Search

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of ViT captures the global context from the outset, overlooking the inherent relationships between neighboring pixels in images or videos. Transformers mainly focus on global information while ignoring the fine-grained local details. Consequently, ViT lacks inductive bias during image or video dataset training. In contrast, convolutional neural networks (CNNs), with their reliance on local filters, possess an inherent inductive bias, making them more efficient and quicker to converge than ViT with less data. In this paper, we present a lightweight Depth-Wise Convolution module as a shortcut in ViT models, bypassing entire Transformer blocks to ensure the models capture both local and global information with minimal overhead. Additionally, we introduce two architecture variants, allowing the Depth-Wise Convolution modules to be applied to multiple Transformer blocks for parameter savings, and incorporating independent parallel Depth-Wise Convolution modules with different kernels to enhance the acquisition of local information. The proposed approach significantly boosts the performance of ViT models on image classification, object detection and instance segmentation by a large margin, especially on small datasets, as evaluated on CIFAR-10, CIFAR-100, Tiny-ImageNet and ImageNet for image classification, and COCO for object detection and instance segmentation. The source code can be accessed at https://github.com/ZTX-100/Efficient_ViT_with_DW.

Given a collection $\mathcal{G} =\{G_1,G_2,\dots,G_m\}$ of graphs on the common vertex set $V$ of size $n$, an $m$-edge graph $H$ on the same vertex set $V$ is transversal in $\mathcal{G}$ if there exists a bijection $\varphi :E(H)\rightarrow [m]$ such that $e \in E(G_{\varphi(e)})$ for all $e\in E(H)$. Denote $\delta(\mathcal{G}):=\operatorname*{min}\left\{\delta(G_i): i\in [m]\right\}$. In this paper, we first establish a minimum degree condition for the existence of transversal Hamilton paths in $\mathcal{G}$: if $n=m+1$ and $\delta(\mathcal{G})\geq \frac{n-1}{2}$, then $\mathcal{G}$ contains a transversal Hamilton path. This solves a problem proposed by [Li, Li and Li, J. Graph Theory, 2023]. As a continuation of the transversal version of Dirac's theorem [Joos and Kim, Bull. Lond. Math. Soc., 2020] and the stability result for transversal Hamilton cycles [Cheng and Staden, arXiv:2403.09913v1], our second result characterizes all graph collections with minimum degree at least $\frac{n}{2}-1$ and without transversal Hamilton cycles. We obtain an analogous result for transversal Hamilton paths. The proof is a combination of the stability result for transversal Hamilton paths or cycles, transversal blow-up lemma, along with some structural analysis., Comment: 33 pages, 10 figures

H&E-to-IHC stain translation techniques offer a promising solution for precise cancer diagnosis, especially in low-resource regions where there is a shortage of health professionals and limited access to expensive equipment. Considering the pixel-level misalignment of H&E-IHC image pairs, current research explores the pathological consistency between patches from the same positions of the image pair. However, most of them overemphasize the correspondence between domains or patches, overlooking the side information provided by the non-corresponding objects. In this paper, we propose a Mix-Domain Contrastive Learning (MDCL) method to leverage the supervision information in unpaired H&E-to-IHC stain translation. Specifically, the proposed MDCL method aggregates the inter-domain and intra-domain pathology information by estimating the correlation between the anchor patch and all the patches from the matching images, encouraging the network to learn additional contrastive knowledge from mixed domains. With the mix-domain pathology information aggregation, MDCL enhances the pathological consistency between the corresponding patches and the component discrepancy of the patches from the different positions of the generated IHC image. Extensive experiments on two H&E-to-IHC stain translation datasets, namely MIST and BCI, demonstrate that the proposed method achieves state-of-the-art performance across multiple metrics.

In this work, a deep learning-based technique is used to study the image-to-joint inverse kinematics of a tendon-driven supportive continuum arm. An eye-off-hand configuration is considered by mounting a camera at a fixed pose with respect to the inertial frame attached at the arm base. This camera captures an image for each distinct joint variable at each sampling time to construct the training dataset. This dataset is then employed to adapt a feed-forward deep convolutional neural network, namely the modified VGG-16 model, to estimate the joint variable. One thousand images are recorded to train the deep network, and transfer learning and fine-tuning techniques are applied to the modified VGG-16 to further improve the training. Finally, training is also completed with a larger dataset of images that are affected by various types of noises, changes in illumination, and partial occlusion. The main contribution of this research is the development of an image-to-joint network that can estimate the joint variable given an image of the arm, even if the image is not captured in an ideal condition. The key benefits of this research are twofold: 1) image-to-joint mapping can offer a real-time alternative to computationally complex inverse kinematic mapping through analytical models; and 2) the proposed technique can provide robustness against noise, occlusion, and changes in illumination. The dataset is publicly available on Kaggle., Comment: Presented at the Candian Conference on Robots and Vision (CRV)

Recent advancements in event argument extraction (EAE) involve incorporating useful auxiliary information into models during training and inference, such as retrieved instances and event templates. These methods face two challenges: (1) the retrieval results may be irrelevant and (2) templates are developed independently for each event without considering their possible relationship. In this work, we propose DEGAP to address these challenges through a simple yet effective components: dual prefixes, i.e. learnable prompt vectors, where the instance-oriented prefix and template-oriented prefix are trained to learn information from different event instances and templates. Additionally, we propose an event-guided adaptive gating mechanism, which can adaptively leverage possible connections between different events and thus capture relevant information from the prefix. Finally, these event-guided prefixes provide relevant information as cues to EAE model without retrieval. Extensive experiments demonstrate that our method achieves new state-of-the-art performance on four datasets (ACE05, RAMS, WIKIEVENTS, and MLEE). Further analysis shows the impact of different components.

For a fixed family of $r$-uniform hypergraphs $\mathcal{F}$, the anti-Ramsey number of $\mathcal{F}$, denoted by $ ar(n,r,\mathcal{F})$, is the minimum number $c$ of colors such that for any edge-coloring of the complete $r$-uniform hypergraph on $n$ vertices with at least $c$ colors, there is a rainbow copy of some hypergraph in $\mathcal{F}$. Here, a rainbow hypergraph is an edge-colored hypergraph with all edges colored differently. Let $\mathcal{P}_k$ and $\mathcal{C}_k$ be the families of loose paths and loose cycles with $k$ edges in an $r$-uniform hypergraph, respectively. In this paper, we determine the exact values of $ ar(n,r,\mathcal{P}_k)$ and $ ar(n,r,\mathcal{C}_k)$ for all $k\geq 4$ and $r\geq 3$.

Aphid infestations are one of the primary causes of extensive damage to wheat and sorghum fields and are one of the most common vectors for plant viruses, resulting in significant agricultural yield losses. To address this problem, farmers often employ the inefficient use of harmful chemical pesticides that have negative health and environmental impacts. As a result, a large amount of pesticide is wasted on areas without significant pest infestation. This brings to attention the urgent need for an intelligent autonomous system that can locate and spray sufficiently large infestations selectively within the complex crop canopies. We have developed a large multi-scale dataset for aphid cluster detection and segmentation, collected from actual sorghum fields and meticulously annotated to include clusters of aphids. Our dataset comprises a total of 54,742 image patches, showcasing a variety of viewpoints, diverse lighting conditions, and multiple scales, highlighting its effectiveness for real-world applications. In this study, we trained and evaluated four real-time semantic segmentation models and three object detection models specifically for aphid cluster segmentation and detection. Considering the balance between accuracy and efficiency, Fast-SCNN delivered the most effective segmentation results, achieving 80.46% mean precision, 81.21% mean recall, and 91.66 frames per second (FPS). For object detection, RT-DETR exhibited the best overall performance with a 61.63% mean average precision (mAP), 92.6% mean recall, and 72.55 on an NVIDIA V100 GPU. Our experiments further indicate that aphid cluster segmentation is more suitable for assessing aphid infestations than using detection models.

We discuss the topological properties of the independence complex of Kneser graphs, Ind(KG$(n, k))$, with $n\geq 3$ and $k\geq 1$. By identifying one kind of maximal simplices through projective planes, we obtain homology generators for the $6$-dimensional homology of the complex Ind(KG$(3, k))$. Using cross-polytopal generators, we provide lower bounds for the rank of $p$-dimensional homology of the complex Ind(KG$(n, k))$ where $p=1/2\cdot {2n+k\choose 2n}$. Denote $\mathcal{F}_n^{[m]}$ to be the collection of $n$-subsets of $[m]$ equipped with the symmetric difference metric. We prove that if $\ell$ is the minimal integer with the $q$th dimensional reduced homology $\tilde{H}_q(\mathcal{VR}(\mathcal{F}^{[\ell]}_n; 2(n-1)))$ being non-trivial, then $$\text{rank} (\tilde{H}_q(\mathcal{VR}(\mathcal{F}_n^{[m]}; 2(n-1)))\geq \sum_{i=\ell}^m{i-2\choose \ell-2}\cdot \text{rank} (\tilde{H}_q(\mathcal{VR}(\mathcal{F}_n^{[\ell]}; 2(n-1))). $$ Since the independence complex Ind(KG$(n, k))$ and the Vietoris-Rips complex $\mathcal{VR}(\mathcal{F}^{[2n+k]}_n; 2(n-1))$ are the same, we obtain a homology propagation result in the setting of independence complexes of Kneser graphs. Connectivity of these complexes is also discussed in this paper.

Cloud computing (cloud computing) is a kind of distributed computing, referring to the network "cloud" will be a huge data calculation and processing program into countless small programs, and then, through the system composed of multiple servers to process and analyze these small programs to get the results and return to the user. This report explores the intersection of cloud computing and financial information processing, identifying risks and challenges faced by financial institutions in adopting cloud technology. It discusses the need for intelligent solutions to enhance data processing efficiency and accuracy while addressing security and privacy concerns. Drawing on regulatory frameworks, the report proposes policy recommendations to mitigate concentration risks associated with cloud computing in the financial industry. By combining intelligent forecasting and evaluation technologies with cloud computing models, the study aims to provide effective solutions for financial data processing and management, facilitating the industry's transition towards digital transformation.

In this study, the performance of generalized low-density parity-check (GLDPC) codes under the a posteriori probability (APP) decoder is analyzed. We explore the concentration, symmetry, and monotonicity properties of GLDPC codes under the APP decoder, extending the applicability of density evolution to GLDPC codes. On the binary memoryless symmetric channels, using the BEC and BI-AWGN channels as two examples, we demonstrate that with an appropriate proportion of generalized constraint (GC) nodes, GLDPC codes can reduce the original gap to capacity compared to their original LDPC counterparts. Additionally, on the BI-AWGN channel, we apply and improve the Gaussian approximation algorithm in the density evolution of GLDPC codes. By adopting Gaussian mixture distributions to approximate the message distributions from variable nodes and Gaussian distributions for those from constraint nodes, the precision of the channel parameter threshold can be significantly enhanced while maintaining a low computational complexity similar to that of Gaussian approximations. Furthermore, we identify a class of subcodes that can greatly simplify the performance analysis and practical decoding of GLDPC codes, which we refer to as message-invariant subcodes. Using the aforementioned techniques, our simulation experiments provide empirical evidence that GLDPC codes, when decoded with the APP decoder and equipped with the right fraction of GC nodes, can achieve substantial performance improvements compared to low-density parity-check (LDPC) codes.

Efficient decoding is crucial to high-throughput and low-power wireless communication scenarios. A theoretical analysis of the performance-complexity tradeoff toward low-complexity decoding is required for a better understanding of the fundamental limits in the above-mentioned scenarios. This study aims to explore the performance of decoders with complexity constraints. Specifically, we investigate the performance of LDPC codes with different numbers of belief-propagation iterations and the performance of polar codes with an SSC decoder. We found that the asymptotic error rates of both polar codes and LDPC codes are functions of complexity $T$ and code length $N$, in the form of $2^{-a2^{b\frac{T}{N}}}$, where $a$ and $b$ are constants that depend on channel and coding schemes. Our analysis reveals the different performance-complexity tradeoffs for LDPC and polar codes. The results indicate that if one aims to further enhance the decoding efficiency for LDPC codes, the key lies in how to efficiently pass messages on the factor graph. In terms of decoding efficiency, polar codes asymptotically outperform $(J, K)$-regular LDPC codes with a code rate $R \le 1-\frac{J(J-1)}{2^J+(J-1)}$ in the low-complexity regime $(T \le O(NlogN))$., Comment: arXiv admin note: text overlap with arXiv:2012.13378 by other authors

Detecting and segmenting polyps is crucial for expediting the diagnosis of colon cancer. This is a challenging task due to the large variations of polyps in color, texture, and lighting conditions, along with subtle differences between the polyp and its surrounding area. Recently, vision Transformers have shown robust abilities in modeling global context for polyp segmentation. However, they face two major limitations: the inability to learn local relations among multi-level layers and inadequate feature aggregation in the decoder. To address these issues, we propose a novel decoder architecture aimed at hierarchically aggregating locally enhanced multi-level dense features. Specifically, we introduce a novel module named Dense Attention Gate (DAG), which adaptively fuses all previous layers' features to establish local feature relations among all layers. Furthermore, we propose a novel nested decoder architecture that hierarchically aggregates decoder features, thereby enhancing semantic features. We incorporate our novel dense decoder with the PVT backbone network and conduct evaluations on five polyp segmentation datasets: Kvasir, CVC-300, CVC-ColonDB, CVC-ClinicDB, and ETIS. Our experiments and comparisons with nine competing segmentation models demonstrate that the proposed architecture achieves state-of-the-art performance and outperforms the previous models on four datasets. The source code is available at: https://github.com/krushi1992/Dense-Decoder.

Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision. This paper proposes a generalized framework called SuperLoRA that unifies and extends different LoRA variants, which can be realized under different hyper-parameter settings. Introducing grouping, folding, shuffling, projecting, and tensor factoring, SuperLoRA offers high flexibility compared with other LoRA variants and demonstrates superior performance for transfer learning tasks especially in the extremely few-parameter regimes., Comment: 33 pages, 29 figures

Inspire therapy is an FDA-approved internal neurostimulation treatment for obstructive sleep apnea. However, not all patients respond to this therapy, posing a challenge even for experienced otolaryngologists to determine candidacy. This paper makes the first attempt to leverage both machine learning and deep learning techniques in discerning patient responsiveness to Inspire therapy using medical data and videos captured through Drug-Induced Sleep Endoscopy (DISE), an essential procedure for Inspire therapy. To achieve this, we gathered and annotated three datasets from 127 patients. Two of these datasets comprise endoscopic videos focused on the Base of the Tongue and Velopharynx. The third dataset composes the patient's clinical information. By utilizing these datasets, we benchmarked and compared the performance of six deep learning models and five classical machine learning algorithms. The results demonstrate the potential of employing machine learning and deep learning techniques to determine a patient's eligibility for Inspire therapy, paving the way for future advancements in this field.

Given a graph $H$, a balanced subdivision of $H$ is obtained by replacing all edges of $H$ with internally disjoint paths of the same length. In this paper, we prove that for any graph $H$, a linear-in-$e(H)$ bound on average degree guarantees a balanced $H$-subdivision. This strengthens an old result of Bollob\'as and Thomason, and resolves a question of Gil-Fern\'{a}ndez, Hyde, Liu, Pikhurko and Wu. We observe that this linear bound on average degree is best possible whenever $H$ is logarithmically dense. We further show that this logarithmic density is the critical threshold: for many graphs $H$ below this density, its subdivisions are forcible by a sublinear bound in $e(H)$ on average degree. We provide such examples by proving that the subdivisions of any almost bipartite graph $H$ with sublogarithmic density are forcible by a sublinear-in-$e(H)$ bound on average degree, provided that $H$ satisfies some additional separability condition., Comment: 34 pages, 2 pages, Comments welcome!

The escalating global concern over extensive food wastage necessitates innovative solutions to foster a net-zero lifestyle and reduce emissions. The LILA home composter presents a convenient means of recycling kitchen scraps and daily food waste into nutrient-rich, high-quality compost. To capture the nutritional information of the produced compost, we have created and annotated a large high-resolution image dataset of kitchen food waste with segmentation masks of 19 nutrition-rich categories. Leveraging this dataset, we benchmarked four state-of-the-art semantic segmentation models on food waste segmentation, contributing to the assessment of compost quality of Nitrogen, Phosphorus, or Potassium. The experiments demonstrate promising results of using segmentation models to discern food waste produced in our daily lives. Based on the experiments, SegFormer, utilizing MIT-B5 backbone, yields the best performance with a mean Intersection over Union (mIoU) of 67.09. Class-based results are also provided to facilitate further analysis of different food waste classes.

Mitral Transcatheter Edge-to-Edge Repair (mTEER) is a medical procedure utilized for the treatment of mitral valve disorders. However, predicting the outcome of the procedure poses a significant challenge. This paper makes the first attempt to harness classical machine learning (ML) and deep learning (DL) techniques for predicting mitral valve mTEER surgery outcomes. To achieve this, we compiled a dataset from 467 patients, encompassing labeled echocardiogram videos and patient reports containing Transesophageal Echocardiography (TEE) measurements detailing Mitral Valve Repair (MVR) treatment outcomes. Leveraging this dataset, we conducted a benchmark evaluation of six ML algorithms and two DL models. The results underscore the potential of ML and DL in predicting mTEER surgery outcomes, providing insight for future investigation and advancements in this domain., Comment: 5 pages, 1 figure

Accurately detecting multiple change-points is critical for various applications, but determining the optimal number of change-points remains a challenge. Existing approaches based on information criteria attempt to balance goodness-of-fit and model complexity, but their performance varies depending on the model. Recently, data-driven selection criteria based on cross-validation has been proposed, but these methods can be prone to slight overfitting in finite samples. In this paper, we introduce a method that controls the probability of overestimation and provides uncertainty quantification for learning multiple change-points via cross-validation. We frame this problem as a sequence of model comparison problems and leverage high-dimensional inferential procedures. We demonstrate the effectiveness of our approach through experiments on finite-sample data, showing superior uncertainty quantification for overestimation compared to existing methods. Our approach has broad applicability and can be used in diverse change-point models., Comment: 11 pages, 1 figure, to appear at AAAI 2024

In this paper, we propose a novel framework named DRL-CPG to learn disentangled latent representation for controllable person image generation, which can produce realistic person images with desired poses and human attributes (e.g., pose, head, upper clothes, and pants) provided by various source persons. Unlike the existing works leveraging the semantic masks to obtain the representation of each component, we propose to generate disentangled latent code via a novel attribute encoder with transformers trained in a manner of curriculum learning from a relatively easy step to a gradually hard one. A random component mask-agnostic strategy is introduced to randomly remove component masks from the person segmentation masks, which aims at increasing the difficulty of training and promoting the transformer encoder to recognize the underlying boundaries between each component. This enables the model to transfer both the shape and texture of the components. Furthermore, we propose a novel attribute decoder network to integrate multi-level attributes (e.g., the structure feature and the attribute representation) with well-designed Dual Adaptive Denormalization (DAD) residual blocks. Extensive experiments strongly demonstrate that the proposed approach is able to transfer both the texture and shape of different human parts and yield realistic results. To our knowledge, we are the first to learn disentangled latent representations with transformers for person image generation.

Riemannian convex optimization and minimax optimization have recently drawn considerable attention. Their appeal lies in their capacity to adeptly manage the non-convexity of the objective function as well as constraints inherent in the feasible set in the Euclidean sense. In this work, we delve into monotone Riemannian Variational Inequality Problems (RVIPs), which encompass both Riemannian convex optimization and minimax optimization as particular cases. In the context of Euclidean space, it is established that the last-iterates of both the extragradient (EG) and past extragradient (PEG) methods converge to the solution of monotone variational inequality problems at a rate of $O\left(\frac{1}{\sqrt{T}}\right)$ (Cai et al., 2022). However, analogous behavior on Riemannian manifolds remains an open question. To bridge this gap, we introduce the Riemannian extragradient (REG) and Riemannian past extragradient (RPEG) methods. We demonstrate that both exhibit $O\left(\frac{1}{\sqrt{T}}\right)$ last-iterate convergence. Additionally, we show that the average-iterate convergence of both REG and RPEG is $O\left(\frac{1}{{T}}\right)$, aligning with observations in the Euclidean case (Mokhtari et al., 2020). These results are enabled by judiciously addressing the holonomy effect so that additional complications in Riemannian cases can be reduced and the Euclidean proof inspired by the performance estimation problem (PEP) technique or the sum-of-squares (SOS) technique can be applied again., Comment: Published in Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024)

Image restoration aims to restore high-quality images from degraded counterparts and has seen significant advancements through deep learning techniques. The technique has been widely applied to mobile devices for tasks such as mobile photography. Given the resource limitations on mobile devices, such as memory constraints and runtime requirements, the efficiency of models during deployment becomes paramount. Nevertheless, most previous works have primarily concentrated on analyzing the efficiency of single modules and improving them individually. This paper examines the efficiency across different layers. We propose a roadmap that can be applied to further accelerate image restoration models prior to deployment while simultaneously increasing PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index). The roadmap first increases the model capacity by adding more parameters to partial convolutions on FLOPs non-sensitive layers. Then, it applies partial depthwise convolution coupled with decoupling upsampling/downsampling layers to accelerate the model speed. Extensive experiments demonstrate that our approach decreases runtime by up to 13% and reduces the number of parameters by up to 23%, while increasing PSNR and SSIM on several image restoration datasets. Source Code of our method is available at \href{https://github.com/xiangyu8/MOFA}{https://github.com/xiangyu8/MOFA}., Comment: Accepted by 2023 ICCV Workshop (RCV)

Unlike graphs, determining Tur\'{a}n densities of hypergraphs is known to be notoriously hard in general. The essential reason is that for many classical families of $r$-uniform hypergraphs $\mathcal{F}$, there are perhaps many near-extremal $\mathcal{M}_t$-free configurations with very different structure. Such a phenomenon is called not stable, and Liu and Mubayi gave a first not stable example. Another perhaps reason is that little is known about the set consisting of all possible Tur\'{a}n densities which has cardinality of the continuum. Let $t\ge 2$ be an integer. In this paper, we construct a finite family $\mathcal{M}_t$ of 3-uniform hypergraphs such that the Tur\'{a}n density of $\mathcal{M}_t$ is irrational, and there are $t$ near-extremal $\mathcal{M}_t$-free configurations that are far from each other in edit-distance. This is the first not stable example that has an irrational Tur\'{a}n density. It also provides a new phenomenon about feasible region functions.

Aphid infestation poses a significant threat to crop production, rural communities, and global food security. While chemical pest control is crucial for maximizing yields, applying chemicals across entire fields is both environmentally unsustainable and costly. Hence, precise localization and management of aphids are essential for targeted pesticide application. The paper primarily focuses on using deep learning models for detecting aphid clusters. We propose a novel approach for estimating infection levels by detecting aphid clusters. To facilitate this research, we have captured a large-scale dataset from sorghum fields, manually selected 5,447 images containing aphids, and annotated each individual aphid cluster within these images. To facilitate the use of machine learning models, we further process the images by cropping them into patches, resulting in a labeled dataset comprising 151,380 image patches. Then, we implemented and compared the performance of four state-of-the-art object detection models (VFNet, GFLV2, PAA, and ATSS) on the aphid dataset. Extensive experimental results show that all models yield stable similar performance in terms of average precision and recall. We then propose to merge close neighboring clusters and remove tiny clusters caused by cropping, and the performance is further boosted by around 17%. The study demonstrates the feasibility of automatically detecting and managing insects using machine learning models. The labeled dataset will be made openly available to the research community.

Aphid infestations can cause extensive damage to wheat and sorghum fields and spread plant viruses, resulting in significant yield losses in agriculture. To address this issue, farmers often rely on chemical pesticides, which are inefficiently applied over large areas of fields. As a result, a considerable amount of pesticide is wasted on areas without pests, while inadequate amounts are applied to areas with severe infestations. The paper focuses on the urgent need for an intelligent autonomous system that can locate and spray infestations within complex crop canopies, reducing pesticide use and environmental impact. We have collected and labeled a large aphid image dataset in the field, and propose the use of real-time semantic segmentation models to segment clusters of aphids. A multiscale dataset is generated to allow for learning the clusters at different scales. We compare the segmentation speeds and accuracy of four state-of-the-art real-time semantic segmentation models on the aphid cluster dataset, benchmarking them against nonreal-time models. The study results show the effectiveness of a real-time solution, which can reduce inefficient pesticide use and increase crop yields, paving the way towards an autonomous pest detection system.

Aphids are one of the main threats to crops, rural families, and global food security. Chemical pest control is a necessary component of crop production for maximizing yields, however, it is unnecessary to apply the chemical approaches to the entire fields in consideration of the environmental pollution and the cost. Thus, accurately localizing the aphid and estimating the infestation level is crucial to the precise local application of pesticides. Aphid detection is very challenging as each individual aphid is really small and all aphids are crowded together as clusters. In this paper, we propose to estimate the infection level by detecting aphid clusters. We have taken millions of images in the sorghum fields, manually selected 5,447 images that contain aphids, and annotated each aphid cluster in the image. To use these images for machine learning models, we crop the images into patches and created a labeled dataset with over 151,000 image patches. Then, we implement and compare the performance of four state-of-the-art object detection models.

Elementary trapping sets (ETSs) are the main culprits for the performance of LDPC codes in the error floor region. Due to the large quantity, complex structures, and computational difficulties of ETSs, how to eliminate dominant ETSs in designing LDPC codes becomes a pivotal issue to improve the error floor behavior. In practice, researchers commonly address this problem by avoiding some special graph structures to free specific ETSs in Tanner graph. In this paper, we deduce the accurate Tur\'an number of $\theta(1,2,2)$ and prove that all $(a,b)$-ETSs in Tanner graph with variable-regular degree $d_L(v)=\gamma$ must satisfy the bound $b\geq a\gamma-\frac{1}{2}a^2$, which improves the lower bound obtained by Amirzade when the girth is 6. For the case of girth 8, by limiting the relation between any two 8-cycles in the Tanner graph, we prove a similar inequality $b\geq a\gamma-\frac{a(\sqrt{8a-7}-1)}{2}$. The simulation results show that the designed codes have good performance with lower error floor over additive white Gaussian noise channels., Comment: 5 pages, 3 figures

Simultaneous multi-index quantification, segmentation, and uncertainty estimation of liver tumors on multi-modality non-contrast magnetic resonance imaging (NCMRI) are crucial for accurate diagnosis. However, existing methods lack an effective mechanism for multi-modality NCMRI fusion and accurate boundary information capture, making these tasks challenging. To address these issues, this paper proposes a unified framework, namely edge-aware multi-task network (EaMtNet), to associate multi-index quantification, segmentation, and uncertainty of liver tumors on the multi-modality NCMRI. The EaMtNet employs two parallel CNN encoders and the Sobel filters to extract local features and edge maps, respectively. The newly designed edge-aware feature aggregation module (EaFA) is used for feature fusion and selection, making the network edge-aware by capturing long-range dependency between feature and edge maps. Multi-tasking leverages prediction discrepancy to estimate uncertainty and improve segmentation and quantification performance. Extensive experiments are performed on multi-modality NCMRI with 250 clinical subjects. The proposed model outperforms the state-of-the-art by a large margin, achieving a dice similarity coefficient of 90.01$\pm$1.23 and a mean absolute error of 2.72$\pm$0.58 mm for MD. The results demonstrate the potential of EaMtNet as a reliable clinical-aided tool for medical image analysis.

We propose a general methodology Reliever for fast and reliable changepoint detection when the model fitting is costly. Instead of fitting a sequence of models for each potential search interval, Reliever employs a substantially reduced number of proxy/relief models that are trained on a predetermined set of intervals. This approach can be seamlessly integrated with state-of-the-art changepoint search algorithms. In the context of high-dimensional regression models with changepoints, we establish that the Reliever, when combined with an optimal search scheme, achieves estimators for both the changepoints and corresponding regression coefficients that attain optimal rates of convergence, up to a logarithmic factor. Through extensive numerical studies, we showcase the ability of Reliever to rapidly and accurately detect changes across a diverse range of parametric and nonparametric changepoint models.

The widespread use of black box prediction methods has sparked an increasing interest in algorithm/model-agnostic approaches for quantifying goodness-of-fit, with direct ties to specification testing, model selection and variable importance assessment. A commonly used framework involves defining a predictiveness criterion, applying a cross-fitting procedure to estimate the predictiveness, and utilizing the difference in estimated predictiveness between two models as the test statistic. However, even after standardization, the test statistic typically fails to converge to a non-degenerate distribution under the null hypothesis of equal goodness, leading to what is known as the degeneracy issue. To addresses this degeneracy issue, we present a simple yet effective device, Zipper. It draws inspiration from the strategy of additional splitting of testing data, but encourages an overlap between two testing data splits in predictiveness evaluation. Zipper binds together the two overlapping splits using a slider parameter that controls the proportion of overlap. Our proposed test statistic follows an asymptotically normal distribution under the null hypothesis for any fixed slider value, guaranteeing valid size control while enhancing power by effective data reuse. Finite-sample experiments demonstrate that our procedure, with a simple choice of the slider, works well across a wide range of settings.

The projection operation is a critical component in a wide range of optimization algorithms, such as online gradient descent (OGD), for enforcing constraints and achieving optimal regret bounds. However, it suffers from computational complexity limitations in high-dimensional settings or when dealing with ill-conditioned constraint sets. Projection-free algorithms address this issue by replacing the projection oracle with more efficient optimization subroutines. But to date, these methods have been developed primarily in the Euclidean setting, and while there has been growing interest in optimization on Riemannian manifolds, there has been essentially no work in trying to utilize projection-free tools here. An apparent issue is that non-trivial affine functions are generally non-convex in such domains. In this paper, we present methods for obtaining sub-linear regret guarantees in online geodesically convex optimization on curved spaces for two scenarios: when we have access to (a) a separation oracle or (b) a linear optimization oracle. For geodesically convex losses, and when a separation oracle is available, our algorithms achieve $O(T^{1/2}\:)$ and $O(T^{3/4}\;)$ adaptive regret guarantees in the full information setting and the bandit setting, respectively. When a linear optimization oracle is available, we obtain regret rates of $O(T^{3/4}\;)$ for geodesically convex losses and $O(T^{2/3}\; log T )$ for strongly geodesically convex losses., Comment: Published in Proceedings of The Thirty-seventh Annual Conference on Neural Information Processing Systems (NeurIPS 2023)

Light field (LF) depth estimation is a crucial task with numerous practical applications. However, mainstream methods based on the multi-view stereo (MVS) are resource-intensive and time-consuming as they need to construct a finer cost volume. To address this issue and achieve a better trade-off between accuracy and efficiency, we propose an occlusion-aware cascade cost volume for LF depth (disparity) estimation. Our cascaded strategy reduces the sampling number while keeping the sampling interval constant during the construction of a finer cost volume. We also introduce occlusion maps to enhance accuracy in constructing the occlusion-aware cost volume. Specifically, we first obtain the coarse disparity map through the coarse disparity estimation network. Then, the sub-aperture images (SAIs) of side views are warped to the center view based on the initial disparity map. Next, we propose photo-consistency constraints between the warped SAIs and the center SAI to generate occlusion maps for each SAI. Finally, we introduce the coarse disparity map and occlusion maps to construct an occlusion-aware refined cost volume, enabling the refined disparity estimation network to yield a more precise disparity map. Extensive experiments demonstrate the effectiveness of our method. Compared with state-of-the-art methods, our method achieves a superior balance between accuracy and efficiency and ranks first in terms of MSE and Q25 metrics among published methods on the HCI 4D benchmark. The code and model of the proposed method are available at https://github.com/chaowentao/OccCasNet.

First-order optimization methods tend to inherently favor certain solutions over others when minimizing an underdetermined training objective that has multiple global optima. This phenomenon, known as implicit bias, plays a critical role in understanding the generalization capabilities of optimization algorithms. Recent research has revealed that in separable binary classification tasks gradient-descent-based methods exhibit an implicit bias for the $\ell_2$-maximal margin classifier. Similarly, generic optimization methods, such as mirror descent and steepest descent, have been shown to converge to maximal margin classifiers defined by alternative geometries. While gradient-descent-based algorithms provably achieve fast implicit bias rates, corresponding rates in the literature for generic optimization methods are relatively slow. To address this limitation, we present a series of state-of-the-art implicit bias rates for mirror descent and steepest descent algorithms. Our primary technique involves transforming a generic optimization algorithm into an online optimization dynamic that solves a regularized bilinear game, providing a unified framework for analyzing the implicit bias of various optimization methods. Our accelerated rates are derived by leveraging the regret bounds of online learning algorithms within this game framework. We then show the flexibility of this framework by analyzing the implicit bias in adversarial training, and again obtain significantly improved convergence rates., Comment: Undated version: New results for implicit bias in adversarial training

Flexible laryngoscopy is commonly performed by otolaryngologists to detect laryngeal diseases and to recognize potentially malignant lesions. Recently, researchers have introduced machine learning techniques to facilitate automated diagnosis using laryngeal images and achieved promising results. Diagnostic performance can be improved when patients' demographic information is incorporated into models. However, manual entry of patient data is time consuming for clinicians. In this study, we made the first endeavor to employ deep learning models to predict patient demographic information to improve detector model performance. The overall accuracy for gender, smoking history, and age was 85.5%, 65.2%, and 75.9%, respectively. We also created a new laryngoscopic image set for machine learning study and benchmarked the performance of 8 classical deep learning models based on CNNs and Transformers. The results can be integrated into current learning models to improve their performance by incorporating the patient's demographic information.

The numerical determination of solitary states is an important topic for such research areas as Bose-Einstein condensates, nonlinear optics, plasma physics, etc. In this paper, we propose a data-driven approach for identifying solitons based on dynamical solutions of real-time differential equations. Our approach combines a machine-learning architecture called the complex-valued neural operator (CNO) with an energy-restricted gradient optimization. The former serves as a generalization of the traditional neural operator to the complex domain, and constructs a smooth mapping between the initial and final states; the latter facilitates the search for solitons by constraining the energy space. We concretely demonstrate this approach on the quasi-one-dimensional Bose-Einstein condensate with homogeneous and inhomogeneous nonlinearities. Our work offers a new idea for data-driven effective modeling and studies of solitary waves in nonlinear physical systems., Comment: 9 pages, 5 figures

The uniform Tur\'an density $\pi_{1}(F)$ of a $3$-uniform hypergraph $F$ is the supremum over all $d$ for which there is an $F$-free hypergraph with the property that every linearly sized subhypergraph with density at least $d$. Determining $\pi_{1}(F)$ for given hypergraphs $F$ was suggested by Erd\H{o}s and S\'os in 1980s. In particular, they raised the questions of determining $\pi_{1}(K_4^{(3)-})$ and $\pi_{1}(K_4^{(3)})$. The former question was solved recently in [Israel J. Math. 211 (2016), 349-366] and [J. Eur. Math. Soc. 20 (2018), 1139-1159], while the latter is still a major open problem. In addition to $K_4^{(3)-}$, there are very few hypergraphs whose uniform Tur\'an density has been determined. In this paper, we give a sufficient condition for $3$-uniform hypergraphs $F$ satisfying $\pi_{1}(F)=1/4$. In particular, currently all known $3$-uniform hypergraphs whose uniform Tur\'an density is $1/4$, such as $K_4^{(3)-}$ and the $3$-uniform hypergraphs $F^{\star}_5$ studied in [arXiv:2211.12747], satisfy this condition. Moreover, we find some intriguing $3$-uniform hypergraphs whose uniform Tur\'an density is also $1/4$., Comment: 23 pages

A $k$-graph (or $k$-uniform hypergraph) $H$ is uniformly dense if the edge distribution of $H$ is uniformly dense with respect to every large collection of $k$-vertex cliques induced by sets of $(k-2)$-tuples. Reiher, R\"odl and Schacht [Int. Math. Res. Not., 2018] proposed the study of the uniform Tur\'an density $\pi_{k-2}(F)$ for given $k$-graphs $F$ in uniformly dense $k$-graphs. Meanwhile, they [J. London Math. Soc., 2018] characterized $k$-graphs $F$ satisfying $\pi_{k-2}(F)=0$ and showed that $\pi_{k-2}(\cdot)$ ``jumps" from 0 to at least $k^{-k}$. In particular, they asked whether there exist $3$-graphs $F$ with $\pi_{1}(F)$ equal or arbitrarily close to $1/27$. Recently, Garbe, Kr\'al' and Lamaison [arXiv:2105.09883] constructed some $3$-graphs with $\pi_{1}(F)=1/27$. In this paper, for any $k$-graph $F$, we give a lower bound of $\pi_{k-2}(F)$ based on a probabilistic framework, and provide a general theorem that reduces proving an upper bound on $\pi_{k-2}(F)$ to embedding $F$ in reduced $k$-graphs of the same density using the regularity method for $k$-graphs. By using this result and Ramsey theorem for multicolored hypergraphs, we extend the results of Garbe, Kr\'al' and Lamaison to $k\ge 3$. In other words, we give a sufficient condition for $k$-graphs $F$ satisfying $\pi_{k-2}(F)=k^{-k}$. Additionally, we also construct an infinite family of $k$-graphs with $\pi_{k-2}(F)=k^{-k}$., Comment: 25 pages

Let $Y_{3,2}$ be the 3-graph with two edges intersecting in two vertices. We prove that every 3-graph $ H $ on $ n $ vertices with at least $ \max \left \{ \binom{4\alpha n}{3}, \binom{n}{3}-\binom{n-\alpha n}{3} \right \}+o(n^3) $ edges contains a $Y_{3,2}$-tiling covering more than $ 4\alpha n$ vertices, for sufficiently large $ n $ and $0<\alpha< 1/4$. The bound on the number of edges is asymptotically best possible and solves a conjecture of the authors for 3-graphs that generalizes the Matching Conjecture of Erd\H{o}s., Comment: Acccepted by European Journal of Combinatorics