Multi-Stage Network With Geometric Semantic Attention for Two-View Correspondence Learning.

The removal of outliers is crucial for establishing correspondence between two images. However, when the proportion of outliers reaches nearly 90%, the task becomes highly challenging. Existing methods face limitations in effectively utilizing geometric transformation consistency (GTC) information and incorporating geometric semantic neighboring information. To address these challenges, we propose a Multi-Stage Geometric Semantic Attention (MSGSA) network. The MSGSA network consists of three key modules: the multi-branch (MB) module, the GTC module, and the geometric semantic attention (GSA) module. The MB module, structured with a multi-branch design, facilitates diverse and robust spatial transformations. The GTC module captures transformation consistency information from the preceding stage. The GSA module categorizes input based on the prior stage's output, enabling efficient extraction of geometric semantic information through a graph-based representation and inter-category information interaction using Transformer. Extensive experiments on the YFCC100M and SUN3D datasets demonstrate that MSGSA outperforms current state-of-the-art methods in outlier removal and camera pose estimation, particularly in scenarios with a high prevalence of outliers. Source code is available at https://github.com/shuyuanlin.

Latent Semantic Consensus for Deterministic Geometric Model Fitting.

Estimating reliable geometric model parameters from the data with severe outliers is a fundamental and important task in computer vision. This paper attempts to sample high-quality subsets and select model instances to estimate parameters in the multi-structural data. To address this, we propose an effective method called Latent Semantic Consensus (LSC). The principle of LSC is to preserve the latent semantic consensus in both data points and model hypotheses. Specifically, LSC formulates the model fitting problem into two latent semantic spaces based on data points and model hypotheses, respectively. Then, LSC explores the distributions of points in the two latent semantic spaces, to remove outliers, generate high-quality model hypotheses, and effectively estimate model instances. Finally, LSC is able to provide consistent and reliable solutions within only a few milliseconds for general multi-structural model fitting, due to its deterministic fitting nature and efficiency. Compared with several state-of-the-art model fitting methods, our LSC achieves significant superiority for the performance of both accuracy and speed on synthetic data and real images. The code will be available at https://github.com/guobaoxiao/LSC.

Density-Guided Incremental Dominant Instance Exploration for Two-View Geometric Model Fitting.

Existing two-view multi-model fitting methods typically follow a two-step manner, i.e., model generation and selection, without considering their interaction. Therefore, in the first step, these methods have to generate a considerable number of instances in order to cover all desired ones, which not only offers no guarantees, but also introduces unnecessary expensive calculations. To address this challenge, this study presents a new algorithm, termed as D2Fitting, that incrementally explores dominant instances. Particularly, rather than viewing model generation and selection as two disjoint parts, D2Fitting fully considers their interaction, and thus performs these two subroutines alternatively under a simple yet effective optimization framework. This design can avoid generating too many redundant instances, thus reducing computational overhead and allowing the proposed D2Fitting being real-time. Meanwhile, we further design a novel density-guided sampler to sample high-quality minimal subsets during the model generation process, so as to fully exploit the spatial distribution of the input data. Also, to mitigate the influence of noise on the subsets sampled by the proposed sampler, a global-residual optimization strategy is investigated for the minimal subset refinement. With all the ingredients mentioned above, the proposed D2Fitting can accurately estimate the number and parameters of geometric models and efficiently segment the input data simultaneously. Extensive experiments on several public datasets demonstrate the significant superiority of D2Fitting over several state-of-the-arts.

PGFNet: Preference-Guided Filtering Network for Two-View Correspondence Learning.

Accurate correspondence selection between two images is of great importance for numerous feature matching based vision tasks. The initial correspondences established by off-the-shelf feature extraction methods usually contain a large number of outliers, and this often leads to the difficulty in accurately and sufficiently capturing contextual information for the correspondence learning task. In this paper, we propose a Preference-Guided Filtering Network (PGFNet) to address this problem. The proposed PGFNet is able to effectively select correct correspondences and simultaneously recover the accurate camera pose of matching images. Specifically, we first design a novel iterative filtering structure to learn the preference scores of correspondences for guiding the correspondence filtering strategy. This structure explicitly alleviates the negative effects of outliers so that our network is able to capture more reliable contextual information encoded by the inliers for network learning. Then, to enhance the reliability of preference scores, we present a simple yet effective Grouped Residual Attention block as our network backbone, by designing a feature grouping strategy, a feature grouping manner, a hierarchical residual-like manner and two grouped attention operations. We evaluate PGFNet by extensive ablation studies and comparative experiments on the tasks of outlier removal and camera pose estimation. The results demonstrate outstanding performance gains over the existing state-of-the-art methods on different challenging scenes. The code is available at https://github.com/guobaoxiao/PGFNet.

Learning matrix factorization with scalable distance metric and regularizer.

Matrix factorization has always been an encouraging field, which attempts to extract discriminative features from high-dimensional data. However, it suffers from negative generalization ability and high computational complexity when handling large-scale data. In this paper, we propose a learnable deep matrix factorization via the projected gradient descent method, which learns multi-layer low-rank factors from scalable metric distances and flexible regularizers. Accordingly, solving a constrained matrix factorization problem is equivalently transformed into training a neural network with an appropriate activation function induced from the projection onto a feasible set. Distinct from other neural networks, the proposed method activates the connected weights not just the hidden layers. As a result, it is proved that the proposed method can learn several existing well-known matrix factorizations, including singular value decomposition, convex, nonnegative and semi-nonnegative matrix factorizations. Finally, comprehensive experiments demonstrate the superiority of the proposed method against other state-of-the-arts.

Co-Clustering on Bipartite Graphs for Robust Model Fitting.

Recently, graph-based methods have been widely applied to model fitting. However, in these methods, association information is invariably lost when data points and model hypotheses are mapped to the graph domain. In this paper, we propose a novel model fitting method based on co-clustering on bipartite graphs (CBG) to estimate multiple model instances in data contaminated with outliers and noise. Model fitting is reformulated as a bipartite graph partition behavior. Specifically, we use a bipartite graph reduction technique to eliminate some insignificant vertices (outliers and invalid model hypotheses), thereby improving the reliability of the constructed bipartite graph and reducing the computational complexity. We then use a co-clustering algorithm to learn a structured optimal bipartite graph with exact connected components for partitioning that can directly estimate the model instances (i.e., post-processing steps are not required). The proposed method fully utilizes the duality of data points and model hypotheses on bipartite graphs, leading to superior fitting performance. Exhaustive experiments show that the proposed CBG method performs favorably when compared with several state-of-the-art fitting methods.

MSA-Net: Establishing Reliable Correspondences by Multiscale Attention Network.

In this paper, we propose a novel multi-scale attention based network (called MSA-Net) for feature matching problems. Current deep networks based feature matching methods suffer from limited effectiveness and robustness when applied to different scenarios, due to random distributions of outliers and insufficient information learning. To address this issue, we propose a multi-scale attention block to enhance the robustness to outliers, for improving the representational ability of the feature map. In addition, we also design a novel context channel refine block and a context spatial refine block to mine the information context with less parameters along channel and spatial dimensions, respectively. The proposed MSA-Net is able to effectively infer the probability of correspondences being inliers with less parameters. Extensive experiments on outlier removal and relative pose estimation have shown the performance improvements of our network over current state-of-the-art methods with less parameters on both outdoor and indoor datasets. Notably, our proposed network achieves an 11.7% improvement at error threshold 5° without RANSAC than the state-of-the-art method on relative pose estimation task when trained on YFCC100M dataset.

GC6mA-Pred: A deep learning approach to identify DNA N6-methyladenine sites in the rice genome.

MOTIVATION: DNA N6-methyladenine (6mA) is a pivotal DNA modification for various biological processes. More accurate prediction of 6mA methylation sites plays an irreplaceable part in grasping the internal rationale of related biological activities. However, the existing prediction methods only extract information from a single dimension, which has some limitations. Therefore, it is very necessary to obtain the information of 6mA sites from different dimensions, so as to establish a reliable prediction method. RESULTS: In this study, a neural network based bioinformatics model named GC6mA-Pred is proposed to predict N6-methyladenine modifications in DNA sequences. GC6mA-Pred extracts significant information from both sequence level and graph level. In the sequence level, GC6mA-Pred uses a three-layer convolution neural network (CNN) model to represent the sequence. In the graph level, GC6mA-Pred employs graph neural network (GNN) method to integrate various information contained in the chemical molecular formula corresponding to DNA sequence. In our newly built dataset, GC6mA-Pred shows better performance than other existing models. The results of comparative experiments have illustrated that GC6mA-Pred is capable of producing a marked effect in accurately identifying DNA 6mA modifications.

SRDFM: Siamese Response Deep Factorization Machine to improve anti-cancer drug recommendation.

Predicting the response of cancer patients to a particular treatment is a major goal of modern oncology and an important step toward personalized treatment. In the practical clinics, the clinicians prefer to obtain the most-suited drugs for a particular patient instead of knowing the exact values of drug sensitivity. Instead of predicting the exact value of drug response, we proposed a deep learning-based method, named Siamese Response Deep Factorization Machines (SRDFM) Network, for personalized anti-cancer drug recommendation, which directly ranks the drugs and provides the most effective drugs. A Siamese network (SN), a type of deep learning network that is composed of identical subnetworks that share the same architecture, parameters and weights, was used to measure the relative position (RP) between drugs for each cell line. Through minimizing the difference between the real RP and the predicted RP, an optimal SN model was established to provide the rank for all the candidate drugs. Specifically, the subnetwork in each side of the SN consists of a feature generation level and a predictor construction level. On the feature generation level, both drug property and gene expression, were adopted to build a concatenated feature vector, which even enables the recommendation for newly designed drugs with only chemical property known. Particularly, we developed a response unit here to generate weighted genetic feature vector to simulate the biological interaction mechanism between a specific drug and the genes. For the predictor construction level, we built this level integrating a factorization machine (FM) component with a deep neural network component. The FM can well handle the discrete chemical information and both low-order and high-order feature interactions could be sufficiently learned. Impressively, the SRDFM works well on both single-drug recommendation and synergic drug combination. Experiment result on both single-drug and synergetic drug data sets have shown the efficiency of the SRDFM. The Python implementation for the proposed SRDFM is available at at https://github.com/RanSuLab/SRDFM Contact: ran.su@tju.edu.cn, gbx@mju.edu.cn and weileyi@sdu.edu.cn.

iDNA-ABT: advanced deep learning model for detecting DNA methylation with adaptive features and transductive information maximization.

MOTIVATION: DNA methylation plays an important role in epigenetic modification, the occurrence, and the development of diseases. Therefore, identification of DNA methylation sites is critical for better understanding and revealing their functional mechanisms. To date, several machine learning and deep learning methods have been developed for the prediction of different DNA methylation types. However, they still highly rely on manual features, which can largely limit the high-latent information extraction. Moreover, most of them are designed for one specific DNA methylation type, and therefore cannot predict multiple methylation sites in multiple species simultaneously. In this study, we propose iDNA-ABT, an advanced deep learning model that utilizes adaptive embedding based on Bidirectional Encoder Representations from Transformers (BERT) together with transductive information maximization (TIM). RESULTS: Benchmark results show that our proposed iDNA-ABT can automatically and adaptively learn the distinguishing features of biological sequences from multiple species, and thus perform significantly better than the state-of-the-art methods in predicting three different DNA methylation types. In addition, TIM loss is proven to be effective in dichotomous tasks via the comparison experiment. Furthermore, we verify that our features have strong adaptability and robustness to different species through comparison of adaptive embedding and six handcrafted feature encodings. Importantly, our model shows great generalization ability in different species, demonstrating that our model can adaptively capture the cross-species differences and improve the predictive performance. For the convenient use of our method, we further established an online webserver as the implementation of the proposed iDNA-ABT. AVAILABILITY AND IMPLEMENTATION: Our proposed iDNA-ABT and data are freely accessible via http://server.wei-group.net/iDNA_ABT and our source codes are available for downloading in the GitHub repository (https://github.com/YUYING07/iDNA_ABT). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PepFormer: End-to-End Transformer-Based Siamese Network to Predict and Enhance Peptide Detectability Based on Sequence Only.

The detectability of peptides is fundamentally important in shotgun proteomics experiments. At present, there are many computational methods to predict the detectability of peptides based on sequential composition or physicochemical properties, but they all have various shortcomings. Here, we present PepFormer, a novel end-to-end Siamese network coupled with a hybrid architecture of a Transformer and gated recurrent units that is able to predict the peptide detectability based on peptide sequences only. Specially, we, for the first time, use contrastive learning and construct a new loss function for model training, greatly improving the generalization ability of our predictive model. Comparative results demonstrate that our model performs significantly better than state-of-the-art methods on benchmark data sets in two species (Homo sapiens and Mus musculus). To make the model more interpretable, we further investigate the embedded representations of peptide sequences automatically learnt from our model, and the visualization results indicate that our model can efficiently capture high-latent discriminative information, improving the predictive performance. In addition, our model shows a strong ability of cross-species transfer learning and adaptability, demonstrating that it has great potential in robust prediction of peptides detectability on different species. The source code of our proposed method can be found via https://github.com/WLYLab/PepFormer.

Deterministic Model Fitting by Local-neighbor Preservation and Global-residual Optimization.

Geometric model fitting has been widely used in many computer vision tasks. However, it remains as a challenging task when handing multiple-structural data contaminated by noises and outliers. Most previous work on model fitting cannot guarantee the consistency of their solutions due to their randomness, precluding them from many real-world applications. In this research, we propose a fast two-view approximately deterministic model fitting scheme (called LGF), to provide consistent solutions for multiple-structural data. The proposed LGF scheme starts from defining preference function by preserving local neighborhood relationship, and then adopts the min-hash technique to roughly sample subsets. By this way, it is able to cover all model instances in data in the parameter space with a high probability. After that, LGF refines the previous sampled subsets by globalresidual optimization. Furthermore, we propose a simple yet effective model selection framework to estimate the number and the parameters of model instances in data. Extensive experiments on real images show that the proposed LGF scheme is able to observe superior or very competitive performance on both accuracy and speed over several state-of-the-art model fitting methods.

A Bioinformatics Tool for the Prediction of DNA N6-Methyladenine Modifications Based on Feature Fusion and Optimization Protocol.

DNA N6-methyladenine (6mA) is closely involved with various biological processes. Identifying the distributions of 6mA modifications in genome-scale is of great significance to in-depth understand the functions. In recent years, various experimental and computational methods have been proposed for this purpose. Unfortunately, existing methods cannot provide accurate and fast 6mA prediction. In this study, we present 6mAPred-FO, a bioinformatics tool that enables researchers to make predictions based on sequences only. To sufficiently capture the characteristics of 6mA sites, we integrate the sequence-order information with nucleotide positional specificity information for feature encoding, and further improve the feature representation capacity by analysis of variance-based feature optimization protocol. The experimental results show that using this feature protocol, we can significantly improve the predictive performance. Via further feature analysis, we found that the sequence-order information and positional specificity information are complementary to each other, contributing to the performance improvement. On the other hand, the improvement is also due to the use of the feature optimization protocol, which is capable of effectively capturing the most informative features from the original feature space. Moreover, benchmarking comparison results demonstrate that our 6mAPred-FO outperforms several existing predictors. Finally, we establish a web-server that implements the proposed method for convenience of researchers' use, which is currently available at http://server.malab.cn/6mAPred-FO.

Meta-GDBP: a high-level stacked regression model to improve anticancer drug response prediction.

Anticancer drug response prediction plays an important role in personalized medicine. In particular, precisely predicting drug response in specific cancer types and patients is still a challenge problem. Here we propose Meta-GDBP, a novel anticancer drug-response model, which involves two levels. At the first level of Meta-GDBP, we build four optimized base models (BMs) using genetic information, chemical properties and biological context with an ensemble optimization strategy, while at the second level, we construct a weighted model to integrate the four BMs. Notably, the weights of the models are learned upstream, thus the parameter cost is significantly reduced compared to previous methods. We evaluate the Meta-GDBP on Genomics of Drug Sensitivity in Cancer (GDSC) and the Cancer Cell Line Encyclopedia (CCLE) data sets. Benchmarking results demonstrate that compared to other methods, the Meta-GDBP achieves a much higher correlation between the predicted and the observed responses for almost all the drugs. Moreover, we apply the Meta-GDBP to predict the GDSC-missing drug response and use the CCLE-known data to validate the performance. The results show quite a similar tendency between these two response sets. Particularly, we here for the first time introduce a biological context-based frequency matrix (BCFM) to associate the biological context with the drug response. It is encouraging that the proposed BCFM is biologically meaningful and consistent with the reported biological mechanism, further demonstrating its efficacy for predicting drug response. The R implementation for the proposed Meta-GDBP is available at https://github.com/RanSuLab/Meta-GDBP.

Searching for Representative Modes on Hypergraphs for Robust Geometric Model Fitting.

In this paper, we propose a simple and effective geometric model fitting method to fit and segment multi-structure data even in the presence of severe outliers. We cast the task of geometric model fitting as a representative mode-seeking problem on hypergraphs. Specifically, a hypergraph is first constructed, where the vertices represent model hypotheses and the hyperedges denote data points. The hypergraph involves higher-order similarities (instead of pairwise similarities used on a simple graph), and it can characterize complex relationships between model hypotheses and data points. In addition, we develop a hypergraph reduction technique to remove "insignificant" vertices while retaining as many "significant" vertices as possible in the hypergraph. Based on the simplified hypergraph, we then propose a novel mode-seeking algorithm to search for representative modes within reasonable time. Finally, the proposed mode-seeking algorithm detects modes according to two key elements, i.e., the weighting scores of vertices and the similarity analysis between vertices. Overall, the proposed fitting method is able to efficiently and effectively estimate the number and the parameters of model instances in the data simultaneously. Experimental results demonstrate that the proposed method achieves significant superiority over several state-of-the-art model fitting methods on both synthetic data and real images.