni-Ga were reconstructed with the vector field tomography approach via Lorentz transmission electron microscopy. The type of the bubbles was determined from investigating the magnetic vectors in entire space. We found that the bubbles switched their chirality easily but still keep the polarity to remain the singularity of the bubbles within the material. Our results offer valuable insights into the fundamental mechanisms underlying the spin chirality flips dynamics of skyrmion bubbles.

cond-mat.mtrl-sci↗

arXiv2021

Scalable massively parallel computing using continuous-time data representation in nanoscale crossbar array

The growth of connected intelligent devices in the Internet of Things has created a pressing need for real-time processing and understanding of large volumes of analogue data. The difficulty in boosting the computing speed renders digital computing unable to meet the demand for processing analogue information that is intrinsically continuous in magnitude and time. By utilizing a continuous data representation in a nanoscale crossbar array, parallel computing can be implemented for the direct processing of analogue information in real time. Here, we propose a scalable massively parallel computing scheme by exploiting a continuous-time data representation and frequency multiplexing in a nanoscale crossbar array. This computing scheme enables the parallel reading of stored data and the one-shot operation of matrix-matrix multiplications in the crossbar array. Furthermore, we achieve the one-shot recognition of 16 letter images based on two physically interconnected crossbar arrays and demonstrate that the processing and modulation of analogue information can be simultaneously performed in a memristive crossbar array.

cond-mat.mtrl-sci↗

arXiv2021

Image Collation: Matching illustrations in manuscripts

Illustrations are an essential transmission instrument. For an historian, the first step in studying their evolution in a corpus of similar manuscripts is to identify which ones correspond to each other. This image collation task is daunting for manuscripts separated by many lost copies, spreading over centuries, which might have been completely re-organized and greatly modified to adapt to novel knowledge or belief and include hundreds of illustrations. Our contributions in this paper are threefold. First, we introduce the task of illustration collation and a large annotated public dataset to evaluate solutions, including 6 manuscripts of 2 different texts with more than 2 000 illustrations and 1 200 annotated correspondences. Second, we analyze state of the art similarity measures for this task and show that they succeed in simple cases but struggle for large manuscripts when the illustrations have undergone very significant changes and are discriminated only by fine details. Finally, we show clear evidence that significant performance boosts can be expected by exploiting cycle-consistent correspondences. Our code and data are available on http://imagine.enpc.fr/~shenx/ImageCollation.

cs.CV↗

arXiv2021

Boosting Co-teaching with Compression Regularization for Label Noise

In this paper, we study the problem of learning image classification models in the presence of label noise. We revisit a simple compression regularization named Nested Dropout. We find that Nested Dropout, though originally proposed to perform fast information retrieval and adaptive data compression, can properly regularize a neural network to combat label noise. Moreover, owing to its simplicity, it can be easily combined with Co-teaching to further boost the performance. Our final model remains simple yet effective: it achieves comparable or even better performance than the state-of-the-art approaches on two real-world datasets with label noise which are Clothing1M and ANIMAL-10N. On Clothing1M, our approach obtains 74.9% accuracy which is slightly better than that of DivideMix. On ANIMAL-10N, we achieve 84.1% accuracy while the best public result by PLC is 83.4%. We hope that our simple approach can be served as a strong baseline for learning with label noise. Our implementation is available at https://github.com/yingyichen-cyy/Nested-Co-teaching.

cs.CV↗

arXiv2020

RANSAC-Flow: generic two-stage image alignment

This paper considers the generic problem of dense alignment between two images, whether they be two frames of a video, two widely different views of a scene, two paintings depicting similar content, etc. Whereas each such task is typically addressed with a domain-specific solution, we show that a simple unsupervised approach performs surprisingly well across a range of tasks. Our main insight is that parametric and non-parametric alignment methods have complementary strengths. We propose a two-stage process: first, a feature-based parametric coarse alignment using one or more homographies, followed by non-parametric fine pixel-wise alignment. Coarse alignment is performed using RANSAC on off-the-shelf deep features. Fine alignment is learned in an unsupervised way by a deep network which optimizes a standard structural similarity metric (SSIM) between the two images, plus cycle-consistency. Despite its simplicity, our method shows competitive results on a range of tasks and datasets, including unsupervised optical flow on KITTI, dense correspondences on Hpatches, two-view geometry estimation on YFCC100M, localization on Aachen Day-Night, and, for the first time, fine alignment of artworks on the Brughel dataset. Our code and data are available at http://imagine.enpc.fr/~shenx/RANSAC-Flow/

cs.CV↗

arXiv2020

Pressure-induced inverse order-disorder transition in double perovskites

Given the consensus that pressure improves cation order in most of known materials, a discovery of pressure-induced disorder could require reconsideration of order-disorder transition in solid state physics/chemistry and geophysics. Double perovskites Y2CoIrO6 and Y2CoRuO6 synthesized at ambient pressure show B-site order, while the polymorphs synthesized at 6 and 15 GPa are partially-ordered and disordered respectively. With the decrease of ordering degrees, the lattices are shrunken and the crystal structures alter from monoclinic to orthorhombic symmetry. Correspondingly, long-range ferrimagnetic order in the B-site ordered phases are gradually overwhelmed by B-site disorder. Theoretical calculations suggest that unusual unit cell compressions under external pressures unexpectedly stabilize the disordered phases of Y2CoIrO6 and Y2CoRuO6.

cond-mat.mtrl-sci↗