Mitochondria segmentation from electron microscopy (EM) images plays a crucial role in biological and medical research. However, models trained on source domains often suffer from performance degradation when applied to target domains due to domain shift. Unsupervised domain adaptation (UDA) methods have been proposed to address this issue, but they often overlook the reliability of pseudo-labels and the effectiveness of supervision signals. In this paper, we propose R4MITO, a novel UDA framework for robust mitochondria segmentation. First, we introduce Reliable Prototype Pseudo-labels to mitigate the inconsistency of class-level features between across domains by leveraging source prototypes to model target prototypes. Second, we devise Correlation-wise Consistency Regularization to exploit inter-pixel correlations, aligning agent-level correlations under various perturbations. Third, we propose Rank-aware Relationship Consistency Regularization to fully utilize the rich information encoded in inter-agent relationships by imposing rank-aware constraints on agent-ranking probability distributions. Extensive experiments on multiple EM datasets demonstrate the superiority of our R4MITO over existing state-of-the-art UDA methods for mitochondria segmentation.

Vision-Language models (VLMs) have shown great potential in enhancing open-world visual concept comprehension. Recent researches focus on an optimum multimodal collaboration strategy that significantly advances CLIP-based few-shot tasks. However, existing prompt-based solutions suffer from unidirectional information flow and increased parameters since they explicitly condition the vision prompts on textual prompts across different transformer layers using non-shareable coupling functions. To address this issue, we propose a Dual-shared mechanism based on LoRA (DsRA) that addresses VLM adaptation in low-data regimes. The proposed DsRA enjoys several merits. First, we design an inter-modal shared coefficient that focuses on capturing visual and textual shared patterns, ensuring effective mutual synergy between image and text features. Second, an intra-modal shared matrix is proposed to achieve efficient parameter fine-tuning by combining the different coefficients to generate layer-wise adapters placed in encoder layers. Our extensive experiments demonstrate that DsRA improves the generalizability under few-shot classification, base-to-new generalization, and domain generalization settings. Our code will be released soon.

Camouflaged Object Segmentation (COS) seeks to accurately identify and segment objects that are intricately blended with their surroundings, making them challenging to distinguish at the pixel level. Existing COS methods often struggle to capture the subtle distinctions between targets and backgrounds, despite their improved adaptability to camouflaged objects. To address this challenge, we propose a novel Adaptive Camouflage Discrimination Network (ACDNet), to focus more attention on object-relevant features while suppressing attached camouflage features. The proposed ACDNet enjoys several merits. First, we design a gradient-based feature modulator that injects gradient information into channel-wise attention layers, thereby enhancing the discriminability between camouflaged objects and background features. Second, a hierarchical prompting strategy is introduced to endow the prototype-based classifier with target awareness and multi-level perception, mitigating the impact of camouflage diversity. Extensive experimental results on four benchmarks demonstrate that our ACDNet performs favorably against state-of-the-art COS methods.

Open-vocabulary semantic segmentation (OVSS) aims to segment an image into regions of corresponding semantic vocabularies, without being limited to a predefined set of object categories. Existing works mainly utilize large-scale vision-language models (e.g., CLIP) to leverage their superior open-vocabulary classification abilities in a two-stage manner. However, their heavy reliance on the first-stage segmentation network leaves the full potential of CLIP untapped, creating an unresolved gap between the rich pre-training knowledge and the challenging per-pixel classification task. Although the recent one-stage paradigm has further leveraged pre-trained vision knowledge from CLIP, it fails to effectively utilize text information due to the inclusion of numerous unrelated semantics in the vocabulary list. How to avoid noise interference in text information and utilize language guidance remains a Gordian knot. In this paper, we propose a bi-directional bridge network (BBN) to bridge the gap between upstream pre-trained models and downstream segmentation tasks. It first purifies the noisy text embedding and then guides semantics-vision aggregation with the purified information in a purification-then-guidance manner, thereby facilitating effective semantic utilization. Specifically, we design an optimal purification modulator to purify noisy text information via the optimal transport algorithm, and a reliable guidance modulator to integrate proper textual information into vision embedding via the designed reliable attention in an adaptive manner. Extensive experimental results on five challenging benchmarks demonstrate that our BBN performs favorably against state-of-the-art open-vocabulary semantic segmentation methods.

Automatic mitochondrial segmentation enjoys great popularity with the development of deep learning. However, the coarse prediction raised by the presence of regular 3D grids in previous methods regardless of 3D CNN or the vision transformers suggest a possibly sub-optimal feature arrangement. To mitigate this limitation, we attempt to interpret the 3D EM image stacks as a set of interrelated 3D fragments for a better solution. However, it is non-trivial to model the 3D fragments without introducing excessive computational overhead. In this paper, we design a coherent fragment vision transformer (FragViT) combined with affinity learning to manipulate features on 3D fragments yet explore mutual relationships to model fragment-wise context, enjoying locality prior without sacrificing global reception. The proposed FragViT includes a fragment encoder and a hierarchical fragment aggregation module. The fragment encoder is equipped with affinity heads to transform the tokens into fragments with homogeneous semantics, and the multi-layer self-attention is used to explicitly learn inter-fragment relations with long-range dependencies. The hierarchical fragment aggregation module is responsible for hierarchically aggregating fragment-wise prediction back to the final voxel-wise prediction in a progressive manner. Extensive experimental results on the challenging MitoEM, Lucchi, and AC3/AC4 benchmarks demonstrate the effectiveness of the proposed method.

Open-vocabulary semantic segmentation (OVS) aims to segment images of arbitrary categories specified by class labels or captions. However, most previous best-performing methods, whether pixel grouping methods or region recognition methods, suffer from false matches between image features and category labels. We attribute this to the natural gap between the textual features and visual features. In this work, we rethink how to mitigate false matches from the perspective of image-to-image matching and propose a novel relation-aware intra-modal matching (RIM) framework for OVS based on visual foundation models. RIM achieves robust region classification by firstly constructing diverse image-modal reference features and then matching them with region features based on relation-aware ranking distribution. The proposed RIM enjoys several merits. First, the intra-modal reference features are better aligned, circumventing potential ambiguities that may arise in cross-modal matching. Second, the ranking-based matching process harnesses the structure information implicit in the inter-class relationships, making it more robust than comparing individually. Extensive experiments on three benchmarks demonstrate that RIM outperforms previous state-of-the-art methods by large margins, obtaining a lead of more than 10% in mIoU on PASCAL VOC benchmark.

Referring Remote Sensing Image Segmentation (RRSIS) is a challenging task that aims to identify specific regions in aerial images that are relevant to given textual conditions. Existing methods tend to adopt the paradigm of implicit optimization, utilizing a framework consisting of early cross-modal feature fusion and a fixed convolutional kernel-based predictor, neglecting the inherent inter-domain gap and conducting class-agnostic predictions. In this paper, we rethink the issues with the implicit optimization paradigm and address the RRSIS task from a dual-alignment perspective. Specifically, we prepend the dedicated Dual Alignment Network (DANet), including an explicit alignment strategy and a reliable agent alignment module. The explicit alignment strategy effectively reduces domain discrepancies by narrowing the inter-domain affinity distribution. Meanwhile, the reliable agent alignment module aims to enhance the predictor's multi-modality awareness and alleviate the impact of deceptive noise interference. Extensive experiments on two remote sensing datasets demonstrate the effectiveness of our proposed DANet in achieving superior segmentation performance without introducing additional learnable parameters compared to state-of-the-art methods.

Sex-biased gene expression differs across human populations; however, the underlying genetic basis and molecular mechanisms remain largely unknown. Here, we explore the influence of ancestry on sex differences in the human transcriptome and its genetic effects on a Eurasian admixed population: Uyghurs living in Xinjiang (XJU), by analyzing whole-genome sequencing data and transcriptome data of 90 XJU and 40 unrelated Han Chinese individuals. We identified 302 sex-biased expressed genes and 174 sex-biased cis-expression quantitative loci (sb-cis-eQTLs) in XJU, which were enriched in innate immune-related functions, indicating sex differences in immunity. Notably, approximately one-quarter of the sb-cis-eQTLs showed a strong correlation with ancestry composition; i.e. populations of similar ancestry tended to show similar patterns of sex-biased gene expression. Our analysis further suggested that genetic admixture induced a moderate degree of sex-biased gene expression. Interestingly, analysis of chromosome interactions revealed that the X chromosome acted on autosomal immunity-associated genes, partially explaining the sex-biased phenotypic differences. Our work extends the knowledge of sex-biased gene expression from the perspective of genetic admixture and bridges the gap in the exploration of sex-biased phenotypes shaped by autosome and X-chromosome interactions. Notably, we demonstrated that sex chromosomes cannot fully explain sex differentiation in immune-related phenotypes.

Camouflaged Instance Segmentation (CIS) aims at predicting the instance-level masks of camouflaged objects, which are usually the animals in the wild adapting their appearance to match the surroundings. Previous instance segmentation methods perform poorly on this task as they are easily disturbed by the deceptive camouflage. To address these challenges, we propose a novel De-camouflaging Network (DCNet) including a pixel-level camouflage decoupling module and an instance-level camouflage suppression module. The proposed DCNet enjoys several merits. First, the pixel-level camouflage decoupling module can extract camouflage characteristics based on the Fourier transformation. Then a difference attention mechanism is proposed to eliminate the camouflage characteristics while reserving target object characteristics in the pixel feature. Second, the instance-level camouflage suppression module can aggregate rich instance information from pixels by use of instance prototypes. To mitigate the effect of background noise during segmentation, we introduce some reliable reference points to build a more robust similarity measurement. With the aid of these two modules, our DCNet can effectively model de-camouflaging and achieve accurate segmentation for camouflaged instances. Extensive experimental results on two benchmarks demonstrate that our DCNet performs favorably against state-of-the-art CIS methods, e.g., with more than 5% performance gains on COD10K and NC4K datasets in average precision.

Mitochondria, as tiny structures within the cell, are of significant importance in studying cell functions for biological and clinical analysis. And exploring how to automatically segment mitochondria in electron microscopy (EM) images has attracted increasing attention. However, most of existing methods struggle to adapt to different scales and appearances of the input due to the inherent limitations of the traditional CNN architecture. To mitigate these limitations, we propose a novel adaptive template transformer (ATFormer) for mitochondria segmentation. The proposed ATFormer model enjoys several merits. First, the designed structural template learning module can acquire appearance-adaptive templates of background, foreground and contour to sense the characteristics of different shapes of mitochondria. And we further adopt an optimal transport algorithm to enlarge the discrepancy among diverse templates to activate corresponding regions fully. Second, we introduce a hierarchical attention learning mechanism to absorb multi-level information for templates to be adaptive scale-aware classifiers for dense prediction. Extensive experimental results on three challenging benchmarks including MitoEM, Lucchi and NucMM-Z datasets demonstrate that our ATFormer performs favorably against state-of-the-art mitochondria segmentation methods.

Neural connectivity reconstruction aims to understand the function of biological reconstruction and promote basic scientific research. The intricate morphology and densely intertwined branches make it an extremely challenging task. Most previous best-performing methods adopt affinity learning or metric learning. Nevertheless, they either neglect to model explicit voxel semantics caused by implicit optimization or are hysteresis to spatial information. Furthermore, the inherent locality of 3D CNNs limits modeling long-range dependencies, leading to sub-optimal results. In this work, we propose a coherent and unified Appearance Prompt Vision Transformer (APViT) to integrate affinity and metric learning to exploit the complementarity by learning long-range spatial dependencies. The proposed APViT enjoys several merits. First, the extension continuity-aware attention module aims at constructing hierarchical attention customized for neuron extensibility and slice continuity to learn instance voxel semantic context from a global perspective and utilize continuity priors to enhance voxel spatial awareness. Second, the appearance prompt modulator is responsible for leveraging voxel-adaptive appearance knowledge conditioned on affinity rich in spatial information to instruct instance voxel semantics, exploiting the potential of affinity learning to complement metric learning. Extensive experimental results on multiple challenging benchmarks demonstrate that our APViT achieves consistent improvements with huge flexibility under the same post-processing strategy.

Sex-biased gene flow has been common in the demographic history of modern humans. However, the lack of sophisticated methods for delineating the detailed sex-biased admixture process prevents insights into complex admixture history and thus our understanding of the evolutionary mechanisms of genetic diversity. Here, we present a novel algorithm, MultiWaverX, for modeling complex admixture history with sex-biased gene flow. Systematic simulations showed that MultiWaverX is a powerful tool for modeling complex admixture history and inferring sex-biased gene flow. Application of MultiWaverX to empirical data of 17 typical admixed populations in America, Central Asia, and the Middle East revealed sex-biased admixture histories that were largely consistent with the historical records. Notably, fine-scale admixture process reconstruction enabled us to recognize latent sex-biased gene flow in certain populations that would likely be overlooked by much of the routine analysis with commonly used methods. An outstanding example in the real world is the Kazakh population that experienced complex admixture with sex-biased gene flow but in which the overall signature has been canceled due to biased gene flow from an opposite direction.

BACKGROUND: Computer simulations have been widely applied in population genetics and evolutionary studies. A great deal of effort has been made over the past two decades in developing simulation tools. However, there are not many simulation tools suitable for studying population admixture. RESULTS: We here developed a forward-time simulator, AdmixSim 2, an individual-based tool that can flexibly and efficiently simulate population genomics data under complex evolutionary scenarios. Unlike its previous version, AdmixSim 2 is based on the extended Wright-Fisher model, and it implements many common evolutionary parameters to involve gene flow, natural selection, recombination, and mutation, which allow users to freely design and simulate any complex scenario involving population admixture. AdmixSim 2 can be used to simulate data of dioecious or monoecious populations, autosomes, or sex chromosomes. To our best knowledge, there are no similar tools available for the purpose of simulation of complex population admixture. Using empirical or previously simulated genomic data as input, AdmixSim 2 provides phased haplotype data for the convenience of further admixture-related analyses such as local ancestry inference, association studies, and other applications. We here evaluate the performance of AdmixSim 2 based on simulated data and validated functions via comparative analysis of simulated data and empirical data of African American, Mexican, and Uyghur populations. CONCLUSIONS: AdmixSim 2 is a flexible simulation tool expected to facilitate the study of complex population admixture in various situations.

Signa1 modulation recognition (SMR) is an essential and challenging topic in orthogonal frequency-division multiplexing (OFDM) systems, and also it is the fundamental technique for signal detection and recovery. However, traditional feature extraction based SMR methods cannot effectively acquire the characteristics of the OFDM signals. Hence, the modulated OFD-M signal cannot be reliably identified. In this paper, we propose a deep learning (DL) based SMR method for recognizing OFDM signals, which is combined with a convolutional neural network (CNN) trained on in-phase and quadrature (IQ) samples. In the network model, the batch normalization (BN) layer and dropout layer are used to speed up model training and prevent overfitting, respectively. Three convolution layers with different convolution kernels perform well than traditional feature extraction methods in obtaining intrinsic properties of OFDM signals. The same number of multiple modulated signals are mixed and sent to the trained model for identification. Experiments are conducted to show that the method we proposed performs better than the traditional methods, mainly reflected in a higher probability of correct classification (PCC) and better consistency.

This paper demonstrates a simulation methodology based on a reasonable 3D channel model. System level simulations on various 3D antenna port configurations are performed, and results are compared with those of 2D MIMO system. Several interesting observations are made from the evaluation results: (1) the vertically distributed active antenna elements provide less MIMO gain than the horizontally distributed active antenna elements; (2) with the same number of antenna elements, the 3D active antenna configuration can provide better performance than the 2D one, and the performance improvement is much larger for MU-MIMO than SU-MIMO; (3) even when the 2D antenna configuration has more antenna elements (providing more antenna array gain) than the 3D active antenna configuration, the 3D configuration can still outperform the 2D one if there are enough transmitter ports.

The algorithms of the channel quality indication (CQI) feedback and the scheduling are proposed to optimize the performance of the frequency division duplex (FDD) downlink coordinated multipoint transmission/reception (CoMP) coordinated scheduling/beamforming (CS/CB) system, where the transmit beamforming is based on the principle of the signal-to-leakage-plus-noise-ratio (SLNR) maximization. The algorithms of the precoding matrix index (PMI) feedback and the precoding corresponding to such CQI feedback and scheduling are introduced here for the completeness of the solution. The performance of above proposed algorithms are evaluated on the system-level simulation platform. By the simulation results, obvious performance gain could be observed in terms of the cell-average throughput and cell-edge user throughput.

This paper investigates OFDMA downlink resource (spectrum and power) sharing algorithms for fixed relay stations. Iterative waterfilling is used in the power allocation process and shown to result in an optimal power allocation solution for multiple-relay networks. Iterative waterfilling is then developed with a power reallocation process to achieve more efficient spectrum utilization. Furthermore, joint subcarrier and power allocation algorithms are proposed with and without consideration for multiuser fairness. Simulation results show that iterative waterfilling can significantly improve the system capacity. The proposed joint allocation algorithm achieves gains of up to 21% in system capacity compared to iterative waterfilling. The joint allocation algorithm with fairness is shown to degrade system capacity, however fairness is important in a multiuser network.

In this paper, algorithms on distributed resource (spectrum and power) sharing for relay stations are investigated for downlink transmissions in an OFDMA-based relay-aided cell. Both system capacity and user fairness are considered. By grouping the relay stations into coalitions according to the set of users they are relaying, the optimal resource allocation can be solved by considering resource allocation within and among the coalitions. The algorithm for intra-coalition resource allocation is proposed by utilizing the key observation: for each data symbol transmitted from the base station to a user (in a subcarrier), only one among all the available relay stations is required to relay the symbol. The inter-coalition resource allocation is modeled by both a non-cooperative and a cooperative game, where the cooperative game is solved by a nonsymmetric Nash bargaining solution. Simulation results show that the non-cooperative algorithm outperforms random allocation by approximately 50% in system capacity with 3 relay stations in each coalition. The cooperative algorithm has approximately 5% loss in system capacity comparing with the non-cooperative algorithm, but achieves a significant gain in terms of fairness performance.

In this paper, we focus on the design of efficient resource allocation algorithms for a multihop cellular network, with orthogonal frequency division multiple access (OFDMA) as downlink transmission technique and utilizing decode-and- forward cooperation strategy. Our objective is to maximize the total capacity based on the constraint of individual transmission power at each transmitter. We also consider users' QoS requirements by maximizing the total capacity while giving users proportional fairness weights according to their data requirements. We show that for each data symbol (at each subcarrier) transmitted by base station, the best relaying strategy is to let only one among all the relay stations perform the relaying task. This is true for both objectives of maximizing total capacity and maximizing capacity with proportional fairness constraint. We then propose efficient greedy algorithms for both centralized and distributed resource allocations based on our analysis. Simulation results indicate that our proposed algorithms effectively enhance the total capacity.