Yu Chen

Zhiwen Yan, Weng Fei Low, Yu Chen et al.

3D Gaussians have recently emerged as a highly efficient representation for 3D reconstruction and rendering. Despite its high rendering quality and speed at high resolutions, they both deteriorate drastically when rendered at lower resolutions or from far away camera position. During low resolution or far away rendering, the pixel size of the image can fall below the Nyquist frequency compared to the screen size of each splatted 3D Gaussian and leads to aliasing effect. The rendering is also drastically slowed down by the sequential alpha blending of more splatted Gaussians per pixel. To address these issues, we propose a multi-scale 3D Gaussian splatting algorithm, which maintains Gaussians at different scales to represent the same scene. Higher-resolution images are rendered with more small Gaussians, and lower-resolution images are rendered with fewer larger Gaussians. With similar training time, our algorithm can achieve 13\%-66\% PSNR and 160\%-2400\% rendering speed improvement at 4$\times$-128$\times$ scale rendering on Mip-NeRF360 dataset compared to the single scale 3D Gaussian splitting. Our code and more results are available on our project website https://jokeryan.github.io/projects/ms-gs/

Xiangyong Lu, Kaoru Ota, Mianxiong Dong et al.

Nowadays many cities around the world have introduced electric buses to optimize urban traffic and reduce local carbon emissions. In order to cut carbon emissions and maximize the utility of electric buses, it is important to choose suitable routes for them. Traditionally, route selection is on the basis of dedicated surveys, which are costly in time and labor. In this paper, we mainly focus attention on planning electric bus routes intelligently, depending on the unique needs of each region throughout the city. We propose Clairvoyance, a route planning system that leverages a deep neural network and a multilayer perceptron to predict the future people's trips and the future transportation carbon emission in the whole city, respectively. Given the future information of people's trips and transportation carbon emission, we utilize a greedy mechanism to recommend bus routes for electric buses that will depart in an ideal state. Furthermore, representative features of the two neural networks are extracted from the heterogeneous urban datasets. We evaluate our approach through extensive experiments on real-world data sources in Zhuhai, China. The results show that our designed neural network-based algorithms are consistently superior to the typical baselines. Additionally, the recommended routes for electric buses are helpful in reducing the peak value of carbon emissions and making full use of electric buses in the city.

Xianglong Tan, Zhikang Liu, Chen Yu et al.

Robots with the ability to actively acquire power from surroundings will be greatly beneficial for long-term autonomy and to survive in uncertain environments. In this work, we present a robot capable of drawing circuits with conductive ink while also rearranging the visual world to receive maximum energy from a power source. A range of circuit drawing tasks is designed to simulate real-world scenarios, including avoiding physical obstacles and regions that would discontinue drawn circuits. We adopt the state-of-the-art Transporter networks for pick-and-place manipulation from visual observation. We conduct experiments in both simulation and real-world settings, and our results show that, with a small number of demonstrations, the robot learns to rearrange the placement of objects (removing obstacles and bridging areas unsuitable for drawing) and to connect a power source with a minimum amount of conductive ink. As autonomous robots become more present, in our houses and other planets, our proposed method brings a novel way for machines to keep themselves functional by rearranging their surroundings to create their own electric circuits.

Satoshi Tsutsui, David Crandall, Chen Yu

We analyze egocentric views of attended objects from infants. This paper shows 1) empirical evidence that children's egocentric views have more diverse distributions compared to adults' views, 2) we can computationally simulate the infants' distribution, and 3) the distribution is beneficial for training more generalized image classifiers not only for infant egocentric vision but for third-person computer vision.

Yiming Li, Shan Liu, Yu Chen et al.

As the successor of H.265/HEVC, the new versatile video coding standard (H.266/VVC) can provide up to 50% bitrate saving with the same subjective quality, at the cost of increased decoding complexity. To accelerate the application of the new coding standard, a real-time H.266/VVC software decoder that can support various platforms is implemented, where SIMD technologies, parallelism optimization, and the acceleration strategies based on the characteristics of each coding tool are applied. As the mobile devices have become an essential carrier for video services nowadays, the mentioned optimization efforts are not only implemented for the x86 platform, but more importantly utilized to highly optimize the decoding performance on the ARM platform in this work. The experimental results show that when running on the Apple A14 SoC (iPhone 12pro), the average single-thread decoding speed of the present implementation can achieve 53fps (RA and LB) for full HD (1080p) bitstreams generated by VTM-11.0 reference software using 8bit Common Test Conditions (CTC). When multi-threading is enabled, an average of 32 fps (RA) can be achieved when decoding the 4K bitstreams.

Yingqiu Zhu, Yu Chen, Danyang Huang et al.

In deep learning tasks, the learning rate determines the update step size in each iteration, which plays a critical role in gradient-based optimization. However, the determination of the appropriate learning rate in practice typically replies on subjective judgement. In this work, we propose a novel optimization method based on local quadratic approximation (LQA). In each update step, given the gradient direction, we locally approximate the loss function by a standard quadratic function of the learning rate. Then, we propose an approximation step to obtain a nearly optimal learning rate in a computationally efficient way. The proposed LQA method has three important features. First, the learning rate is automatically determined in each update step. Second, it is dynamically adjusted according to the current loss function value and the parameter estimates. Third, with the gradient direction fixed, the proposed method leads to nearly the greatest reduction in terms of the loss function. Extensive experiments have been conducted to prove the strengths of the proposed LQA method.

Satoshi Tsutsui, Dian Zhi, Md Alimoor Reza et al.

Inspired by the remarkable ability of the infant visual learning system, a recent study collected first-person images from children to analyze the `training data' that they receive. We conduct a follow-up study that investigates two additional directions. First, given that infants can quickly learn to recognize a new object without much supervision (i.e. few-shot learning), we limit the number of training images. Second, we investigate how children control the supervision signals they receive during learning based on hand manipulation of objects. Our experimental results suggest that supervision with hand manipulation is better than without hands, and the trend is consistent even when a small number of images is available.

Yu Chen, Tom Diethe, Neil Lawrence

Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the knowledge of previous tasks while learning a new task, a phenomenon known as catastrophic forgetting. When using Bayesian models in continual learning, knowledge from previous tasks can be retained in two ways: 1). posterior distributions over the parameters, containing the knowledge gained from inference in previous tasks, which then serve as the priors for the following task; 2). coresets, containing knowledge of data distributions of previous tasks. Here, we show that Bayesian continual learning can be facilitated in terms of these two means through the use of natural gradients and Stein gradients respectively.

Ying Tai, Yicong Liang, Xiaoming Liu et al.

In recent years, heatmap regression based models have shown their effectiveness in face alignment and pose estimation. However, Conventional Heatmap Regression (CHR) is not accurate nor stable when dealing with high-resolution facial videos, since it finds the maximum activated location in heatmaps which are generated from rounding coordinates, and thus leads to quantization errors when scaling back to the original high-resolution space. In this paper, we propose a Fractional Heatmap Regression (FHR) for high-resolution video-based face alignment. The proposed FHR can accurately estimate the fractional part according to the 2D Gaussian function by sampling three points in heatmaps. To further stabilize the landmarks among continuous video frames while maintaining the precise at the same time, we propose a novel stabilization loss that contains two terms to address time delay and non-smooth issues, respectively. Experiments on 300W, 300-VW and Talking Face datasets clearly demonstrate that the proposed method is more accurate and stable than the state-of-the-art models.

Weiyang Liu, Bo Dai, Ahmad Humayun et al.

In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learner. We show that the teaching complexity in the iterative case is very different from that in the batch case. Instead of constructing a minimal training set for learners, our iterative machine teaching focuses on achieving fast convergence in the learner model. Depending on the level of information the teacher has from the learner model, we design teaching algorithms which can provably reduce the number of teaching examples and achieve faster convergence than learning without teachers. We also validate our theoretical findings with extensive experiments on different data distribution and real image datasets.