Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. Despite of the success of previous works, explorations on an effective training strategy for the saliency network and accurate matches be
tween image-level annotations and salient objects are still inadequate. In this work, 1) we propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions, liberating the saliency network from error-prone propagation caused by pseudo labels. 2) we prove that even a much smaller dataset (merely 1.8% of ImageNet) with well-matched annotations can facilitate models to achieve better performance as well as generalizability. This sheds new light on the development of WSOD and encourages more contributions to the community. Comprehensive experiments demonstrate that our method outperforms all the existing WSOD methods by adopting the self-calibrated strategy only. Steady improvements are further achieved by training on the proposed dataset. Additionally, our method achieves 94.7% of the performance of fully-supervised methods on average. And what is more, the fully supervised models adopting our predicted results as ground truths achieve successful results (95.6% for BASNet and 97.3% for ITSD on F-measure), while costing only 0.32% of labeling time for pixel-level annotation.
Domain generalization (DG) aims to generalize a model trained on multiple source (i.e., training) domains to a distributionally different target (i.e., test) domain. In contrast to the conventional DG that strictly requires the availability of multip
le source domains, this paper considers a more realistic yet challenging scenario, namely Single Domain Generalization (Single-DG), where only one source domain is available for training. In this scenario, the limited diversity may jeopardize the model generalization on unseen target domains. To tackle this problem, we propose a style-complement module to enhance the generalization power of the model by synthesizing images from diverse distributions that are complementary to the source ones. More specifically, we adopt a tractable upper bound of mutual information (MI) between the generated and source samples and perform a two-step optimization iteratively: (1) by minimizing the MI upper bound approximation for each sample pair, the generated images are forced to be diversified from the source samples; (2) subsequently, we maximize the MI between the samples from the same semantic category, which assists the network to learn discriminative features from diverse-styled images. Extensive experiments on three benchmark datasets demonstrate the superiority of our approach, which surpasses the state-of-the-art single-DG methods by up to 25.14%.
The wireless network is undergoing a trend from onnection of things to connection of intelligence. With data spread over the communication networks and computing capability enhanced on the devices, distributed learning becomes a hot topic in both ind
ustrial and academic communities. Many frameworks, such as federated learning and federated distillation, have been proposed. However, few of them takes good care of obstacles such as the time-varying topology resulted by the characteristics of wireless networks. In this paper, we propose a distributed learning framework based on a scalable deep neural network (DNN) design. By exploiting the permutation equivalence and invariance properties of the learning tasks, the DNNs with different scales for different clients can be built up based on two basic parameter sub-matrices. Further, model aggregation can also be conducted based on these two sub-matrices to improve the learning convergence and performance. Finally, simulation results verify the benefits of the proposed framework by compared with some baselines.
Recently, the intrinsic magnetic topological insulator MnBi2Te4 has attracted enormous research interest due to the great success in realizing exotic topological quantum states, such as the quantum anomalous Hall effect (QAHE), axion insulator state,
high-Chern-number and high-temperature Chern insulator states. One key issue in this field is to effectively manipulate these states and control topological phase transitions. Here, by systematic angle-dependent transport measurements, we reveal a magnetization-tuned topological quantum phase transition from Chern insulator to magnetic insulator with gapped Dirac surface states in MnBi2Te4 devices. Specifically, as the magnetic field is tilted away from the out-of-plane direction by around 40-60 degrees, the Hall resistance deviates from the quantization value and a colossal, anisotropic magnetoresistance is detected. The theoretical analyses based on modified Landauer-Buttiker formalism show that the field-tilt-driven switching from ferromagnetic state to canted antiferromagnetic state induces a topological quantum phase transition from Chern insulator to magnetic insulator with gapped Dirac surface states in MnBi2Te4 devices. Our work provides an efficient means for modulating topological quantum states and topological quantum phase transitions.
The internet is filled with fake face images and videos synthesized by deep generative models. These realistic DeepFakes pose a challenge to determine the authenticity of multimedia content. As countermeasures, artifact-based detection methods suffer
from insufficiently fine-grained features that lead to limited detection performance. DNN-based detection methods are not efficient enough, given that a DeepFake can be created easily by mobile apps and DNN-based models require high computational resources. For the first time, we show that DeepFake faces have fewer feature points than real ones, especially in certain facial regions. Inspired by feature point detector-descriptors to extract discriminative features at the pixel level, we propose the Fused Facial Region_Feature Descriptor (FFR_FD) for effective and fast DeepFake detection. FFR_FD is only a vector extracted from the face, and it can be constructed from any feature point detector-descriptors. We train a random forest classifier with FFR_FD and conduct extensive experiments on six large-scale DeepFake datasets, whose results demonstrate that our method is superior to most state of the art DNN-based models.
Joint event and causality extraction is a challenging yet essential task in information retrieval and data mining. Recently, pre-trained language models (e.g., BERT) yield state-of-the-art results and dominate in a variety of NLP tasks. However, thes
e models are incapable of imposing external knowledge in domain-specific extraction. Considering the prior knowledge of frequent n-grams that represent cause/effect events may benefit both event and causality extraction, in this paper, we propose convolutional knowledge infusion for frequent n-grams with different windows of length within a joint extraction framework. Knowledge infusion during convolutional filter initialization not only helps the model capture both intra-event (i.e., features in an event cluster) and inter-event (i.e., associations across event clusters) features but also boosts training convergence. Experimental results on the benchmark datasets show that our model significantly outperforms the strong BERT+CSNN baseline.
We study the effects of bismuth doping on the crystal structure and phase transitions in single crystals of the perovskite semiconductor methylammonium lead tribromide, MAPbBr3. By measuring temperature-dependent specific heat capacity (Cp) we find t
hat, as Bi doping increases, the phase transition assigned to the cubic to tetragonal phase boundary decreases in temperature. Furthermore, after doping we observe one phase transition between 135 and 155 K, in contrast to two transitions observed in the undoped single crystal. These results appear strikingly similar to previously reported effects of mechanical pressure on perovskite crystal structure. Using X-ray diffraction, we show that the lattice constant decreases as Bi is incorporated into the crystal, as predicted by density functional theory (DFT). We propose that bismuth substitutional doping on the lead site is dominant, resulting in BiPb+ centers which induce compressive chemical strain that alters the crystalline phase transitions.
Hard point-contact spectroscopy and scanning probe microscopy/spectroscopy are powerful techniques for investigating materials with strong expandability. To support these studies, tips with various physical and chemical properties are required. To en
sure the reproducibility of experimental results, the fabrication of tips should be standardized, and a controllable and convenient system should be set up. Here a systematic methodology to fabricate various tips is proposed, involving electrochemical etching reactions. The reaction parameters fall into four categories: solution, power supply, immersion depth, and interruption. An etching system was designed and built so that these parameters could be accurately controlled. With this system, etching parameters for copper, silver, gold, platinum/iridium alloy, tungsten, lead, niobium, iron, nickel, cobalt, and permalloy were explored and standardized. Among these tips, silver and niobiums new recipes were explored and standardized. Optical and scanning electron microscopies were performed to characterize the sharp needles. Relevant point-contact experiments were carried out with an etched silver tip to confirm the suitability of the fabricated tips.
Historical features are important in ads click-through rate (CTR) prediction, because they account for past engagements between users and ads. In this paper, we study how to efficiently construct historical features through counting features. The key
challenge of such problem lies in how to automatically identify counting keys. We propose a tree-based method for counting key selection. The intuition is that a decision tree naturally provides various combinations of features, which could be used as counting key candidate. In order to select personalized counting features, we train one decision tree model per user, and the counting keys are selected across different users with a frequency-based importance measure. To validate the effectiveness of proposed solution, we conduct large scale experiments on Twitter video advertising data. In both online learning and offline training settings, the automatically identified counting features outperform the manually curated counting features.
Researches on anomalous Hall effect (AHE) have been lasting for a century to make clear the underlying physical mechanism. Generally, the AHE appears in magnetic materials, in which extrinsic process related to scattering effects and intrinsic contri
bution connected with Berry curvature are crucial. Recently, AHE has been counterintuitively observed in non-magnetic topological materials and attributed to the existence of Weyl points. However, the Weyl point scenario would lead to unsaturated AHE even in large magnetic fields and contradicts the saturation of AHE in several tesla (T) in experiments. In this work, we investigate the Hall effect of ZrTe5 and HfTe5 thin flakes in static ultrahigh magnetic fields up to 33 T. We find the AHE saturates to 55 (70) Ohm^-1*cm^-1 for ZrTe5 (HfTe5) thin flakes above ~ 10 T. Combining detailed magnetotransport experiments and Berry curvature calculations, we clarify that the splitting of massive Dirac bands without Weyl points can be responsible for AHE in non-magnetic topological materials ZrTe5 and HfTe5 thin flakes. This model can identify our thin flake samples to be weak topological insulators and serve as a new tool to probe the band structure topology in topological materials.
