Searcharxiv⌕ Search

arXiv subjects

Qiong Wang

Publications and source records attributed to Qiong Wang.

At least 55 records · Page 3Linked to original sources
arXiv2023

Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos

Breast lesion segmentation in ultrasound (US) videos is essential for diagnosing and treating axillary lymph node metastasis. However, the lack of a well-established and large-scale ultrasound video dataset with high-quality annotations has posed a persistent challenge for the research community. To overcome this issue, we meticulously curated a US video breast lesion segmentation dataset comprising 572 videos and 34,300 annotated frames, covering a wide range of realistic clinical scenarios. Furthermore, we propose a novel frequency and localization feature aggregation network (FLA-Net) that learns temporal features from the frequency domain and predicts additional lesion location positions to assist with breast lesion segmentation. We also devise a localization-based contrastive loss to reduce the lesion location distance between neighboring video frames within the same video and enlarge the location distances between frames from different ultrasound videos. Our experiments on our annotated dataset and two public video polyp segmentation datasets demonstrate that our proposed FLA-Net achieves state-of-the-art performance in breast lesion segmentation in US videos and video polyp segmentation while significantly reducing time and space complexity. Our model and dataset are available at https://github.com/jhl-Det/FLA-Net.

eess.IV↗
arXiv2023

Interface Modification for Energy Levels Alignment and Charge Extraction in CsPbI$_3$ Perovskite Solar Cells

In perovskite solar cells (PSCs) energy levels alignment and charge extraction at the interfaces are the essential factors directly affecting the device performance. In this work, we present a modified interface between all-inorganic CsPbI$_3$ perovskite and its hole selective contact (Spiro-OMeTAD), realized by a dipole molecule trioctylphosphine oxide (TOPO), to align the energy levels. On a passivated perovskite film, by n-Octyl ammonium Iodide (OAI), we created an upward surface band-bending at the interface by TOPO treatment. This improved interface by the dipole molecule induces a better energy level alignment and enhances the charge extraction of holes from the perovskite layer to the hole transport material. Consequently, a Voc of 1.2 V and high-power conversion efficiency (PCE) of over 19% were achieved for inorganic CsPbI$_3$ perovskite solar cells. Further, to demonstrate the effect of the TOPO dipole molecule, we present a layer-by-layer charge extraction study by transient surface photovoltage technique (trSPV) accomplished by charge transport simulation.

cond-mat.mtrl-sci↗
arXiv2023

Semi-Supervised Semantic Segmentation With Region Relevance

Semi-supervised semantic segmentation aims to learn from a small amount of labeled data and plenty of unlabeled ones for the segmentation task. The most common approach is to generate pseudo-labels for unlabeled images to augment the training data. However, the noisy pseudo-labels will lead to cumulative classification errors and aggravate the local inconsistency in prediction. This paper proposes a Region Relevance Network (RRN) to alleviate the problem mentioned above. Specifically, we first introduce a local pseudo-label filtering module that leverages discriminator networks to assess the accuracy of the pseudo-label at the region level. A local selection loss is proposed to mitigate the negative impact of wrong pseudo-labels in consistency regularization training. In addition, we propose a dynamic region-loss correction module, which takes the merit of network diversity to further rate the reliability of pseudo-labels and correct the convergence direction of the segmentation network with a dynamic region loss. Extensive experiments are conducted on PASCAL VOC 2012 and Cityscapes datasets with varying amounts of labeled data, demonstrating that our proposed approach achieves state-of-the-art performance compared to current counterparts.

cs.CV↗
arXiv2023

RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction

In biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures. However, it is slow, expensive, and harmful to cells. In this paper, we model it as a deep learning task termed subcellular structure prediction (SSP), aiming to predict the 3D fluorescent images of multiple subcellular structures from a 3D transmitted-light image. Unfortunately, due to the limitations of current biotechnology, each image is partially labeled in SSP. Besides, naturally, subcellular structures vary considerably in size, which causes the multi-scale issue of SSP. To overcome these challenges, we propose Re-parameterizing Mixture-of-Diverse-Experts (RepMode), a network that dynamically organizes its parameters with task-aware priors to handle specified single-label prediction tasks. In RepMode, the Mixture-of-Diverse-Experts (MoDE) block is designed to learn the generalized parameters for all tasks, and gating re-parameterization (GatRep) is performed to generate the specialized parameters for each task, by which RepMode can maintain a compact practical topology exactly like a plain network, and meanwhile achieves a powerful theoretical topology. Comprehensive experiments show that RepMode can achieve state-of-the-art overall performance in SSP.

cs.CV↗
arXiv2023

Masked Image Training for Generalizable Deep Image Denoising

When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method for image denoising, especially with the emergence of Transformer-based models that have achieved notable state-of-the-art results on various image tasks. However, deep learning-based methods often suffer from a lack of generalization ability. For example, deep models trained on Gaussian noise may perform poorly when tested on other noise distributions. To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training. Our method involves masking random pixels of the input image and reconstructing the missing information during training. We also mask out the features in the self-attention layers to avoid the impact of training-testing inconsistency. Our approach exhibits better generalization ability than other deep learning models and is directly applicable to real-world scenarios. Additionally, our interpretability analysis demonstrates the superiority of our method.

cs.CV↗
arXiv2023

FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network

Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images. The current correlation-based methods construct pair-wise feature correlations to establish the many-to-many matching because the typical prototype-based approaches cannot learn fine-grained correspondence relations. However, the existing methods still suffer from the noise contained in naive correlations and the lack of context semantic information in correlations. To alleviate these problems mentioned above, we propose a Feature-Enhanced Context-Aware Network (FECANet). Specifically, a feature enhancement module is proposed to suppress the matching noise caused by inter-class local similarity and enhance the intra-class relevance in the naive correlation. In addition, we propose a novel correlation reconstruction module that encodes extra correspondence relations between foreground and background and multi-scale context semantic features, significantly boosting the encoder to capture a reliable matching pattern. Experiments on PASCAL-$5^i$ and COCO-$20^i$ datasets demonstrate that our proposed FECANet leads to remarkable improvement compared to previous state-of-the-arts, demonstrating its effectiveness.

cs.CV↗
arXiv2022

Channel-Aware Ordered Successive Relaying with Finite-Blocklength Coding

Successive relaying can improve the transmission rate by allowing the source and relays to transmit messages simultaneously, but it may cause severe inter-relay interference (IRI). IRI cancellation schemes have been proposed to mitigate IRI. However, interference cancellation methods have a high risk of error propagation, resulting in a severe transmission rate loss in finite blocklength regimes. Thus, jointly decoding for successive relaying with finite-blocklength coding (FBC) remains a challenge. In this paper, we present an optimized channel-aware ordered successive relaying protocol with finite-blocklength coding (CAO-SIR-FBC), which can recover the rate loss by carefully adapting the relay transmission order and rate. We analyze the average throughput of the CAO-SIR-FBC method, based on which a closed-form expression in a high signal-to-noise regime (SNR) is presented. Average throughput analysis and simulations show that CAO-SIR-FBC outperforms conventional two-timeslot half-duplex relaying in terms of spectral efficiency.

cs.IT↗
arXiv2022

Acknowledging the Unknown for Multi-label Learning with Single Positive Labels

Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels. We consider an extreme of this weakly supervised learning problem, called single positive multi-label learning (SPML), where each multi-label training image has only one positive label. Traditionally, all unannotated labels are assumed as negative labels in SPML, which introduces false negative labels and causes model training to be dominated by assumed negative labels. In this work, we choose to treat all unannotated labels from an alternative perspective, i.e. acknowledging they are unknown. Hence, we propose entropy-maximization (EM) loss to attain a special gradient regime for providing proper supervision signals. Moreover, we propose asymmetric pseudo-labeling (APL), which adopts asymmetric-tolerance strategies and a self-paced procedure, to cooperate with EM loss and then provide more precise supervision. Experiments show that our method significantly improves performance and achieves state-of-the-art results on all four benchmarks. Code is available at https://github.com/Correr-Zhou/SPML-AckTheUnknown.

cs.CV↗
arXiv2022

Intra-Modal Constraint Loss For Image-Text Retrieval

Cross-modal retrieval has drawn much attention in both computer vision and natural language processing domains. With the development of convolutional and recurrent neural networks, the bottleneck of retrieval across image-text modalities is no longer the extraction of image and text features but an efficient loss function learning in embedding space. Many loss functions try to closer pairwise features from heterogeneous modalities. This paper proposes a method for learning joint embedding of images and texts using an intra-modal constraint loss function to reduce the violation of negative pairs from the same homogeneous modality. Experimental results show that our approach outperforms state-of-the-art bi-directional image-text retrieval methods on Flickr30K and Microsoft COCO datasets. Our code is publicly available: https://github.com/CanonChen/IMC.

cs.CV↗
arXiv2022

Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation with only image-level labels aims to reduce annotation costs for the segmentation task. Existing approaches generally leverage class activation maps (CAMs) to locate the object regions for pseudo label generation. However, CAMs can only discover the most discriminative parts of objects, thus leading to inferior pixel-level pseudo labels. To address this issue, we propose a saliency guided Inter- and Intra-Class Relation Constrained (I$^2$CRC) framework to assist the expansion of the activated object regions in CAMs. Specifically, we propose a saliency guided class-agnostic distance module to pull the intra-category features closer by aligning features to their class prototypes. Further, we propose a class-specific distance module to push the inter-class features apart and encourage the object region to have a higher activation than the background. Besides strengthening the capability of the classification network to activate more integral object regions in CAMs, we also introduce an object guided label refinement module to take a full use of both the segmentation prediction and the initial labels for obtaining superior pseudo-labels. Extensive experiments on PASCAL VOC 2012 and COCO datasets demonstrate well the effectiveness of I$^2$CRC over other state-of-the-art counterparts. The source codes, models, and data have been made available at \url{https://github.com/NUST-Machine-Intelligence-Laboratory/I2CRC}.

cs.CV↗
arXiv2021

Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention

Purpose: Segmentation of liver vessels from CT images is indispensable prior to surgical planning and aroused broad range of interests in the medical image analysis community. Due to the complex structure and low contrast background, automatic liver vessel segmentation remains particularly challenging. Most of the related researches adopt FCN, U-net, and V-net variants as a backbone. However, these methods mainly focus on capturing multi-scale local features which may produce misclassified voxels due to the convolutional operator's limited locality reception field. Methods: We propose a robust end-to-end vessel segmentation network called Inductive BIased Multi-Head Attention Vessel Net(IBIMHAV-Net) by expanding swin transformer to 3D and employing an effective combination of convolution and self-attention. In practice, we introduce the voxel-wise embedding rather than patch-wise embedding to locate precise liver vessel voxels, and adopt multi-scale convolutional operators to gain local spatial information. On the other hand, we propose the inductive biased multi-head self-attention which learns inductive biased relative positional embedding from initialized absolute position embedding. Based on this, we can gain a more reliable query and key matrix. To validate the generalization of our model, we test on samples which have different structural complexity. Results: We conducted experiments on the 3DIRCADb datasets. The average dice and sensitivity of the four tested cases were 74.8% and 77.5%, which exceed results of existing deep learning methods and improved graph cuts method. Conclusion: The proposed model IBIMHAV-Net provides an automatic, accurate 3D liver vessel segmentation with an interleaved architecture that better utilizes both global and local spatial features in CT volumes. It can be further extended for other clinical data.

eess.IV↗
arXiv2021

Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning

The backpropagation networks are notably susceptible to catastrophic forgetting, where networks tend to forget previously learned skills upon learning new ones. To address such the 'sensitivity-stability' dilemma, most previous efforts have been contributed to minimizing the empirical risk with different parameter regularization terms and episodic memory, but rarely exploring the usages of the weight loss landscape. In this paper, we investigate the relationship between the weight loss landscape and sensitivity-stability in the continual learning scenario, based on which, we propose a novel method, Flattening Sharpness for Dynamic Gradient Projection Memory (FS-DGPM). In particular, we introduce a soft weight to represent the importance of each basis representing past tasks in GPM, which can be adaptively learned during the learning process, so that less important bases can be dynamically released to improve the sensitivity of new skill learning. We further introduce Flattening Sharpness (FS) to reduce the generalization gap by explicitly regulating the flatness of the weight loss landscape of all seen tasks. As demonstrated empirically, our proposed method consistently outperforms baselines with the superior ability to learn new skills while alleviating forgetting effectively.

cs.LG↗
arXiv2021

Asymptotically Optimal Inventory Control for Assemble-to-Order Systems

We consider Assemble-to-Order (ATO) inventory systems with a general Bill of Materials and general deterministic lead times. Unsatisfied demands are always backlogged. We apply a four-step asymptotic framework to develop inventory policies for minimizing the long-run average expected total inventory cost. Our approach features a multi-stage Stochastic Program (SP) to establish a lower bound on the inventory cost and determine parameter values for inventory control. Our replenishment policy deviates from the conventional constant base stock policies to accommodate non-identical lead times. Our component allocation policy differentiates demands based on backlog costs, Bill of Materials, and component availabilities. We prove that our policy is asymptotically optimal on the diffusion scale, that is, as the longest lead time grows, the percentage difference between the average cost under our policy and its lower bound converges to zero. In developing these results, we formulate a broad Stochastic Tracking Model and prove general convergence results from which the asymptotic optimality of our policy follows as specialized corollaries.

math.OC↗
arXiv2021

Ammonia-induced Calcium Phosphate Nanostructure: A Potential Assay for Studying Osteoporosis and Bone Metastasis

Osteoclastic resorption of bone plays a central role in both osteoporosis and bone metastasis. A reliable in vitro assay that simulates osteoclastic resorption in vivo would significantly speed up the process of devel-oping effective therapeutic solutions for those diseases. Here we reported the development of a novel and robust nano-structured calcium phosphate coating with unique functions on the track-etched porous mem-brane by using an ammonia-induced mineralization (AiM) technique. The calcium phosphate coating uni-formly covers one side of the PET membrane enabling testing for osteoclastic resorption. The track-etched pores in the PET membrane allow calcium phosphate mineral pins to grow inside, which, on one hand, enhances coating integration with membrane substrate, and on the other hand provides diffusion channels for delivering drugs from the lower chamber of a double-chamber cell culture system. The applications of the processed calcium phosphate coating was first demonstrated as a drug screening device by using alen-dronate, a widely used drug for osteoporosis. It was confirmed that the delivery of alendronate significant-ly decreased both the number of monocyte-differentiated osteoclasts and coating resorption. To demon-strate the application in studying bone metastasis, we delivered PC3 prostate cancer conditioned medium and confirmed that both the differentiation of monocytes into osteoclasts and the osteoclastic resorption of the calcium phosphate coating were significantly enhanced. This novel assay thus provides a new platform for studying osteoclastic activities and assessing drug efficacy in vitro.

q-bio.TO↗
arXiv2021

Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation

One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these existing approaches simulate the test conditions too strictly during the training process, and thus cannot make full use of the given label information. Besides, these approaches mainly focus on the foreground-background target class segmentation setting. They only utilize binary mask labels for training. In this paper, we propose to leverage the multi-class label information during the episodic training. It will encourage the network to generate more semantically meaningful features for each category. After integrating the target class cues into the query features, we then propose a pyramid feature fusion module to mine the fused features for the final classifier. Furthermore, to take more advantage of the support image-mask pair, we propose a self-prototype guidance branch to support image segmentation. It can constrain the network for generating more compact features and a robust prototype for each semantic class. For inference, we propose a fused prototype guidance branch for the segmentation of the query image. Specifically, we leverage the prediction of the query image to extract the pseudo-prototype and combine it with the initial prototype. Then we utilize the fused prototype to guide the final segmentation of the query image. Extensive experiments demonstrate the superiority of our proposed approach.

cs.CV↗
arXiv2021

Exploiting random lead times for significant inventory cost savings

We study the classical single-item inventory system in which unsatisfied demands are backlogged. Replenishment lead times are random, independent identically distributed, causing orders to cross in time. We develop a new inventory policy to exploit implications of lead time randomness and order crossover, and evaluate its performance by asymptotic analysis and simulations. Our policy does not follow the basic principle of Constant Base Stock (CBS) policy, or more generally, (s,S) and (r,Q) policies, which is to keep the inventory position within a fixed range. Instead, it uses the current inventory level (= inventory-on-hand minus backlog) to set a dynamic target for inventory in-transit, and place orders to follow this target. Our policy includes CBS policy as a special case, under a particular choice of a policy parameter. We show that our policy can significantly reduce the average inventory cost compared with CBS policy. Specifically, we prove that if the lead time is exponentially distributed, then under our policy, with properly chosen policy parameters, the expected (absolute) inventory level scales as $o(\sqrt{r})$, as the demand rate $r\to\infty$. In comparison, it is known to scale as $Θ(\sqrt{r})$ under CBS policy. In particular, this means that, as $r\to\infty$, the average inventory cost under our policy vanishes in comparison with that under CBS policy. Furthermore, our simulations show that the advantage of our policy remains to be substantial under non-exponential lead time distributions, and may even be greater than under exponential distribution. We also use simulations to compare GBS to an optimal policy for some cases where computing the optimal cost is tractable. The results show that our policy removes a majority of excess costs of CBS policy over the minimum cost, leading to much smaller optimality gaps.

math.PR↗
arXiv2021

Texture Formation in Polycrystalline Thin Films of All-Inorganic Lead Halide Perovskite

Controlling grain orientations within polycrystalline all-inorganic halide perovskite solar cells can help increase conversion efficiencies toward their thermodynamic limits, however the forces governing texture formation are ambiguous. Using synchrotron X-ray diffraction, we report meso-structure formation within polycrystalline CsPbI2.85Br0.15 powders as they cool from a high-temperature cubic perovskite (α-phase). Tetragonal distortions (\b{eta}-phase) trigger preferential crystallographic alignment within polycrystalline ensembles, a feature we suggest is coordinated across multiple neighboring grains via interfacial forces that select for certain lattice distortions over others. External anisotropy is then imposed on polycrystalline thin films of orthorhombic (γ-phase) CsPbI3-xBrx perovskite via substrate clamping, revealing two fundamental uniaxial texture formations; (i) I-rich films possess orthorhombic-like texture (<100> out-of-plane; <010> and <001> in-plane), while (ii) Br-rich films form tetragonal-like texture (<110> out-of-plane; <1-10> and <001> in-plane). In contrast to relatively uninfluential factors like the choice of substrate, film thickness and annealing temperature, Br incorporation modifies the γ-CsPbI3-xBrx crystal structure by reducing the orthorhombic lattice distortion (making it more tetragonal-like) and governs the formation of the different, energetically favored textures within polycrystalline thin films.

cond-mat.mtrl-sci↗