paper-with-me

홈 › Papers

Look globally, age locally: Face aging with an attention mechanism

2019-10-24 · Haiping Zhu, Zhizhong Huang, Hongming Shan, Junping Zhang

Face aging is of great importance for cross-age recognition and entertainment-related applications. Recently, conditional generative adversarial networks (cGANs) have achieved impressive results for face aging. Existing cGANs-based methods usually require a pixel-wise loss to keep the identity and background consistent. However, minimizing the pixel-wise loss between the input and synthesized images likely resulting in a ghosted or blurry face. To address this deficiency, this paper introduces an Attention Conditional GANs (AcGANs) approach for face aging, which utilizes attention mechanism to only alert the regions relevant to face aging. In doing so, the synthesized face can well preserve the background information and personal identity without using the pixel-wise loss, and the ghost artifacts and blurriness can be significantly reduced. Based on the benchmarked dataset Morph, both qualitative and quantitative experiment results demonstrate superior performance over existing algorithms in terms of image quality, personal identity, and age accuracy.

📄 PDF Abstract BibTeX arXiv:1910.12771

Code (1)

JensonZhu14/AcGAN 공식 구현 pytorch

Tasks

MORPH

Similar Papers 제목 키워드 기반

Locally Controlled Face Aging with Latent Diffusion Models

2025-07-29 · Lais Isabelle Alves dos Santos, Julien Despois, Thibaut Chauffier, Sileye O. Ba 외 arxiv

We present a novel approach to face aging that addresses the limitations of current methods which treat aging as a global, homogeneous process. Existing techniques using GANs and diffusion models often condition generati…

Look Locally Infer Globally: A Generalizable Face Anti-Spoofing Approach

2020-06-04 · Debayan Deb, Anil K. Jain

State-of-the-art spoof detection methods tend to overfit to the spoof types seen during training and fail to generalize to unknown spoof types. Given that face anti-spoofing is inherently a local task, we propose a face …

Computational EfficiencyFace Anti-SpoofingGPU

Rate Region of RIS-Aided URLLC Broadcast Channels: Diagonal versus Beyond Diagonal Globally Passive RIS

2024-10-28 · Mohammad Soleymani, Alessio Zappone, Eduard Jorswieck, Marco Di Renzo 외

We analyze the finite-block-length rate region of wireless systems aided by reconfigurable intelligent surfaces (RISs), employing treating interference as noise. We consider three nearly passive RIS architectures, includ…

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

2025-10-15 · Yang Li, Zhichen Dong, Yuhan Sun, Weixun Wang 외 arxiv

The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine ste…

Reinforcement Learning

Energy Efficiency Comparison of RIS Architectures in MISO Broadcast Channels

2024-08-08 · Mohammad Soleymani, Ignacio Santamaria, Eduard Jorswieck, Marco Di Renzo 외

In this paper, we develop energy-efficient schemes for multi-user multiple-input single-output (MISO) broadcast channels (BCs), assisted by reconfigurable intelligent surfaces (RISs). To this end, we consider three archi…