Machine learning models usually assume that a set of feature values used to obtain an output is fixed in advance. However, in many real-world problems, a cost is associated with measuring these features. To address the issue of reducing measurement costs, various methods have been proposed to dynamically select which features to measure, but existing methods assume that the set of measurable features remains constant, which makes them unsuitable for cases where the set of measurable features varies from instance to instance. To overcome this limitation, we define a new problem setting for Dynamic Feature Selection (DFS) with variable feature sets and propose a deep learning method that utilizes prior information about each feature, referred to as ''features of features''. Experimental results on several datasets demonstrate that the proposed method effectively selects features based on the prior information, even when the set of measurable features changes from instance to instance.
Voice conversion (VC) has made progress in feature disentanglement, but it is still difficult to balance timbre and content information. This paper evaluates the pre-trained model features commonly used in voice conversion, and proposes an innovative method for disentangling speech feature representations. Specifically, we first propose an ideal content feature, referred to as the average feature, which is calculated by averaging the features within frame-level aligned parallel speech (FAPS) data. For generating FAPS data, we utilize a technique that involves freezing the duration predictor in a Text-to-Speech system and manipulating speaker embedding. To fit the average feature on traditional VC datasets, we then design the AVENet to take features as input and generate closely matching average features. Experiments are conducted on the performance of AVENet-extracted features within a VC system. The experimental results demonstrate its superiority over multiple current speech feature disentangling methods. These findings affirm the effectiveness of our disentanglement approach.
Depth estimation plays a pivotal role in advancing human-robot interactions, especially in indoor environments where accurate 3D scene reconstruction is essential for tasks like navigation and object handling. Monocular depth estimation, which relies on a single RGB camera, offers a more affordable solution compared to traditional methods that use stereo cameras or LiDAR. However, despite recent progress, many monocular approaches struggle with accurately defining depth boundaries, leading to less precise reconstructions. In response to these challenges, this study introduces a novel depth estimation framework that leverages latent space features within a deep convolutional neural network to enhance the precision of monocular depth maps. The proposed model features dual encoder-decoder architecture, enabling both color-to-depth and depth-to-depth transformations. This structure allows for refined depth estimation through latent space encoding. To further improve the accuracy of depth boundaries and local features, a new loss function is introduced. This function combines latent loss with gradient loss, helping the model maintain the integrity of depth boundaries. The framework is t
Pose estimation and human action recognition (HAR) are pivotal technologies spanning various domains. While the image-based pose estimation and HAR are widely admired for their superior performance, they lack in privacy protection and suboptimal performance in low-light and dark environments. This paper exploits the capabilities of millimeter-wave (mmWave) radar technology for human pose estimation by processing radar data with Graph Neural Network (GNN) architecture, coupled with the attention mechanism. Our goal is to capture the finer details of the radar point cloud to improve the pose estimation performance. To this end, we present a unique feature extraction technique that exploits the full potential of the GNN processing method for pose estimation. Our model mmGAT demonstrates remarkable performance on two publicly available benchmark mmWave datasets and establishes new state of the art results in most scenarios in terms of human pose estimation. Our approach achieves a noteworthy reduction of pose estimation mean per joint position error (MPJPE) by 35.6% and PA-MPJPE by 14.1% from the current state of the art benchmark within this domain.
Tooth image segmentation is a cornerstone of dental digitization. However, traditional image encoders relying on fixed-resolution feature maps often lead to discontinuous segmentation and poor discrimination between target regions and background, due to insufficient modeling of environmental and global context. Moreover, transformer-based self-attention introduces substantial computational overhead because of its quadratic complexity (O(n^2)), making it inefficient for high-resolution dental images. To address these challenges, we introduce a three-stage encoder with hierarchical feature representation to capture scale-adaptive information in dental images. By jointly leveraging low-level details and high-level semantics through cross-scale feature fusion, the model effectively preserves fine structural information while maintaining strong contextual awareness. Furthermore, a bidirectional sequence modeling strategy is incorporated to enhance global spatial context understanding without incurring high computational cost. We validate our method on two dental datasets, with experimental results demonstrating its superiority over existing approaches. On the OralVision dataset, our mod
Different layers of deep convolutional neural networks(CNNs) can encode different-level information. High-layer features always contain more semantic information, and low-layer features contain more detail information. However, low-layer features suffer from the background clutter and semantic ambiguity. During visual recognition, the feature combination of the low-layer and high-level features plays an important role in context modulation. If directly combining the high-layer and low-layer features, the background clutter and semantic ambiguity may be caused due to the introduction of detailed information. In this paper, we propose a general network architecture to concatenate CNN features of different layers in a simple and effective way, called Selective Feature Connection Mechanism (SFCM). Low-level features are selectively linked to high-level features with a feature selector which is generated by high-level features. The proposed connection mechanism can effectively overcome the above-mentioned drawbacks. We demonstrate the effectiveness, superiority, and universal applicability of this method on multiple challenging computer vision tasks, including image classification, scen
Modern datasets often contain large subsets of correlated features and nuisance features, which are not or loosely related to the main underlying structures of the data. Nuisance features can be identified using the Laplacian score criterion, which evaluates the importance of a given feature via its consistency with the Graph Laplacians' leading eigenvectors. We demonstrate that in the presence of large numbers of nuisance features, the Laplacian must be computed on the subset of selected features rather than on the complete feature set. To do this, we propose a fully differentiable approach for unsupervised feature selection, utilizing the Laplacian score criterion to avoid the selection of nuisance features. We employ an autoencoder architecture to cope with correlated features, trained to reconstruct the data from the subset of selected features. Building on the recently proposed concrete layer that allows controlling for the number of selected features via architectural design, simplifying the optimization process. Experimenting on several real-world datasets, we demonstrate that our proposed approach outperforms similar approaches designed to avoid only correlated or nuisance
This work explores nonparametric methods which aim at synthesizing audio from low-dimensionnal acoustic features typically used in MIR frameworks. Several issues prevent this task to be straightforwardly achieved. Such features are designed for analysis and not for synthesis, thus favoring high-level description over easily inverted acoustic representation. Whereas some previous studies already considered the problem of synthesizing audio from features such as Mel-Frequency Cepstral Coefficients, they mainly relied on the explicit formula used to compute those features in order to inverse them. Here, we instead adopt a simple blind approach, where arbitrary sets of features can be used during synthesis and where reconstruction is exemplar-based. After testing the approach on a speech synthesis from well known features problem, we apply it to the more complex task of inverting songs from the Million Song Dataset. What makes this task harder is twofold. First, that features are irregularly spaced in the temporal domain according to an onset-based segmentation. Second the exact method used to compute these features is unknown, although the features for new audio can be computed using
We study the effects of a class of features of the potential of slow-roll inflationary models corresponding to a step symmetrically dumped by an even power negative exponential factor, which we call local features. Local-type features differ from other branch-type features considered previously, because the potential is only affected in a limited range of the scalar field value, and are symmetric respect to the location of the feature. This type of features only affects the spectrum and bispectrum in a narrow range of scales which leave the horizon during the time interval corresponding to the modification of the potential. On the contrary branch-type features have effects on all the perturbation modes leaving the horizon when the field value is within the interval defining the branch, introducing for example differences in the power spectrum between large and small scale which are absent in the case of local-type features. The spectrum and bispectrum of primordial curvature perturbations are affected by oscillations around the scale $k_0$ exiting the horizon at the time $τ_0$ corresponding to the feature. We also compute the effects of the features on the CMB temperature and polar
In this paper we demonstrate predicting electroencephalograpgy (EEG) features from acoustic features using recurrent neural network (RNN) based regression model and generative adversarial network (GAN). We predict various types of EEG features from acoustic features. We compare our results with the previously studied problem on speech synthesis using EEG and our results demonstrate that EEG features can be generated from acoustic features with lower root mean square error (RMSE), normalized RMSE values compared to generating acoustic features from EEG features (ie: speech synthesis using EEG) when tested using the same data sets.
Synthetic-voice cloning technologies have seen significant advances in recent years, giving rise to a range of potential harms. From small- and large-scale financial fraud to disinformation campaigns, the need for reliable methods to differentiate real and synthesized voices is imperative. We describe three techniques for differentiating a real from a cloned voice designed to impersonate a specific person. These three approaches differ in their feature extraction stage with low-dimensional perceptual features offering high interpretability but lower accuracy, to generic spectral features, and end-to-end learned features offering less interpretability but higher accuracy. We show the efficacy of these approaches when trained on a single speaker's voice and when trained on multiple voices. The learned features consistently yield an equal error rate between 0% and 4%, and are reasonably robust to adversarial laundering.
With the rise of short video platforms in global communication, embedding steganographic data in audio synchronization streams has emerged as a new covert communication method. To address the limitations of traditional techniques in detecting synchronized steganography, this paper proposes a detection and distributed guidance reconstruction model based on short video "Yupan" samples released by China's South Sea Fleet on TikTok. The method integrates sliding spectrum feature extraction and intelligent inference mechanisms. A 25 ms sliding window with short-time Fourier transform (STFT) is used to extract the main frequency trajectory and construct the synchronization frame detection model (M1), identifying a frame flag "FFFFFFFFFFFFFFFFFF80". The subsequent 32-byte payload is decoded by a structured model (M2) to infer distributed guidance commands. Analysis reveals a low-entropy, repetitive byte sequence in the 36 to 45 second audio segment with highly concentrated spectral energy, confirming the presence of synchronization frames. Although plaintext semantics are not restored, the consistency in command field layout suggests features of military communication protocols. The multi
Conditional music generation offers significant advantages in terms of user convenience and control, presenting great potential in AI-generated content research. However, building conditional generative systems for multitrack popular songs presents three primary challenges: insufficient fidelity of input conditions, poor structural modeling, and inadequate inter-track harmony learning in generative models. To address these issues, we propose BandCondiNet, a conditional model based on parallel Transformers, designed to process the multiple music sequences and generate high-quality multitrack samples. Specifically, we propose multi-view features across time and instruments as high-fidelity conditions. Moreover, we propose two specialized modules for BandCondiNet: Structure Enhanced Attention (SEA) to strengthen the musical structure, and Cross-Track Transformer (CTT) to enhance inter-track harmony. We conducted both objective and subjective evaluations on two popular music datasets with different sequence lengths. Objective results on the shorter dataset show that BandCondiNet outperforms other conditional models in 9 out of 10 metrics related to fidelity and inference speed, with th
Not all real-world data are labeled, and when labels are not available, it is often costly to obtain them. Moreover, as many algorithms suffer from the curse of dimensionality, reducing the features in the data to a smaller set is often of great utility. Unsupervised feature selection aims to reduce the number of features, often using feature importance scores to quantify the relevancy of single features to the task at hand. These scores can be based only on the distribution of variables and the quantification of their interactions. The previous literature, mainly investigating anomaly detection and clusters, fails to address the redundancy-elimination issue. We propose an evaluation of correlations among features to compute feature importance scores representing the contribution of single features in explaining the dataset's structure. Based on Coalitional Game Theory, our feature importance scores include a notion of redundancy awareness making them a tool to achieve redundancy-free feature selection. We show that the deriving features' selection outperforms competing methods in lowering the redundancy rate while maximizing the information contained in the data. We also introduce
This paper introduces a novel network topology that seamlessly integrates dynamic inference cost with a top-down attention mechanism, addressing two significant gaps in traditional deep learning models. Drawing inspiration from human perception, we combine sequential processing of generic low-level features with parallelism and nesting of high-level features. This design not only reflects a finding from recent neuroscience research regarding - spatially and contextually distinct neural activations - in human cortex, but also introduces a novel "cutout" technique: the ability to selectively activate %segments of the network for task-relevant only network segments of task-relevant categories to optimize inference cost and eliminate the need for re-training. We believe this paves the way for future network designs that are lightweight and adaptable, making them suitable for a wide range of applications, from compact edge devices to large-scale clouds. Our proposed topology also comes with a built-in top-down attention mechanism, which allows processing to be directly influenced by either enhancing or inhibiting category-specific high-level features, drawing parallels to the selective
Predicting the output of research grants is of considerable relevance to research funding bodies, scientific entities and government agencies. In this study, we investigate whether text features extracted from projects title and abstracts are able to identify productive grants. Our analysis was conducted in three distinct areas, namely Medicine, Dentistry and Veterinary Medicine. Topical and complexity text features were used to identify predictors of productivity. The results indicate that there is a statistically significant relationship between text features and grants productivity, however such a dependence is weak. A feature relevance analysis revealed that the abstract text length and metrics derived from lexical diversity are among the most discriminative features. We also found that the prediction accuracy has a dependence on the considered project language and that topical features are more discriminative than text complexity measurements. Our findings suggest that text features should be used in combination with other features to assist the identification of relevant research ideas.
Deep learning models are known to overfit and memorize spurious features in the training dataset. While numerous empirical studies have aimed at understanding this phenomenon, a rigorous theoretical framework to quantify it is still missing. In this paper, we consider spurious features that are uncorrelated with the learning task, and we provide a precise characterization of how they are memorized via two separate terms: (i) the stability of the model with respect to individual training samples, and (ii) the feature alignment between the spurious feature and the full sample. While the first term is well established in learning theory and it is connected to the generalization error in classical work, the second one is, to the best of our knowledge, novel. Our key technical result gives a precise characterization of the feature alignment for the two prototypical settings of random features (RF) and neural tangent kernel (NTK) regression. We prove that the memorization of spurious features weakens as the generalization capability increases and, through the analysis of the feature alignment, we unveil the role of the model and of its activation function. Numerical experiments show the
Recent advancements in deep learning models have significantly enhanced jet classification performance by analyzing low-level features (LLFs). However, this approach often leads to less interpretable models, emphasizing the need to understand the decision-making process and to identify the high-level features (HLFs) crucial for explaining jet classification. To address this, we consider the top jet tagging problems and introduce an analysis model (AM) that analyzes selected HLFs designed to capture important features of top jets. Our AM mainly consists of the following three modules: a relation network analyzing two-point energy correlations, mathematical morphology and Minkowski functionals for generalizing jet constituent multiplicities, and a recursive neural network analyzing subjet constituent multiplicity to enhance sensitivity to subjet color charges. We demonstrate that our AM achieves performance comparable to the Particle Transformer (ParT) while requiring fewer computational resources in a comparison of top jet tagging using jets simulated at the hadronic calorimeter angular resolution scale. Furthermore, as a more constrained architecture than ParT, the AM exhibits smal
The Tanimoto coefficient is commonly used to measure the similarity between molecules represented as discrete fingerprints, either as a distance metric or a positive definite kernel. While many kernel methods can be accelerated using random feature approximations, at present there is a lack of such approximations for the Tanimoto kernel. In this paper we propose two kinds of novel random features to allow this kernel to scale to large datasets, and in the process discover a novel extension of the kernel to real-valued vectors. We theoretically characterize these random features, and provide error bounds on the spectral norm of the Gram matrix. Experimentally, we show that these random features are effective at approximating the Tanimoto coefficient of real-world datasets and are useful for molecular property prediction and optimization tasks.
Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by adversarial perturbation and lead to an unexpectedly increasing gap between features in the last hidden layer of natural and adversarial samples. To address this issue, we propose a disentanglement-based approach to explicitly model and further remove the specific latent features. We introduce a feature disentangler to separate out the specific latent features from the features of the adversarial samples, thereby boosting robustness by eliminating the specific latent features. Besides, we align clean features in the pre-trained model with features of adversarial samples in the fine-tuned model, to benefit from the intrinsic features of natural samples. Empirical evaluations on three benchmark datasets demonstrate that our approach surpasses existing adversarial fine-tuning methods and adversarial training baselines.