In the task of semi-supervised video object segmentation, the input is the binary mask of an object in the first frame, and the desired output consists of the corresponding masks of that object in the subsequent frames.

Multimodal approaches that integrate protein structure and sequence have achieved remarkable success in protein-protein interface prediction. However, extending these methods to protein-peptide interactions remains challenging due to the inherent conformational flexibility of peptides and the limited availability of structural data that hinder direct training of structure-aware models. To address these limitations, we introduce GeoPep, a novel framework for peptide binding site prediction that leverages transfer learning from ESM3, a multimodal protein foundation model. GeoPep fine-tunes ESM3's rich pre-learned representations from protein-protein binding to address the limited availability of protein-peptide binding data. The fine-tuned model is further integrated with a parameter-efficient neural network architecture capable of learning complex patterns from sparse data. Furthermore, the model is trained using distance-based loss functions that exploit 3D structural information to enhance binding site prediction. Comprehensive evaluations demonstrate that GeoPep significantly outperforms existing methods in protein-peptide binding site prediction by effectively capturing sparse and heterogeneous binding patterns.

In the task of semi-supervised video object segmentation, the input is the binary mask of an object in the first frame, and the desired output consists of the corresponding masks of that object in the subsequent frames.

CLIP exhibits strong visual-textual alignment but struggle with open-vocabulary segmentation due to poor localization. Prior methods enhance spatial coherence by modifying intermediate attention. But, this coherence isn't consistently propagated to the final output due to subsequent operations such as projections. Additionally, intermediate attention lacks direct interaction with text representations, such semantic discrepancy limits the full potential of CLIP. In this work, we propose a training-free, feedback-driven self-adaptive framework that adapts output-based patch-level correspondences back to the intermediate attention. The output predictions, being the culmination of the model's processing, encapsulate the most comprehensive visual and textual semantics about each patch. Our approach enhances semantic consistency between internal representations and final predictions by leveraging the model's outputs as a stronger spatial coherence prior. We design key modules, including attention isolation, confidence-based pruning for sparse adaptation, and adaptation ensemble, to effectively feedback the output coherence cues. Our method functions as a plug-in module, seamlessly integrating into four state-of-the-art approaches with three backbones (ViT-B, ViT-L, ViT-H). We further validate our framework across multiple attention types (Q-K, self-self, and Proxy augmented with MAE, SAM, and DINO). Our approach consistently improves their performance across eight benchmarks.

Environmental exposure to fluoride is a major public health concern, particularly in regions with naturally elevated fluoride concentrations. Accurate modeling of fluoride-related health risks, such as dental fluorosis, requires spatially aware learning frameworks capable of capturing both geographic and semantic heterogeneity. In this work, we propose Spatially Directional Dual-Attention Graph Attention Network (SDD-GAT), a novel spatial graph neural network designed for fine-grained health risk prediction. SDD-GAT introduces a dual-graph architecture that disentangles geographic proximity and attribute similarity, and incorporates a directional attention mechanism that explicitly encodes spatial orientation and distance into the message passing process. To further enhance spatial coherence, we introduce a spatial smoothness regularization term that enforces consistency in predictions across neighboring locations. We evaluate SDD-GAT on a large-scale dataset covering over 50,000 fluoride monitoring samples and fluorosis records across Guizhou Province, China. Results show that SDD-GAT significantly outperforms traditional models and state-of-the-art GNNs in both regression and classification tasks, while also exhibiting improved spatial autocorrelation as measured by Moran's I. Our framework provides a generalizable foundation for spatial health risk modeling and geospatial learning under complex environmental settings.

Effective resource management and environmental planning in regions with high climatic variability, such as Chile, demand advanced predictive tools. This study addresses this challenge by employing an innovative and computationally efficient hybrid methodology that integrates machine learning (ML) methods for time series forecasting with established statistical techniques. The spatiotemporal data undergo decomposition using time-dependent Empirical Orthogonal Functions (EOFs), denoted as \(\phi_{k}(t)\), and their corresponding spatial coefficients, \(\alpha_{k}(s)\), to reduce dimensionality. Wavelet analysis provides high-resolution time and frequency information from the \(\phi_{k}(t)\) functions, while neural networks forecast these functions within a medium-range horizon \(h\). By utilizing various ML models, particularly a Wavelet - ANN hybrid model, we forecast \(\phi_{k}(t+h)\) up to a time horizon \(h\), and subsequently reconstruct the spatiotemporal data using these extended EOFs. This methodology is applied to a grid of climate data covering the territory of Chile. It transitions from a high-dimensional multivariate spatiotemporal data forecasting problem to a low-dimensional univariate forecasting problem. Additionally, cluster analysis with Dynamic Time Warping for defining similarities between rainfall time series, along with spatial coherence and predictability assessments, has been instrumental in identifying geographic areas where model performance is enhanced. This approach also elucidates the reasons behind poor forecast performance in regions or clusters with low spatial coherence and predictability. By utilizing cluster medoids, the forecasting process becomes more practical and efficient. This compound approach significantly reduces computational complexity while generating forecasts of reasonable accuracy and utility.

Diffractive neural networks hold great promise for applications requiring intensive computational processing. Considerable attention has focused on diffractive networks for either spatially coherent or spatially incoherent illumination. Here we illustrate that, as opposed to imaging systems, in diffractive networks the degree of spatial coherence has a dramatic effect. In particular, we show that when the spatial coherence length on the object is comparable to the minimal feature size preserved by the optical system, neither the incoherent nor the coherent extremes serve as acceptable approximations. Importantly, this situation is inherent to many settings involving active illumination, including reflected light microscopy, autonomous vehicles and smartphones. Following this observation, we propose a general framework for training diffractive networks for any specified degree of spatial and temporal coherence, supporting all types of linear and nonlinear layers. Using our method, we numerically optimize networks for image classification, and thoroughly investigate their performance dependence on the illumination coherence properties. We further introduce the concept of coherence-blind networks, which have enhanced resilience to changes in illumination conditions. Our findings serve as a steppingstone toward adopting all-optical neural networks in real-world applications, leveraging nothing but natural light.

Attention mechanisms and non-local mean operations in general are key ingredients in many state-of-the-art deep learning techniques. In particular, the Transformer model based on multi-head self-attention has recently achieved great success in natural language processing and computer vision. However, the vanilla algorithm computing the Transformer of an image with n pixels has O(n^2) complexity, which is often painfully slow and sometimes prohibitively expensive for large-scale image data. In this paper, we propose a fast randomized algorithm --- SCRAM --- that only requires O(n log(n)) time to produce an image attention map. Such a dramatic acceleration is attributed to our insight that attention maps on real-world images usually exhibit (1) spatial coherence and (2) sparse structure. The central idea of SCRAM is to employ PatchMatch, a randomized correspondence algorithm, to quickly pinpoint the most compatible key (argmax) for each query first, and then exploit that knowledge to design a sparse approximation to non-local mean operations. Using the argmax (mode) to dynamically construct the sparse approximation distinguishes our algorithm from all of the existing sparse approximate methods and makes it very efficient. Moreover, SCRAM is a broadly applicable approximation to any non-local mean layer in contrast to some other sparse approximations that can only approximate self-attention. Our preliminary experimental results suggest that SCRAM is indeed promising for speeding up or scaling up the computation of attention maps in the Transformer.

One essential step to realize modern driver assistance technology is the accurate knowledge about the location of static objects in the environment. In this work, we use artificial neural networks to predict the occupation state of a whole scene in an end-to-end manner. This stands in contrast to the traditional approach of accumulating each detection's influence on the occupancy state and allows to learn spatial priors which can be used to interpolate the environment's occupancy state. We show that these priors make our method suitable to predict dense occupancy estimations from sparse, highly uncertain inputs, as given by automotive radars, even for complex urban scenarios. Furthermore, we demonstrate that these estimations can be used for large-scale mapping applications.

Linear dimensionality reduction techniques are powerful tools for image analysis as they allow the identification of important features in a data set. In particular, nonnegative matrix factorization (NMF) has become very popular as it is able to extract sparse, localized and easily interpretable features by imposing an additive combination of nonnegative basis elements. Nonnegative matrix underapproximation (NMU) is a closely related technique that has the advantage to identify features sequentially. In this paper, we propose a variant of NMU that is particularly well suited for image analysis as it incorporates the spatial information, that is, it takes into account the fact that neighboring pixels are more likely to be contained in the same features, and favors the extraction of localized features by looking for sparse basis elements. We show that our new approach competes favorably with comparable state-of-the-art techniques on synthetic, facial and hyperspectral image data sets.