Search

Change detection aims to identify remote sense object changes by analyzing data between bitemporal image pairs. Due to the large temporal and spatial span of data collection in change detection image pairs, there are often a significant amount of task-specific and task-agnostic noise. Previous effort has focused excessively on denoising, with this goes a great deal of loss of fine-grained information. In this paper, we revisit the importance of fine-grained features in change detection and propose a series of operations for fine-grained information compensation and noise decoupling (FINO). First, the context is utilized to compensate for the fine-grained information in the feature space. Next, a shape-aware and a brightness-aware module are designed to improve the capacity for representation learning. The shape-aware module guides the backbone for more precise shape estimation, guiding the backbone network in extracting object shape features. The brightness-aware module learns a overall brightness estimation to improve the model's robustness to task-agnostic noise. Finally, a task-specific noise decoupling structure is designed as a way to improve the model's ability to separate noise interference from feature similarity. With these training schemes, our proposed method achieves new state-of-the-art (SOTA) results in multiple change detection benchmarks. The code will be made available.

Glass-like objects are widespread in daily life but remain intractable to be segmented for most existing methods. The transparent property makes it difficult to be distinguished from background, while the tiny separation boundary further impedes the acquisition of their exact contour. In this paper, by revealing the key co-evolution demand of semantic and boundary learning, we propose a Selective Mutual Evolution (SME) module to enable the reciprocal feature learning between them. Then to exploit the global shape context, we propose a Structurally Attentive Refinement (SAR) module to conduct a fine-grained feature refinement for those ambiguous points around the boundary. Finally, to further utilize the multi-scale representation, we integrate the above two modules into a cascaded structure and then introduce a Reciprocal Feature Evolution Network (RFENet) for effective glass-like object segmentation. Extensive experiments demonstrate that our RFENet achieves state-of-the-art performance on three popular public datasets., Comment: Accepted by 2023 International Joint Conference on Artificial Intelligence (IJCAI2023)

Recently, density map regression-based methods have dominated in crowd counting owing to their excellent fitting ability on density distribution. However, further improvement tends to saturate mainly because of the confusing background noise and the large density variation. In this paper, we propose a Hierarchically Decoupled Network (HDNet) to solve the above two problems within a unified framework. Specifically, a background classification sub-task is decomposed from the density map prediction task, which is then assigned to a Density Decoupling Module (DDM) to exploit its highly discriminative ability. For the remaining foreground prediction sub-task, it is further hierarchically decomposed to several density-specific sub-tasks by the DDM, which are then solved by the regression-based experts in a Foreground Density Estimation Module (FDEM). Although the proposed strategy effectively reduces the hypothesis space so as to relieve the optimization for those task-specific experts, the high correlation of these sub-tasks are ignored. Therefore, we introduce three types of interaction strategies to unify the whole framework, which are Feature Interaction, Gradient Interaction, and Scale Interaction. Integrated with the above spirits, HDNet achieves state-of-the-art performance on several popular counting benchmarks., Comment: Accepted by IEEE International Conference on Multimedia and Expo (ICME), 2022

Dielectric capacitors are widely used in pulsed power electronic devices due to their ultrahigh power densities and extremely fast charge/discharge speed. To achieve enhanced energy storage density, both maximum polarization (Pmax) and breakdown strength (Eb) need to be improved simultaneously. However, these two key parameters are inversely correlated. In this study, order-disorder transition induced polar nanoregions (PNRs) have been achieved in PbZrO3 thin films by making use of the low-energy ion implantation, enabling us overcome the trade-off between high polarizability and breakdown strength, which leads to the tripling of the energy storage density from 20.5 J/cm3 to 62.3 J/cm3 as well as the great enhancement of breakdown strength. This approach could be extended to other dielectric oxides to improve the energy storage performance, providing a new pathway for tailoring the oxide functionalities.

Weakly supervised object localization (WSOL) aims to learn object localizer solely by using image-level labels. The convolution neural network (CNN) based techniques often result in highlighting the most discriminative part of objects while ignoring the entire object extent. Recently, the transformer architecture has been deployed to WSOL to capture the long-range feature dependencies with self-attention mechanism and multilayer perceptron structure. Nevertheless, transformers lack the locality inductive bias inherent to CNNs and therefore may deteriorate local feature details in WSOL. In this paper, we propose a novel framework built upon the transformer, termed LCTR (Local Continuity TRansformer), which targets at enhancing the local perception capability of global features among long-range feature dependencies. To this end, we propose a relational patch-attention module (RPAM), which considers cross-patch information on a global basis. We further design a cue digging module (CDM), which utilizes local features to guide the learning trend of the model for highlighting the weak local responses. Finally, comprehensive experiments are carried out on two widely used datasets, ie, CUB-200-2011 and ILSVRC, to verify the effectiveness of our method.

Localizing individuals in crowds is more in accordance with the practical demands of subsequent high-level crowd analysis tasks than simply counting. However, existing localization based methods relying on intermediate representations (\textit{i.e.}, density maps or pseudo boxes) serving as learning targets are counter-intuitive and error-prone. In this paper, we propose a purely point-based framework for joint crowd counting and individual localization. For this framework, instead of merely reporting the absolute counting error at image level, we propose a new metric, called density Normalized Average Precision (nAP), to provide more comprehensive and more precise performance evaluation. Moreover, we design an intuitive solution under this framework, which is called Point to Point Network (P2PNet). P2PNet discards superfluous steps and directly predicts a set of point proposals to represent heads in an image, being consistent with the human annotation results. By thorough analysis, we reveal the key step towards implementing such a novel idea is to assign optimal learning targets for these proposals. Therefore, we propose to conduct this crucial association in an one-to-one matching manner using the Hungarian algorithm. The P2PNet not only significantly surpasses state-of-the-art methods on popular counting benchmarks, but also achieves promising localization accuracy. The codes will be available at: https://github.com/TencentYoutuResearch/CrowdCounting-P2PNet., Comment: To be appear in ICCV2021 (Oral)

Recently, the problem of inaccurate learning targets in crowd counting draws increasing attention. Inspired by a few pioneering work, we solve this problem by trying to predict the indices of pre-defined interval bins of counts instead of the count values themselves. However, an inappropriate interval setting might make the count error contributions from different intervals extremely imbalanced, leading to inferior counting performance. Therefore, we propose a novel count interval partition criterion called Uniform Error Partition (UEP), which always keeps the expected counting error contributions equal for all intervals to minimize the prediction risk. Then to mitigate the inevitably introduced discretization errors in the count quantization process, we propose another criterion called Mean Count Proxies (MCP). The MCP criterion selects the best count proxy for each interval to represent its count value during inference, making the overall expected discretization error of an image nearly negligible. As far as we are aware, this work is the first to delve into such a classification task and ends up with a promising solution for count interval partition. Following the above two theoretically demonstrated criterions, we propose a simple yet effective model termed Uniform Error Partition Network (UEPNet), which achieves state-of-the-art performance on several challenging datasets. The codes will be available at: https://github.com/TencentYoutuResearch/CrowdCounting-UEPNet., Comment: To be appear in ICCV2021

Existing Multiple-Object Tracking (MOT) methods either follow the tracking-by-detection paradigm to conduct object detection, feature extraction and data association separately, or have two of the three subtasks integrated to form a partially end-to-end solution. Going beyond these sub-optimal frameworks, we propose a simple online model named Chained-Tracker (CTracker), which naturally integrates all the three subtasks into an end-to-end solution (the first as far as we know). It chains paired bounding boxes regression results estimated from overlapping nodes, of which each node covers two adjacent frames. The paired regression is made attentive by object-attention (brought by a detection module) and identity-attention (ensured by an ID verification module). The two major novelties: chained structure and paired attentive regression, make CTracker simple, fast and effective, setting new MOTA records on MOT16 and MOT17 challenge datasets (67.6 and 66.6, respectively), without relying on any extra training data. The source code of CTracker can be found at: github.com/pjl1995/CTracker., Comment: European Conference on Computer Vision 2020 (Spotlight)

The combination of different exotic properties in materials paves the way for the emergence of their new potential applications. An example is the recently found coexistence of the mutually antagonistic ferromagnetism and superconductivity in hydrogenated boron-doped diamond, which promises to be an attractive system with which to explore unconventional physics. Here, we show the emergence of Yu-Shiba-Rusinov (YSR) bands with a spatial extent of tens of nanometers in ferromagnetic superconducting diamond using scanning tunneling spectroscopy. We demonstrate theoretically how a two-dimensional (2D) spin lattice at the surface of a three-dimensional (3D) superconductor gives rise to the YSR bands, and how their density-of-states profile correlates with the spin lattice structure. The established strategy to realize new forms of the coexistence of ferromagnetism and superconductivity opens a way to engineer the unusual electronic states and also to design better performing superconducting devices., Comment: 13 pages, 5 figures

The topological Hall effect (THE) has been discovered in ultrathin SrRuO3 (SRO) films, where the interface between the SRO layer and another oxide layer breaks the inversion symmetry resulting in the appearance of THE. Thus, THE only occurs in ultra-thin SRO films of several unit cells. In addition to employing a heterostructure, the inversion symmetry can be broken intrinsically in bulk SRO by introducing defects. In this study THE is observed in 60 nm thick SRO films, in which defects and lattice distortions are introduced by helium ion irradiation. The irradiated SRO films exhibit a pronounced THE in a wide temperature range from 5 K to 80 K. These observations can be attributed to the emergence of Dzyaloshinskii-Moriya interaction as a result of artificial inversion symmetry breaking associated to the lattice defect engineering. The creation and control of the THE in oxide single layers can be realized by ex situ film processing. Therefore, this work provides new insights into the THE and illustrates a promising strategy to design novel spintronics devices., Comment: 18 pages, including the suppl. material, to be published at Advanced Electronic Materials

Understanding of the metal-insulator transition (MIT) in correlated transition-metal oxides is a fascinating topic in condensed matter physics and a precise control of such transitions plays a key role in developing novel electronic devices. Here we report an effective tuning of the MIT in epitaxial SrVO3 (SVO) films by expanding the out-of-plane lattice constant without changing in-plane lattice parameters, through helium ion irradiation. Upon increase of the ion fluence, we observe a MIT with a crossover from metallic to insulating state in SVO films. A combination of transport and magnetoresistance measurements in SVO at low temperatures reveals that the observed MIT is mainly ascribed to electron-electron interactions rather than disorder-induced localization. Moreover, these results are well supported by the combination of density functional theory and dynamical mean field theory (DFT+DMFT) calculations, further confirming the decrease of the bandwidth and the enhanced electron-electron interactions resulting from the expansion of out-of-plane lattice constant. These findings provide new insights into the understanding of MIT in correlated oxides and perspectives for the design of unexpected functional devices based on strongly correlated electrons., Comment: 17 pages, 4 figures,submitted to Phys. Rev. Materials

Defect engineering has been a powerful tool to enable the creation of exotic phases and the discovery of intriguing phenomena in ferroelectric oxides. However, accurate control the concentration of defects remains a big challenge. In this work, ion implantation, that can provide controllable point defects, allows us the ability to produce a controlled defect-driven true super-tetragonal (T) phase with enhanced tetragonality in ferroelectric BiFeO3 thin films. This point defect engineering is found to drive the phase transition from the as-grown mixed rhombohedral-like (R) and tetragonal-like (MC) phase to true tetragonal (T) symmetry. By further increasing the injected dose of He ion, we demonstrate an enhanced tetragonality super-tetragonal (super-T) phase with the largest c/a ratio (~ 1.3) that has ever been experimentally achieved in BiFeO3. A combination of morphology change and domain evolution further confirm that the mixed R/MC phase structure transforms to the single-domain-state true tetragonal phase. Moreover, the re-emergence of R phase and in-plane stripe nanodomains after heat treatment reveal the memory effect and reversible phase transition. Our findings demonstrate the control of R-Mc-T-super T symmetry changes and the creation of true T phase BiFeO3 with enhanced tetragonality through controllable defect engineering. This work also provides a pathway to generate large tetragonality (or c/a ratio) that could be extended to other ferroelectric material systems (such as PbTiO3, BaTiO3 and HfO2) which may lead to strong polarization enhancement.

In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively. First, we propose a Feature Enhance Module (FEM) for enhancing the original feature maps to extend the single shot detector to dual shot detector. Second, we adopt Progressive Anchor Loss (PAL) computed by two different sets of anchors to effectively facilitate the features. Third, we use an Improved Anchor Matching (IAM) by integrating novel anchor assign strategy into data augmentation to provide better initialization for the regressor. Since these techniques are all related to the two-stream design, we name the proposed network as Dual Shot Face Detector (DSFD). Extensive experiments on popular benchmarks, WIDER FACE and FDDB, demonstrate the superiority of DSFD over the state-of-the-art face detectors., Comment: Camera-ready version of DSFD for CVPR 2019. Code is available at: https://github.com/TencentYoutuResearch/FaceDetection-DSFD

Exchange bias stems from the interaction between different magnetic phases and therefore it generally occurs in magnetic multilayers. Here we present a large exchange bias in a single SrRuO3 layer induced by helium ion irradiation. When the fluence increases, the induced defects not only suppress the magnetization and the Curie temperature, but also drive a metal-insulator transition at a low temperature. In particular, a large exchange bias field up to around 0.36 T can be created by the irradiation. This large exchange bias is related to the coexistence of different magnetic and structural phases that are introduced by embedded defects. Our work demonstrates that spintronic properties in complex oxides can be created and enhanced by applying ion irradiation., Comment: 14 pages, 5 figures

The rare-earth nickelates are a rich playground for transport properties, known to host non-Fermi liquid character, resistance saturation and metal-insulator transitions. We report a study of transport in LaNiO3 in the presence of tunable disorder induced by irradiation. While pristine LaNiO3 samples are metallic, highly irradiated samples show insulating behaviour at all temperatures. Using irradiation fluence as a tuning handle, we uncover an intermediate region hosting a metal-insulator transition. This transition falls within the Mott-Ioffe-Regel regime wherein the mean free path is comparable to lattice spacing. In the high temperature metallic regime, we find a transition from non-Fermi liquid to a Fermi-liquid-like character. On the insulating side of the metal-insulator transition, we find behaviour that is consistent with weak localization. This is reflected in magnetoresistance that scales with the square of the field and in resistivity. In the highly irradiated insulating samples, we find good agreement with variable range hopping, consistent with Anderson localization. We find qualitatively similar behaviour in thick PrNiO3 films as well. Our results demonstrate that ion irradiation can be used to tailor transport, serving as an excellent tool to study the physics of localization., Comment: 14 pages, 4 figures

Oxide heterostructures exhibit a rich variety of magnetic and transport properties which arise due to contact at an interface. This can lead to surprising effects that are very different from the bulk properties of the materials involved. We report the magnetic properties of bilayers of SrRuO3, a well known ferromagnet, and CaRuO3, which is nominally a paramagnet. We find intriguing features that are consistent with CaRuO3 developing dual magnetic character, with both a net moment as well as antiferromagnetic order. We argue the ordered SrRuO3 layer induces an undulating polarization profile in the conduction electrons of CaRuO3, by a mechanism akin to Friedel oscillations. At low temperatures, this oscillating polarization is inherited by rigid local moments within CaRuO3, leading to a robust exchange bias. We present ab initio simulations in support of this picture. Our results demonstrate a new ordering mechanism and throw light on the magnetic character of CaRuO3 ., Comment: 6 pages and 4 figures