Pre-training strategies play a critical role in advancing the performance of transformer-based models for 3D point cloud tasks. In this paper, we introduce Point-RTD (Replaced Token Denoising), a novel pretraining strategy designed to improve token robustness through a corruption-reconstruction framework. Unlike traditional mask-based reconstruction tasks that hide data segments for later prediction, Point-RTD corrupts point cloud tokens and leverages a discriminator-generator architecture for denoising. This shift enables more effective learning of structural priors and significantly enhances model performance and efficiency. On the ShapeNet dataset, Point-RTD reduces reconstruction error by over 93% compared to PointMAE, and achieves more than 14x lower Chamfer Distance on the test set. Our method also converges faster and yields higher classification accuracy on ShapeNet, ModelNet10, and ModelNet40 benchmarks, clearly outperforming the baseline Point-MAE framework in every case. Code is available at https://github.com/GunnerStone/PointRTD.

Human gait analysis with wearable sensors has been widely used in various applications, such as daily life healthcare, rehabilitation, physical therapy, and clinical diagnostics and monitoring. In particular, ground reaction force (GRF) provides critical information about how the body interacts with the ground during locomotion. Although instrumented treadmills have been widely used as the gold standard for measuring GRF during walking, their lack of portability and high cost make them impractical for many applications. As an alternative, low-cost, portable, wearable insole sensors have been utilized to measure GRF; however, these sensors are susceptible to noise and disturbance and are less accurate than treadmill measurements. Deep learning has shown potential in addressing these issues, but such methods are computationally expensive and often require extensive computing resources, limiting their feasibility for real-time and portable systems. To address these challenges, we propose a Time-aware Knowledge Distillation framework for GRF estimation from insole sensor data. This framework leverages similarity and temporal features within a mini-batch during the knowledge distillation process, effectively capturing the complementary relationships between features and the sequential properties of the target and input data. The performance of the lightweight models distilled through this framework was evaluated by comparing GRF estimations from insole sensor data against measurements from an instrumented treadmill. Various teacher-student model architectures and learning strategies were evaluated across multiple performance metrics using data collected at different walking speeds. Empirical results demonstrated that Time-aware Knowledge Distillation outperforms current baselines in GRF estimation from wearable sensor data. Moreover, our method significantly reduces the number of training parameters needed for GRF estimation, offering a data- and resource-efficient solution for human gait analysis while achieving excellent accuracy and model reliability.

Implicit neural representations (INR) have gained significant popularity for signal and image representation for many end-tasks, such as superresolution, 3D modeling, and more. Most INR architectures rely on sinusoidal positional encoding, which accounts for high-frequency information in data. However, the finite encoding size restricts the model's representational power. Higher representational power is needed to go from representing a single given image to representing large and diverse datasets. Our approach addresses this gap by representing an image with a polynomial function and eliminates the need for positional encodings. Therefore, to achieve a progressively higher degree of polynomial representation, we use element-wise multiplications between features and affine-transformed coordinate locations after every ReLU layer. The proposed method is evaluated qualitatively and quantitatively on large datasets like ImageNet. The proposed Poly-INR model performs comparably to state-of-the-art generative models without any convolution, normalization, or self-attention layers, and with far fewer trainable parameters. With much fewer training parameters and higher representative power, our approach paves the way for broader adoption of INR models for generative modeling tasks in complex domains. The code is available at https://github.com/Rajhans0/Poly_INR

Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model. Knowledge distillation (KD), on the other hand, is widely used for model compression and transfer learning, which involves using a larger network’s implicit knowledge to guide the learning of a smaller network. At first glance, these two techniques seem very different, however, we found that "smoothness" is the connecting link between the two and is also a crucial attribute in understanding KD’s interplay with mixup. Although many mixup variants and distillation methods have been proposed, much remains to be understood regarding the role of a mixup in knowledge distillation. In this paper, we present a detailed empirical study on various important dimensions of compatibility between mixup and knowledge distillation. We also scrutinize the behavior of the networks trained with a mixup in the light of knowledge distillation through extensive analysis, visualizations, and comprehensive experiments on image classification. Finally, based on our findings, we suggest improved strategies to guide the student network to enhance its effectiveness. Additionally, the findings of this study provide insightful suggestions to researchers and practitioners that commonly use techniques from KD. Our code is available at https://github.com/hchoi71/MIX-KD.

Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems. However, the large number of parameters makes it difficult to integrate these models into edge devices such as smartphones and wearable devices. To address this problem, knowledge distillation (KD) has been widely employed, that uses a pre-trained high capacity network to train a much smaller network, suitable for edge devices. In this paper, for the first time, we study the applicability and challenges of using KD for time-series data for wearable devices. Successful application of KD requires specific choices of data augmentation methods during training. However, it is not yet known if there exists a coherent strategy for choosing an augmentation approach during KD. In this paper, we report the results of a detailed study that compares and contrasts various common choices and some hybrid data augmentation strategies in KD based human activity analysis. Research in this area is often limited as there are not many comprehensive databases available in the public domain from wearable devices. Our study considers databases from small scale publicly available to one derived from a large scale interventional study into human activity and sedentary behavior. We find that the choice of data augmentation techniques during KD have a variable level of impact on end performance, and find that the optimal network choice as well as data augmentation strategies are specific to a dataset at hand. However, we also conclude with a general set of recommendations that can provide a strong baseline performance across databases.

Many species in the wild exhibit a visual pattern that can be used to uniquely identify an individual. This observation has recently led to visual animal biometrics become a rapidly growing application area of computer vision. Customized software tools for animal biometrics already employ vision based techniques to recognize individuals in images taken in uncontrolled environments. However, most existing tools require the user to localize the animals for accurate identification. In this work, we propose a figure/ground segmentation method that automatically extracts out the animal in an image. Our method relies on a semi-supervised metric learning algorithm that uses a small amount of training data without compromising generalization performance. We design a simple pipeline comprising of superpixel segmentation, texture based feature extraction followed by mean shift clustering using the learned metric. We show that our approach can yield competitive results for figure/ground segmentation of patterned animals in images taken in the wild, often under extreme illumination conditions.

In Wireless Body Area Networks (WBAN) the energy consumption is dominated by sensing and communication. Previous techniques exploited the sparsity of the signal (in transform domains) to reduce communication costs for EEG transmission. For the first time, in this work, we propose to jointly exploit sparsity and rank-deficiency of the multi-channel signal ensemble in order to reduce both sensing and communication power consumptions. We test our method with state-of-the-art recovery techniques and find that the reconstruction accuracy from our method is considerably better and that too at lower energy consumption.

In this work we derive algorithms for solving two problems - the first one is the combined l1-norm (sparsity) and nuclear norm (low rank) regularized least squares problem and the second one is the l2, 1-norm (joint sparsity) and nuclear norm regularized least squares problem. There are no efficient general purpose solvers for these problems; our work plugs this gap by deriving Split Bregman based algorithms for solving the said problems. Both algorithms are applicable for recovering hyperspectral images from their compressive measurements obtained via the single pixel camera. We show that our proposed techniques significantly outperform previous methods in terms of recovery accuracy.

In this paper we address the problem of recovering a matrix, with inherent low rank structure, from its lower dimensional projections. This problem is frequently encountered in wide range of areas including pattern recognition, wireless sensor networks, control systems, recommender systems, image/video reconstruction etc. Both in theory and practice, the most optimal way to solve the low rank matrix recovery problem is via nuclear norm minimization. In this paper, we propose a Split Bregman algorithm for nuclear norm minimization. The use of Bregman technique improves the convergence speed of our algorithm and gives a higher success rate. Also, the accuracy of reconstruction is much better even for cases where small number of linear measurements are available. Our claim is supported by empirical results obtained using our algorithm and its comparison to other existing methods for matrix recovery. The algorithms are compared on the basis of NMSE, execution time and success rate for varying ranks and sampling ratios.