Kuan-Wen Chen

Pei-Kai Huang, Tzu-Hsien Chen, Ya-Ting Chan et al.

Remote Photoplethysmography (rPPG) aims to measure physiological signals and Heart Rate (HR) from facial videos. Recent unsupervised rPPG estimation methods have shown promising potential in estimating rPPG signals from facial regions without relying on ground truth rPPG signals. However, these methods seem oblivious to interference existing in rPPG signals and still result in unsatisfactory performance. In this paper, we propose a novel De-interfered and Descriptive rPPG Estimation Network (DD-rPPGNet) to eliminate the interference within rPPG features for learning genuine rPPG signals. First, we investigate the characteristics of local spatial-temporal similarities of interference and design a novel unsupervised model to estimate the interference. Next, we propose an unsupervised de-interfered method to learn genuine rPPG signals with two stages. In the first stage, we estimate the initial rPPG signals by contrastive learning from both the training data and their augmented counterparts. In the second stage, we use the estimated interference features to derive de-interfered rPPG features and encourage the rPPG signals to be distinct from the interference. In addition, we propose an effective descriptive rPPG feature learning by developing a strong 3D Learnable Descriptive Convolution (3DLDC) to capture the subtle chrominance changes for enhancing rPPG estimation. Extensive experiments conducted on five rPPG benchmark datasets demonstrate that the proposed DD-rPPGNet outperforms previous unsupervised rPPG estimation methods and achieves competitive performances with state-of-the-art supervised rPPG methods. The code is available at: https://github.com/Pei-KaiHuang/TIFS2025-DD-rPPGNet

Pei-Kai Huang, Tzu-Hsien Chen, Ya-Ting Chan et al.

Many remote photoplethysmography (rPPG) estimation models have achieved promising performance in the training domain but often fail to accurately estimate physiological signals or heart rates (HR) in the target domains. Domain generalization (DG) or domain adaptation (DA) techniques are therefore adopted during the offline training stage to adapt the model to either unobserved or observed target domains by utilizing all available source domain data. However, in rPPG estimation problems, the adapted model usually encounters challenges in estimating target data with significant domain variation. In contrast, Test-Time Adaptation (TTA) enables the model to adaptively estimate rPPG signals in various unseen domains by online adapting to unlabeled target data without referring to any source data. In this paper, we first establish a new TTA-rPPG benchmark that encompasses various domain information and HR distributions to simulate the challenges encountered in real-world rPPG estimation. Next, we propose a novel synthetic signal-guided rPPG estimation framework to address the forgetting issue during the TTA stage and to enhance the adaptation capability of the pre-trained rPPG model. To this end, we develop a synthetic signal-guided feature learning method by synthesizing pseudo rPPG signals as pseudo ground truths to guide a conditional generator in generating latent rPPG features. In addition, we design an effective spectral-based entropy minimization technique to encourage the rPPG model to learn new target domain information. Both the generated rPPG features and synthesized rPPG signals prevent the rPPG model from overfitting to target data and forgetting previously acquired knowledge, while also broadly covering various heart rate (HR) distributions. Our extensive experiments on the TTA-rPPG benchmark show that the proposed method achieves superior performance.

Chih Yao Hu, Yang-Sen Lin, Yuna Lee et al.

We present See, Point, Fly (SPF), a training-free aerial vision-and-language navigation (AVLN) framework built atop vision-language models (VLMs). SPF is capable of navigating to any goal based on any type of free-form instructions in any kind of environment. In contrast to existing VLM-based approaches that treat action prediction as a text generation task, our key insight is to consider action prediction for AVLN as a 2D spatial grounding task. SPF harnesses VLMs to decompose vague language instructions into iterative annotation of 2D waypoints on the input image. Along with the predicted traveling distance, SPF transforms predicted 2D waypoints into 3D displacement vectors as action commands for UAVs. Moreover, SPF also adaptively adjusts the traveling distance to facilitate more efficient navigation. Notably, SPF performs navigation in a closed-loop control manner, enabling UAVs to follow dynamic targets in dynamic environments. SPF sets a new state of the art in DRL simulation benchmark, outperforming the previous best method by an absolute margin of 63%. In extensive real-world evaluations, SPF outperforms strong baselines by a large margin. We also conduct comprehensive ablation studies to highlight the effectiveness of our design choice. Lastly, SPF shows remarkable generalization to different VLMs. Project page: https://spf-web.pages.dev

Shaodi Feng, Zhuoyi Lin, Jianan Zhou et al.

Deep learning has been extensively explored to solve vehicle routing problems (VRPs), which yields a range of data-driven neural solvers with promising outcomes. However, most neural solvers are trained to tackle VRP instances in a relatively monotonous context, e.g., simplifying VRPs by using Euclidean distance between nodes and adhering to a single problem size, which harms their off-the-shelf application in different scenarios. To enhance their versatility, this paper presents a novel lifelong learning framework that incrementally trains a neural solver to manage VRPs in distinct contexts. Specifically, we propose a lifelong learner (LL), exploiting a Transformer network as the backbone, to solve a series of VRPs. The inter-context self-attention mechanism is proposed within LL to transfer the knowledge obtained from solving preceding VRPs into the succeeding ones. On top of that, we develop a dynamic context scheduler (DCS), employing the cross-context experience replay to further facilitate LL looking back on the attained policies of solving preceding VRPs. Extensive results on synthetic and benchmark instances (problem sizes up to 18k) show that our LL is capable of discovering effective policies for tackling generic VRPs in varying contexts, which outperforms other neural solvers and achieves the best performance for most VRPs.

Pei-Kai Huanga, Ya-Ting Chan, Kuan-Wen Chen et al.

Many remote Heart Rate (HR) measurement methods focus on estimating remote photoplethysmography (rPPG) signals from video clips lasting around 10 seconds but often overlook the need for HR estimation from ultra-short video clips. In this paper, we aim to accurately measure HR from ultra-short 2-second video clips by specifically addressing two key challenges. First, to overcome the limited number of heartbeat cycles in ultra-short video clips, we propose an effective periodicity-guided rPPG estimation method that enforces consistent periodicity between rPPG signals estimated from ultra-short clips and their much longer ground truth signals. Next, to mitigate estimation inaccuracies due to spectral leakage, we propose including a generator to reconstruct longer rPPG signals from ultra-short ones while preserving their periodic consistency to enable more accurate HR measurement. Extensive experiments on four rPPG estimation benchmark datasets demonstrate that our proposed method not only accurately measures HR from ultra-short video clips but also outperform previous rPPG estimation techniques to achieve state-of-the-art performance.

Nilotpal Sinha, Kuan-Wen Chen

Evolution-based neural architecture search requires high computational resources, resulting in long search time. In this work, we propose a framework of applying the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to the neural architecture search problem called CMANAS, which achieves better results than previous evolution-based methods while reducing the search time significantly. The architectures are modelled using a normal distribution, which is updated using CMA-ES based on the fitness of the sampled population. We used the accuracy of a trained one shot model (OSM) on the validation data as a prediction of the fitness of an individual architecture to reduce the search time. We also used an architecture-fitness table (AF table) for keeping record of the already evaluated architecture, thus further reducing the search time. CMANAS finished the architecture search on CIFAR-10 with the top-1 test accuracy of 97.44% in 0.45 GPU day and on CIFAR-100 with the top-1 test accuracy of 83.24% for 0.6 GPU day on a single GPU. The top architectures from the searches on CIFAR-10 and CIFAR-100 were then transferred to ImageNet, achieving the top-5 accuracy of 92.6% and 92.1%, respectively.

Nilotpal Sinha, Kuan-Wen Chen

Neural Architecture Search (NAS) is emerging as a new research direction which has the potential to replace the hand-crafted neural architectures designed for specific tasks. Previous evolution based architecture search requires high computational resources resulting in high search time. In this work, we propose a novel way of applying a simple genetic algorithm to the NAS problem called EvNAS (Evolving Neural Architecture using One Shot Model) which reduces the search time significantly while still achieving better result than previous evolution based methods. The architectures are represented by using the architecture parameter of the one shot model which results in the weight sharing among the architectures for a given population of architectures and also weight inheritance from one generation to the next generation of architectures. We propose a decoding technique for the architecture parameter which is used to divert majority of the gradient information towards the given architecture and is also used for improving the performance prediction of the given architecture from the one shot model during the search process. Furthermore, we use the accuracy of the partially trained architecture on the validation data as a prediction of its fitness in order to reduce the search time. EvNAS searches for the architecture on the proxy dataset i.e. CIFAR-10 for 4.4 GPU day on a single GPU and achieves top-1 test error of 2.47% with 3.63M parameters which is then transferred to CIFAR-100 and ImageNet achieving top-1 error of 16.37% and top-5 error of 7.4% respectively. All of these results show the potential of evolutionary methods in solving the architecture search problem.

Po-Heng Chen, Zhao-Xu Luo, Zu-Kuan Huang et al.

Feature descriptor matching is a critical step is many computer vision applications such as image stitching, image retrieval and visual localization. However, it is often affected by many practical factors which will degrade its performance. Among these factors, illumination variations are the most influential one, and especially no previous descriptor learning works focus on dealing with this problem. In this paper, we propose IF-Net, aimed to generate a robust and generic descriptor under crucial illumination changes conditions. We find out not only the kind of training data important but also the order it is presented. To this end, we investigate several dataset scheduling methods and propose a separation training scheme to improve the matching accuracy. Further, we propose a ROI loss and hard-positive mining strategy along with the training scheme, which can strengthen the ability of generated descriptor dealing with large illumination change conditions. We evaluate our approach on public patch matching benchmark and achieve the best results compared with several state-of-the-arts methods. To show the practicality, we further evaluate IF-Net on the task of visual localization under large illumination changes scenes, and achieves the best localization accuracy.

Kuan-Wen Chen, Chun-Hsin Wang, Xiao Wei et al.

Augmented reality (AR) displays become more and more popular recently, because of its high intuitiveness for humans and high-quality head-mounted display have rapidly developed. To achieve such displays with augmented information, highly accurate image registration or ego-positioning are required, but little attention have been paid for out-door environments. This paper presents a method for ego-positioning in outdoor environments with low cost monocular cameras. To reduce the computational and memory requirements as well as the communication overheads, we formulate the model compression algorithm as a weighted k-cover problem for better preserving model structures. Specifically for real-world vision-based positioning applications, we consider the issues with large scene change and propose a model update algorithm to tackle these problems. A long- term positioning dataset with more than one month, 106 sessions, and 14,275 images is constructed. Based on both local and up-to-date models constructed in our approach, extensive experimental results show that high positioning accuracy (mean ~ 30.9cm, stdev. ~ 15.4cm) can be achieved, which outperforms existing vision-based algorithms.