arXiv subjects

Chang Liu

Publications and source records attributed to Chang Liu.

At least 721 records · Page 40Linked to original sources

arXiv2023

Towards Interactive Image Inpainting via Sketch Refinement

One tough problem of image inpainting is to restore complex structures in the corrupted regions. It motivates interactive image inpainting which leverages additional hints, e.g., sketches, to assist the inpainting process. Sketch is simple and intuitive to end users, but meanwhile has free forms with much randomness. Such randomness may confuse the inpainting models, and incur severe artifacts in completed images. To address this problem, we propose a two-stage image inpainting method termed SketchRefiner. In the first stage, we propose using a cross-correlation loss function to robustly calibrate and refine the user-provided sketches in a coarse-to-fine fashion. In the second stage, we learn to extract informative features from the abstracted sketches in the feature space and modulate the inpainting process. We also propose an algorithm to simulate real sketches automatically and build a test protocol with different applications. Experimental results on public datasets demonstrate that SketchRefiner effectively utilizes sketch information and eliminates the artifacts due to the free-form sketches. Our method consistently outperforms the state-of-the-art ones both qualitatively and quantitatively, meanwhile revealing great potential in real-world applications. Our code and dataset are available.

cs.CV↗

arXiv2023

A novel explicit design method for complex thin-walled structures based on embedded solid moving morphable components

In this article, a novel explicit approach for designing complex thin-walled structures based on the Moving Morphable Component (MMC) method is proposed, which provides a unified framework to systematically address various design issues, including topology optimization, reinforced-rib layout optimization, and sandwich structure design problems. The complexity of thin-walled structures mainly comes from flexible geometries and the variation of thickness. On the one hand, the geometric complexity of thin-walled structures leads to the difficulty in automatically describing material distribution (e.g., reinforced ribs). On the other hand, thin-walled structures with different thicknesses require various hypotheses (e.g., Kirchhoff-Love shell theory and Reissner-Mindlin shell theory) to ensure the precision of structural responses. Whereas for cases that do not fit the shell hypothesis, the precision loss of response solutions is nonnegligible in the optimization process since the accumulation of errors will cause entirely different designs. Hence, the current article proposes a novel embedded solid component to tackle these challenges. The geometric constraints that make the components fit to the curved thin-walled structure are whereby satisfied. Compared with traditional strategies, the proposed method is free from the limit of shell assumptions of structural analysis and can achieve optimized designs with clear load transmission paths at the cost of few design variables and degrees of freedom for finite element analysis (FEA). Finally, we apply the proposed method to several representative examples to demonstrate its effectiveness, efficiency, versatility, and potential to handle complex industrial structures.

cs.GR↗

arXiv2023

Giant nonlocal edge conduction in the axion insulator state of MnBi2Te4

The recently discovered antiferromagnetic (AFM) topological insulator (TI) MnBi2Te4 represents a versatile material platform for exploring exotic topological quantum phenomena in nanoscale devices. It has been proposed that even-septuple-layer (even-SL) MnBi2Te4 can host helical hinge currents with unique nonlocal behavior, but experimental confirmation is still lacking. In this work, we report transport studies of exfoliated MnBi2Te4 flakes with varied thicknesses down to the few-nanometer regime. We observe giant nonlocal transport signals in even-SL devices when the system is in the axion insulator state but vanishingly small nonlocal signal in the odd-SL devices at the same magnetic field range. In conjunction with theoretical calculations, we demonstrate that the nonlocal transport is via the helical edge currents mainly distributed at the hinges between the side and top/bottom surfaces. The helical edge currents in the axion insulator state may find unique applications in topological quantum devices.

cond-mat.mtrl-sci↗

arXiv2023

Towards Predicting Equilibrium Distributions for Molecular Systems with Deep Learning

Advances in deep learning have greatly improved structure prediction of molecules. However, many macroscopic observations that are important for real-world applications are not functions of a single molecular structure, but rather determined from the equilibrium distribution of structures. Traditional methods for obtaining these distributions, such as molecular dynamics simulation, are computationally expensive and often intractable. In this paper, we introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems. Inspired by the annealing process in thermodynamics, DiG employs deep neural networks to transform a simple distribution towards the equilibrium distribution, conditioned on a descriptor of a molecular system, such as a chemical graph or a protein sequence. This framework enables efficient generation of diverse conformations and provides estimations of state densities. We demonstrate the performance of DiG on several molecular tasks, including protein conformation sampling, ligand structure sampling, catalyst-adsorbate sampling, and property-guided structure generation. DiG presents a significant advancement in methodology for statistically understanding molecular systems, opening up new research opportunities in molecular science.

physics.chem-ph↗

arXiv2023

CounTR: Transformer-based Generalised Visual Counting

In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of "exemplars", i.e. zero-shot or few-shot counting. To this end, we make the following four contributions: (1) We introduce a novel transformer-based architecture for generalised visual object counting, termed as Counting Transformer (CounTR), which explicitly capture the similarity between image patches or with given "exemplars" with the attention mechanism;(2) We adopt a two-stage training regime, that first pre-trains the model with self-supervised learning, and followed by supervised fine-tuning;(3) We propose a simple, scalable pipeline for synthesizing training images with a large number of instances or that from different semantic categories, explicitly forcing the model to make use of the given "exemplars";(4) We conduct thorough ablation studies on the large-scale counting benchmark, e.g. FSC-147, and demonstrate state-of-the-art performance on both zero and few-shot settings.

cs.CV↗

arXiv2023

GRES: Generalized Referring Expression Segmentation

Referring Expression Segmentation (RES) aims to generate a segmentation mask for the object described by a given language expression. Existing classic RES datasets and methods commonly support single-target expressions only, i.e., one expression refers to one target object. Multi-target and no-target expressions are not considered. This limits the usage of RES in practice. In this paper, we introduce a new benchmark called Generalized Referring Expression Segmentation (GRES), which extends the classic RES to allow expressions to refer to an arbitrary number of target objects. Towards this, we construct the first large-scale GRES dataset called gRefCOCO that contains multi-target, no-target, and single-target expressions. GRES and gRefCOCO are designed to be well-compatible with RES, facilitating extensive experiments to study the performance gap of the existing RES methods on the GRES task. In the experimental study, we find that one of the big challenges of GRES is complex relationship modeling. Based on this, we propose a region-based GRES baseline ReLA that adaptively divides the image into regions with sub-instance clues, and explicitly models the region-region and region-language dependencies. The proposed approach ReLA achieves new state-of-the-art performance on the both newly proposed GRES and classic RES tasks. The proposed gRefCOCO dataset and method are available at https://henghuiding.github.io/GRES.

cs.CV↗

arXiv2023

Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning

Recent advances in robust semi-supervised learning (SSL) typically filter out-of-distribution (OOD) information at the sample level. We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field. In this paper, we take an initial step to explore and propose a unified framework termed OOD Semantic Pruning (OSP), which aims at pruning OOD semantics out from in-distribution (ID) features. Specifically, (i) we propose an aliasing OOD matching module to pair each ID sample with an OOD sample with semantic overlap. (ii) We design a soft orthogonality regularization, which first transforms each ID feature by suppressing its semantic component that is collinear with paired OOD sample. It then forces the predictions before and after soft orthogonality decomposition to be consistent. Being practically simple, our method shows a strong performance in OOD detection and ID classification on challenging benchmarks. In particular, OSP surpasses the previous state-of-the-art by 13.7% on accuracy for ID classification and 5.9% on AUROC for OOD detection on TinyImageNet dataset. The source codes are publicly available at https://github.com/rain305f/OSP.

cs.CV↗

arXiv2023

More than Classification: A Unified Framework for Event Temporal Relation Extraction

Event temporal relation extraction~(ETRE) is usually formulated as a multi-label classification task, where each type of relation is simply treated as a one-hot label. This formulation ignores the meaning of relations and wipes out their intrinsic dependency. After examining the relation definitions in various ETRE tasks, we observe that all relations can be interpreted using the start and end time points of events. For example, relation \textit{Includes} could be interpreted as event 1 starting no later than event 2 and ending no earlier than event 2. In this paper, we propose a unified event temporal relation extraction framework, which transforms temporal relations into logical expressions of time points and completes the ETRE by predicting the relations between certain time point pairs. Experiments on TB-Dense and MATRES show significant improvements over a strong baseline and outperform the state-of-the-art model by 0.3\% on both datasets. By representing all relations in a unified framework, we can leverage the relations with sufficient data to assist the learning of other relations, thus achieving stable improvement in low-data scenarios. When the relation definitions are changed, our method can quickly adapt to the new ones by simply modifying the logic expressions that map time points to new event relations. The code is released at \url{https://github.com/AndrewZhe/A-Unified-Framework-for-ETRE}.

cs.CL↗

arXiv2023

Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation

We address the problem of referring image segmentation that aims to generate a mask for the object specified by a natural language expression. Many recent works utilize Transformer to extract features for the target object by aggregating the attended visual regions. However, the generic attention mechanism in Transformer only uses the language input for attention weight calculation, which does not explicitly fuse language features in its output. Thus, its output feature is dominated by vision information, which limits the model to comprehensively understand the multi-modal information, and brings uncertainty for the subsequent mask decoder to extract the output mask. To address this issue, we propose Multi-Modal Mutual Attention ($\mathrm{M^3Att}$) and Multi-Modal Mutual Decoder ($\mathrm{M^3Dec}$) that better fuse information from the two input modalities. Based on {$\mathrm{M^3Dec}$}, we further propose Iterative Multi-modal Interaction ($\mathrm{IMI}$) to allow continuous and in-depth interactions between language and vision features. Furthermore, we introduce Language Feature Reconstruction ($\mathrm{LFR}$) to prevent the language information from being lost or distorted in the extracted feature. Extensive experiments show that our proposed approach significantly improves the baseline and outperforms state-of-the-art referring image segmentation methods on RefCOCO series datasets consistently.

cs.CV↗

arXiv2023

Tokenized Graph Transformer with Neighborhood Augmentation for Node Classification in Large Graphs

Graph Transformers, emerging as a new architecture for graph representation learning, suffer from the quadratic complexity on the number of nodes when handling large graphs. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGphormer) that treats each node as a sequence containing a series of tokens constructed by our proposed Hop2Token module. For each node, Hop2Token aggregates the neighborhood features from different hops into different representations, producing a sequence of token vectors as one input. In this way, NAGphormer could be trained in a mini-batch manner and thus could scale to large graphs. Moreover, we mathematically show that compared to a category of advanced Graph Neural Networks (GNNs), called decoupled Graph Convolutional Networks, NAGphormer could learn more informative node representations from multi-hop neighborhoods. In addition, we propose a new data augmentation method called Neighborhood Augmentation (NrAug) based on the output of Hop2Token that augments simultaneously the features of neighborhoods from global as well as local views to strengthen the training effect of NAGphormer. Extensive experiments on benchmark datasets from small to large demonstrate the superiority of NAGphormer against existing graph Transformers and mainstream GNNs, and the effectiveness of NrAug for further boosting NAGphormer.

cs.LG↗

arXiv2023

Integrated Sensing, Navigation, and Communication for Secure UAV Networks with a Mobile Eavesdropper

This paper proposes an integrated sensing, navigation, and communication (ISNC) framework for safeguarding unmanned aerial vehicle (UAV)-enabled wireless networks against a mobile eavesdropping UAV (E-UAV). To cope with the mobility of the E-UAV, the proposed framework advocates the dual use of artificial noise transmitted by the information UAV (I-UAV) for simultaneous jamming and sensing to facilitate navigation and secure communication. In particular, the I-UAV communicates with legitimate downlink ground users, while avoiding potential information leakage by emitting jamming signals, and estimates the state of the E-UAV with an extended Kalman filter based on the backscattered jamming signals. Exploiting the estimated state of the E-UAV in the previous time slot, the I-UAV determines its flight planning strategy, predicts the wiretap channel, and designs its communication resource allocation policy for the next time slot. To circumvent the severe coupling between these three tasks, a divide-and-conquer approach is adopted. The online navigation design has the objective to minimize the distance between the I-UAV and a pre-defined destination point considering kinematic and geometric constraints. Subsequently, given the predicted wiretap channel, the robust resource allocation design is formulated as an optimization problem to achieve the optimal trade-off between sensing and communication in the next time slot, while taking into account the wiretap channel prediction error and the quality-of-service (QoS) requirements of secure communication. Simulation results demonstrate the superior performance of the proposed design compared with baseline schemes and validate the benefits of integrating sensing and navigation into secure UAV communication systems.

cs.IT↗

arXiv2023

On networks of space-based gravitational-wave detectors

The space-based laser interferometers, LISA, Taiji and TianQin, are targeting to observe milliHz gravitational waves (GWs) in the 2030s. The joint observations from multiple space-based detectors yield significant advantages. In this work, we recap the studies and investigations for the joint space-based GW detector networks to highlight: 1) the high precision of sky localization for the massive binary black hole (BBH) coalescences and the GW sirens in the cosmological implication, 2) the effectiveness to test the parity violation in the stochastic GW background observations, 3) the efficiency of subtracting galactic foreground, 4) the improvement in stellar-mass BBH observations. We inspect alternative networks by trading off massive BBH observations and stochastic GW background observation.

gr-qc↗

arXiv2023

Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment

Text-video retrieval is a challenging cross-modal task, which aims to align visual entities with natural language descriptions. Current methods either fail to leverage the local details or are computationally expensive. What's worse, they fail to leverage the heterogeneous concepts in data. In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings. For disentangled conceptualization, we divide the coarse feature into multiple latent factors related to semantic concepts. For set-to-set alignment, where a set of visual concepts correspond to a set of textual concepts, we propose an adaptive pooling method to aggregate semantic concepts to address the partial matching. In particular, since we encode concepts independently in only a few dimensions, DiCoSA is superior at efficiency and granularity, ensuring fine-grained interactions using a similar computational complexity as coarse-grained alignment. Extensive experiments on five datasets, including MSR-VTT, LSMDC, MSVD, ActivityNet, and DiDeMo, demonstrate that our method outperforms the existing state-of-the-art methods.

cs.CV↗

arXiv2023

TG-VQA: Ternary Game of Video Question Answering

Video question answering aims at answering a question about the video content by reasoning the alignment semantics within them. However, since relying heavily on human instructions, i.e., annotations or priors, current contrastive learning-based VideoQA methods remains challenging to perform fine-grained visual-linguistic alignments. In this work, we innovatively resort to game theory, which can simulate complicated relationships among multiple players with specific interaction strategies, e.g., video, question, and answer as ternary players, to achieve fine-grained alignment for VideoQA task. Specifically, we carefully design a VideoQA-specific interaction strategy to tailor the characteristics of VideoQA, which can mathematically generate the fine-grained visual-linguistic alignment label without label-intensive efforts. Our TG-VQA outperforms existing state-of-the-art by a large margin (more than 5%) on long-term and short-term VideoQA datasets, verifying its effectiveness and generalization ability. Thanks to the guidance of game-theoretic interaction, our model impressively convergences well on limited data (${10}^4 ~videos$), surpassing most of those pre-trained on large-scale data ($10^7~videos$).

cs.CV↗

arXiv2023

Scribble-Supervised Target Extraction Method Based on Inner Structure-Constraint for Remote Sensing Images

Weakly supervised learning based on scribble annotations in target extraction of remote sensing images has drawn much interest due to scribbles' flexibility in denoting winding objects and low cost of manually labeling. However, scribbles are too sparse to identify object structure and detailed information, bringing great challenges in target localization and boundary description. To alleviate these problems, in this paper, we construct two inner structure-constraints, a deformation consistency loss and a trainable active contour loss, together with a scribble-constraint to supervise the optimization of the encoder-decoder network without introducing any auxiliary module or extra operation based on prior cues. Comprehensive experiments demonstrate our method's superiority over five state-of-the-art algorithms in this field. Source code is available at https://github.com/yitongli123/ISC-TE.

cs.CV↗

arXiv2023

Integrated Sensing and Communication in Coordinated Cellular Networks

Integrated sensing and communication (ISAC) is a promising technique to provide sensing services in future wireless networks. Numerous existing works have adopted a monostatic radar architecture to realize ISAC, i.e., employing the same base station (BS) to transmit the ISAC signal and receive the echo. Yet, the concurrent information transmission causes unavoidable self-interference (SI) to the radar echo at the BS. To overcome this difficulty, we propose a coordinated cellular network-supported multistatic radar architecture to implement ISAC, which allows us to spatially separate the ISAC signal transmission and radar echo reception, intrinsically circumventing the problem of SI. To this end, we jointly optimize the transmit and receive beamforming policy to minimize the sensing beam pattern mismatch error subject to ISAC quality-of-service requirements. The resulting non-convex optimization problem is tackled by an alternating optimization-based suboptimal algorithm. Simulation results showed that the proposed scheme outperforms the two baseline schemes adopting conventional designs.

cs.IT↗

arXiv2023

Watermarking Text Generated by Black-Box Language Models

LLMs now exhibit human-like skills in various fields, leading to worries about misuse. Thus, detecting generated text is crucial. However, passive detection methods are stuck in domain specificity and limited adversarial robustness. To achieve reliable detection, a watermark-based method was proposed for white-box LLMs, allowing them to embed watermarks during text generation. The method involves randomly dividing the model vocabulary to obtain a special list and adjusting the probability distribution to promote the selection of words in the list. A detection algorithm aware of the list can identify the watermarked text. However, this method is not applicable in many real-world scenarios where only black-box language models are available. For instance, third-parties that develop API-based vertical applications cannot watermark text themselves because API providers only supply generated text and withhold probability distributions to shield their commercial interests. To allow third-parties to autonomously inject watermarks into generated text, we develop a watermarking framework for black-box language model usage scenarios. Specifically, we first define a binary encoding function to compute a random binary encoding corresponding to a word. The encodings computed for non-watermarked text conform to a Bernoulli distribution, wherein the probability of a word representing bit-1 being approximately 0.5. To inject a watermark, we alter the distribution by selectively replacing words representing bit-0 with context-based synonyms that represent bit-1. A statistical test is then used to identify the watermark. Experiments demonstrate the effectiveness of our method on both Chinese and English datasets. Furthermore, results under re-translation, polishing, word deletion, and synonym substitution attacks reveal that it is arduous to remove the watermark without compromising the original semantics.

cs.CL↗

arXiv2023

Hail Mary Pass: Contests with Stochastic Progress

This paper studies the equilibrium behavior in contests with stochastic progress. Participants have access to a safe action that makes progress deterministically, but they can also take risky moves that stochastically influence their progress towards the goal and thus their relative position. In the unique well-behaved Markov perfect equilibrium of this dynamic contest, the follower drops out if the leader establishes a substantial lead, but resorts to "Hail Marys" beforehand: no matter how low the return of the risky move is, the follower undertakes in an attempt to catch up. Moreover, if the risky move has a medium return (between high and low), the leader will also adopt it when the follower is close to dropping out - an interesting preemptive motive. We also examine the impact of such equilibrium behavior on the optimal prize allocation.

econ.TH↗