Search

The anomalous Floquet Anderson insulator (AFAI) has been theoretically predicted in step-wise periodically driven models, but its stability under more general driving protocols hasn't been determined. We show that adding disorder to the anomalous Floquet topological insulator realized with a continuous driving protocol in the experiment by K. Wintersperger et. al., Nat. Phys. $\textbf{16}$, 1058 (2020), supports an AFAI phase, where, for a range of disorder strengths, all the time averaged bulk states become localized, while the pumped charge in a Laughlin pump setup remains quantized., Comment: 5 pages, 4 figures in the main text; 6 pages, 4 figures in the supplement. Comments are welcome

Learning 3D human-object interaction relation is pivotal to embodied AI and interaction modeling. Most existing methods approach the goal by learning to predict isolated interaction elements, e.g., human contact, object affordance, and human-object spatial relation, primarily from the perspective of either the human or the object. Which underexploit certain correlations between the interaction counterparts (human and object), and struggle to address the uncertainty in interactions. Actually, objects' functionalities potentially affect humans' interaction intentions, which reveals what the interaction is. Meanwhile, the interacting humans and objects exhibit matching geometric structures, which presents how to interact. In light of this, we propose harnessing these inherent correlations between interaction counterparts to mitigate the uncertainty and jointly anticipate the above interaction elements in 3D space. To achieve this, we present LEMON (LEarning 3D huMan-Object iNteraction relation), a unified model that mines interaction intentions of the counterparts and employs curvatures to guide the extraction of geometric correlations, combining them to anticipate the interaction elements. Besides, the 3D Interaction Relation dataset (3DIR) is collected to serve as the test bed for training and evaluation. Extensive experiments demonstrate the superiority of LEMON over methods estimating each element in isolation., Comment: accept by CVPR2024

Consistency Models (CMs) have showed a promise in creating visual content efficiently and with high quality. However, the way to add new conditional controls to the pretrained CMs has not been explored. In this technical report, we consider alternative strategies for adding ControlNet-like conditional control to CMs and present three significant findings. 1) ControlNet trained for diffusion models (DMs) can be directly applied to CMs for high-level semantic controls but struggles with low-level detail and realism control. 2) CMs serve as an independent class of generative models, based on which ControlNet can be trained from scratch using Consistency Training proposed by Song et al. 3) A lightweight adapter can be jointly optimized under multiple conditions through Consistency Training, allowing for the swift transfer of DMs-based ControlNet to CMs. We study these three solutions across various conditional controls, including edge, depth, human pose, low-resolution image and masked image with text-to-image latent consistency models., Comment: Project Page: https://swiftforce.github.io/CCM

Adverse weather image restoration strives to recover clear images from those affected by various weather types, such as rain, haze, and snow. Each weather type calls for a tailored degradation removal approach due to its unique impact on images. Conversely, content reconstruction can employ a uniform approach, as the underlying image content remains consistent. Although previous techniques can handle multiple weather types within a single network, they neglect the crucial distinction between these two processes, limiting the quality of restored images. This work introduces a novel adverse weather image restoration method, called DDCNet, which decouples the degradation removal and content reconstruction process at the feature level based on their channel statistics. Specifically, we exploit the unique advantages of the Fourier transform in both these two processes: (1) the degradation information is mainly located in the amplitude component of the Fourier domain, and (2) the Fourier domain contains global information. The former facilitates channel-dependent degradation removal operation, allowing the network to tailor responses to various adverse weather types; the latter, by integrating Fourier's global properties into channel-independent content features, enhances network capacity for consistent global content reconstruction. We further augment the degradation removal process with a degradation mapping loss function. Extensive experiments demonstrate our method achieves state-of-the-art performance in multiple adverse weather removal benchmarks.

This paper presents a new aggregate power tracking control scheme for populations of thermostatically controlled loads (TCLs). The control design is performed in the framework of partial differential equations (PDEs) based on a late-lumping procedure without truncating the infinite-dimensional model describing the dynamics of the TCL population. An input-output linearization control scheme, which is independent of system parameters and uses only partial state measurement, is derived, and a sliding model-like control is applied to achieve finite-time input-to-state stability for tracking error dynamics. Such a control strategy can ensure robust performance in the presence of modeling uncertainties, while considerably reducing the communication burden in large scale distributed systems similar to that considered in the present work. A rigorous analysis of the closed-loop stability of the underlying PDE system was conducted, which guaranteed the validity of the developed control scheme. Simulation studies were performed while considering two TCL populations with a significant difference in their size, and the results show that the developed control scheme performs well in both cases, thereby confirming the effectiveness of the proposed solution., Comment: arXiv admin note: substantial text overlap with arXiv:2305.09118

Change captioning aims to describe the difference between a pair of similar images. Its key challenge is how to learn a stable difference representation under pseudo changes caused by viewpoint change. In this paper, we address this by proposing a self-supervised cross-view representation reconstruction (SCORER) network. Concretely, we first design a multi-head token-wise matching to model relationships between cross-view features from similar/dissimilar images. Then, by maximizing cross-view contrastive alignment of two similar images, SCORER learns two view-invariant image representations in a self-supervised way. Based on these, we reconstruct the representations of unchanged objects by cross-attention, thus learning a stable difference representation for caption generation. Further, we devise a cross-modal backward reasoning to improve the quality of caption. This module reversely models a ``hallucination'' representation with the caption and ``before'' representation. By pushing it closer to the ``after'' representation, we enforce the caption to be informative about the difference in a self-supervised manner. Extensive experiments show our method achieves the state-of-the-art results on four datasets. The code is available at https://github.com/tuyunbin/SCORER., Comment: Accepted by ICCV 2023

Weakly supervised object localization and semantic segmentation aim to localize objects using only image-level labels. Recently, a new paradigm has emerged by generating a foreground prediction map (FPM) to achieve pixel-level localization. While existing FPM-based methods use cross-entropy to evaluate the foreground prediction map and to guide the learning of the generator, this paper presents two astonishing experimental observations on the object localization learning process: For a trained network, as the foreground mask expands, 1) the cross-entropy converges to zero when the foreground mask covers only part of the object region. 2) The activation value continuously increases until the foreground mask expands to the object boundary. Therefore, to achieve a more effective localization performance, we argue for the usage of activation value to learn more object regions. In this paper, we propose a Background Activation Suppression (BAS) method. Specifically, an Activation Map Constraint (AMC) module is designed to facilitate the learning of generator by suppressing the background activation value. Meanwhile, by using foreground region guidance and area constraint, BAS can learn the whole region of the object. In the inference phase, we consider the prediction maps of different categories together to obtain the final localization results. Extensive experiments show that BAS achieves significant and consistent improvement over the baseline methods on the CUB-200-2011 and ILSVRC datasets. In addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets. Code and models are available at https://github.com/wpy1999/BAS-Extension., Comment: Accepted by IJCV. arXiv admin note: text overlap with arXiv:2112.00580

More and more latency-sensitive services and applications are being deployed into the data center. Performance can be limited by the high latency of the network interconnect. Because the conventional network stack is designed not only for LAN, but also for WAN, it carries a great amount of redundancy that is not required in a data center network. This paper introduces the concept of a three-layer protocol stack that can fulfill the exact demands of data center network communications. The detailed design and implementation of the first layer of the stack, which we call RIFL, is presented. A novel low latency in-band hop-by-hop re-transmission protocol is proposed and adopted in RIFL, which guarantees lossless transmission in a data center environment. Experimental results show that RIFL achieves 110 nanoseconds point-to-point latency on 10-meter Active Optical Cables, at a line rate of 112 Gbps. RIFL is a multi-lane protocol with scalable throughput up to multi-hundred gigabits per second. It can be the enabler of low latency, high throughput, flexible, scalable, and lossless data center networks., Comment: 15 pages, 9 figures, journal

The impact of weak disorder and its spatial correlation on the topology of a Floquet system is not well understood so far. In this study, we investigate a model closely related to a two-dimensional Floquet system that has been realized in experiments. In the absence of disorder, we determine the phase diagram and identify a new phase characterized by edge states with alternating chirality in adjacent gaps. When weak disorder is introduced, we examine the disorder-averaged Bott index and analyze why the anomalous Floquet topological insulator is favored by both uncorrelated and correlated disorder, with the latter having a stronger effect. For a system with a ring-shaped gap, the Born approximation fails to explain the topological phase transition, unlike for a system with a point-like gap., Comment: 6+3 pages, 3 + 2 figures

3D Single Object Tracking (SOT) is a fundamental task of computer vision, proving essential for applications like autonomous driving. It remains challenging to localize the target from surroundings due to appearance variations, distractors, and the high sparsity of point clouds. To address these issues, prior Siamese and motion-centric trackers both require elaborate designs and solving multiple subtasks. In this paper, we propose BEVTrack, a simple yet effective baseline method. By estimating the target motion in Bird's-Eye View (BEV) to perform tracking, BEVTrack demonstrates surprising simplicity from various aspects, i.e., network designs, training objectives, and tracking pipeline, while achieving superior performance. Besides, to achieve accurate regression for targets with diverse attributes (e.g., sizes and motion patterns), BEVTrack constructs the likelihood function with the learned underlying distributions adapted to different targets, rather than making a fixed Laplacian or Gaussian assumption as in previous works. This provides valuable priors for tracking and thus further boosts performance. While only using a single regression loss with a plain convolutional architecture, BEVTrack achieves state-of-the-art performance on three large-scale datasets, KITTI, NuScenes, and Waymo Open Dataset while maintaining a high inference speed of about 200 FPS. The code will be released at https://github.com/xmm-prio/BEVTrack., Comment: The code will be released at https://github.com/xmm-prio/BEVTrack

Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new type of tuning method, termed as regularized mask tuning, which masks the network parameters through a learnable selection. Inspired by neural pathways, we argue that the knowledge required by a downstream task already exists in the pre-trained weights but just gets concealed in the upstream pre-training stage. To bring the useful knowledge back into light, we first identify a set of parameters that are important to a given downstream task, then attach a binary mask to each parameter, and finally optimize these masks on the downstream data with the parameters frozen. When updating the mask, we introduce a novel gradient dropout strategy to regularize the parameter selection, in order to prevent the model from forgetting old knowledge and overfitting the downstream data. Experimental results on 11 datasets demonstrate the consistent superiority of our method over previous alternatives. It is noteworthy that we manage to deliver 18.73% performance improvement compared to the zero-shot CLIP via masking an average of only 2.56% parameters. Furthermore, our method is synergistic with most existing parameter-efficient tuning methods and can boost the performance on top of them. Project page can be found here (https://wuw2019.github.io/R-AMT/)., Comment: Accepted at ICCV 2023

The combination of multi-component Bose-Einstein condensates (BECs) and phase imprinting techniques provides an ideal platform for exploring nonlinear dynamics and investigating the quantum transport properties of superfluids. In this paper, we study abundant density structures and corresponding dynamics of phase-separated binary Bose-Einstein condensates with phase-imprinted single vortex or vortex dipole. By adjusting the ratio between the interspecies and intraspecies interactions, and the locations of the phase singularities, the typical density profiles such as ball-shell structures, crescent-gibbous structures, Matryoshka-like structures, sector-sector structures and sandwich-type structures appear, and the phase diagrams are obtained. The dynamics of these structures exhibit diverse properties, including the penetration of vortex dipoles, emergence of half-vortex dipoles, co-rotation of sectors, and oscillation between sectors. The pinning effects induced by a potential defect are also discussed, which is useful for controlling and manipulating individual quantum states.

Recent vision transformers, large-kernel CNNs and MLPs have attained remarkable successes in broad vision tasks thanks to their effective information fusion in the global scope. However, their efficient deployments, especially on mobile devices, still suffer from noteworthy challenges due to the heavy computational costs of self-attention mechanisms, large kernels, or fully connected layers. In this work, we apply conventional convolution theorem to deep learning for addressing this and reveal that adaptive frequency filters can serve as efficient global token mixers. With this insight, we propose Adaptive Frequency Filtering (AFF) token mixer. This neural operator transfers a latent representation to the frequency domain via a Fourier transform and performs semantic-adaptive frequency filtering via an elementwise multiplication, which mathematically equals to a token mixing operation in the original latent space with a dynamic convolution kernel as large as the spatial resolution of this latent representation. We take AFF token mixers as primary neural operators to build a lightweight neural network, dubbed AFFNet. Extensive experiments demonstrate the effectiveness of our proposed AFF token mixer and show that AFFNet achieve superior accuracy and efficiency trade-offs compared to other lightweight network designs on broad visual tasks, including visual recognition and dense prediction tasks., Comment: Accepted by ICCV2023

Low-dimensional ferroelectric tunnel junctions are appealing for the realization of nanoscale nonvolatile memory devices due to their inherent advantage of device miniaturization. Those based on current mechanisms still have restrictions including low tunneling electroresistance (TER) effects and complex heterostructures. Here, we introduce an entirely new TER mechanism to construct the nanotube ferroelectric tunnel junction with ferroelectric nanotubes as the tunneling region. When rolling a ferroelectric monolayer into a nanotube, due to the coexistence of its intrinsic ferroelectric polarization with the flexoelectric polarization induced by bending, there occurs metal-insulator transition depending on radiative polarization states. For the pristine monolayer, its out-of-plane polarization is tunable by an in-plane electric field, the conducting states of the ferroelectric nanotube can thus be tuned between metallic and insulating via axial electric means. Using {\alpha}-In2Se3 as an example, our first-principles density functional theory calculations and nonequilibrium Green's function formalism confirm the feasibility of the TER mechanism and indicate an ultrahigh TER ratio exceeding 9.9*10^10% of the proposed nanotube ferroelectric tunnel junctions. Our findings provide a promising approach based on simple homogeneous structures for high density ferroelectric microelectronic devices with excellent ON/OFF performance., Comment: 15 pages, 5 figures

UV and visible photonics enable applications ranging from spectroscopic sensing to communication and quantum information processing. Photonics structures in these wavelength regimes, however, tend to experience higher loss than their IR counterpart. Particularly in the near-UV band, on-chip optical microresonators have not yet achieved a quality factor beyond 1 million. Here we report ultra-low-loss photonic waveguides and resonators patterned from alumina thin films prepared by a highly scalable atomic layer deposition process. We demonstrate ultra high Q factor of 1.5$\,\times\,$10$^6$ at 390nm, a record value at UV bands, and 1.9$\,\times\,$10$^6$ at 488.5nm.

The explosive growth of rumors with text and images on social media platforms has drawn great attention. Existing studies have made significant contributions to cross-modal information interaction and fusion, but they fail to fully explore hierarchical and complex semantic correlation across different modality content, severely limiting their performance on detecting multi-modal rumor. In this work, we propose a novel knowledge-enhanced hierarchical information correlation learning approach (KhiCL) for multi-modal rumor detection by jointly modeling the basic semantic correlation and high-order knowledge-enhanced entity correlation. Specifically, KhiCL exploits cross-modal joint dictionary to transfer the heterogeneous unimodality features into the common feature space and captures the basic cross-modal semantic consistency and inconsistency by a cross-modal fusion layer. Moreover, considering the description of multi-modal content is narrated around entities, KhiCL extracts visual and textual entities from images and text, and designs a knowledge relevance reasoning strategy to find the shortest semantic relevant path between each pair of entities in external knowledge graph, and absorbs all complementary contextual knowledge of other connected entities in this path for learning knowledge-enhanced entity representations. Furthermore, KhiCL utilizes a signed attention mechanism to model the knowledge-enhanced entity consistency and inconsistency of intra-modality and inter-modality entity pairs by measuring their corresponding semantic relevant distance. Extensive experiments have demonstrated the effectiveness of the proposed method.