arXiv subjects

Yu-Chao Gu

Publications and source records attributed to Yu-Chao Gu.

4 recordsLinked to original sources

arXiv2023

Mirror QCD phase transition as the origin of the nanohertz Stochastic Gravitational-Wave Background

Several Pulsar Timing Array (PTA) collaborations have recently provided strong evidence for a nHz Stochastic Gravitational-Wave Background (SGWB). Here we investigate the implications of a first-order phase transition occurring within the early universe's dark quantum chromodynamics (dQCD) epoch, specifically within the framework of the mirror twin Higgs dark sector model. Our analysis indicates a distinguishable SGWB signal originating from this phase transition, which can explain the measurements obtained by PTAs. Remarkably, a significant portion of the parameter space for the SGWB signal also effectively resolves the existing tensions in both the $H_0$ and $S_8$ measurements in Cosmology. This intriguing correlation suggests a possible common origin of these three phenomena for $0.2 < \Delta N_{\rm eff} < 0.5$, where the mirror dark matter component constitutes about $30\%$ of the total dark matter abundance. Next generation CMB experiment such as CMB-S4 is able to test this parameter region.

astro-ph.HE↗

arXiv2022

MobileSal: Extremely Efficient RGB-D Salient Object Detection

The high computational cost of neural networks has prevented recent successes in RGB-D salient object detection (SOD) from benefiting real-world applications. Hence, this paper introduces a novel network, MobileSal, which focuses on efficient RGB-D SOD using mobile networks for deep feature extraction. However, mobile networks are less powerful in feature representation than cumbersome networks. To this end, we observe that the depth information of color images can strengthen the feature representation related to SOD if leveraged properly. Therefore, we propose an implicit depth restoration (IDR) technique to strengthen the mobile networks' feature representation capability for RGB-D SOD. IDR is only adopted in the training phase and is omitted during testing, so it is computationally free. Besides, we propose compact pyramid refinement (CPR) for efficient multi-level feature aggregation to derive salient objects with clear boundaries. With IDR and CPR incorporated, MobileSal performs favorably against state-of-the-art methods on six challenging RGB-D SOD datasets with much faster speed (450fps for the input size of 320 $\times$ 320) and fewer parameters (6.5M). The code is released at https://mmcheng.net/mobilesal.

cs.CV↗

arXiv2021

DOTS: Decoupling Operation and Topology in Differentiable Architecture Search

Differentiable Architecture Search (DARTS) has attracted extensive attention due to its efficiency in searching for cell structures. DARTS mainly focuses on the operation search and derives the cell topology from the operation weights. However, the operation weights can not indicate the importance of cell topology and result in poor topology rating correctness. To tackle this, we propose to Decouple the Operation and Topology Search (DOTS), which decouples the topology representation from operation weights and makes an explicit topology search. DOTS is achieved by introducing a topology search space that contains combinations of candidate edges. The proposed search space directly reflects the search objective and can be easily extended to support a flexible number of edges in the searched cell. Existing gradient-based NAS methods can be incorporated into DOTS for further improvement by the topology search. Considering that some operations (e.g., Skip-Connection) can affect the topology, we propose a group operation search scheme to preserve topology-related operations for a better topology search. The experiments on CIFAR10/100 and ImageNet demonstrate that DOTS is an effective solution for differentiable NAS.

cs.CV↗

arXiv2020

Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow

Generalized zero-shot learning (GZSL) aims to recognize both seen and unseen classes by transferring knowledge from semantic descriptions to visual representations. Recent generative methods formulate GZSL as a missing data problem, which mainly adopts GANs or VAEs to generate visual features for unseen classes. However, GANs often suffer from instability, and VAEs can only optimize the lower bound on the log-likelihood of observed data. To overcome the above limitations, we resort to generative flows, a family of generative models with the advantage of accurate likelihood estimation. More specifically, we propose a conditional version of generative flows for GZSL, i.e., VAE-Conditioned Generative Flow (VAE-cFlow). By using VAE, the semantic descriptions are firstly encoded into tractable latent distributions, conditioned on that the generative flow optimizes the exact log-likelihood of the observed visual features. We ensure the conditional latent distribution to be both semantic meaningful and inter-class discriminative by i) adopting the VAE reconstruction objective, ii) releasing the zero-mean constraint in VAE posterior regularization, and iii) adding a classification regularization on the latent variables. Our method achieves state-of-the-art GZSL results on five well-known benchmark datasets, especially for the significant improvement in the large-scale setting. Code is released at https://github.com/guyuchao/VAE-cFlow-ZSL.

cs.CV↗