Pose-guided 3D human generation in indoor scene Authors: Minseok Kim, Changwoo Kang, Jeongin Park, Kyungdon Joo ABSTRACT In this work, we address the problem of scene-aware 3D human avatar generation based on human-scene interactions. In particular, we pay attention to the fact that physical contact between a...
Diffusion-Based Signed Distance Fields for 3D Shape Generation Jaehyeok Shim, Changwoo Kang, Kyungdon Joo; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 20887-20897 Abstract We propose a 3D shape generation framework (SDF-Diffusion in short) that uses denoising diffusion models with continuous 3D...
NTT-PIM: Row-Centric Architecture and Mapping for Efficient Number-Theoretic Transform on PIM Jaewoo Park, Sugil Lee, Jongeun Lee Recently DRAM-based PIMs (processing-in-memories) with unmodified cell arrays have demonstrated impressive performance for accelerating AI applications. However, due to the very restrictive hardware constraints, PIM remains an accelerator for simple functions only....
Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks Authors" Changhyeon Lee and Seulki Lee Abstract In this paper, we propose to approximate the softmax output, which is the key product of the attention mechanism, to reduce its activation memory usage when training attention-based networks (aka Transformers). During...
On-NAS: On-Device Neural Architecture Search on Memory-Constrained Intelligent Embedded Systems Authors: Bosung Kim, Seulki Lee ABSTRACT We introduce On-NAS, a memory-efficient on-device neural archi-tecture search (NAS) solution, that enables memory-constrained embedded devices to find the best deep model architecture and train it on the device. Based on the cell-based...
An Energy-Efficient GAN Processor for Mobile Image Translation Authors: Jinhoon Jo; Sangho Lee; Ghangmin Yun; Kyuho Lee Abstract: An energy-efficient generative adversarial network (GAN) accelerator is proposed for mobile image-to-image translation. In image translation, low precision bits below 8 were not employed due to significant output image quality degradation. In addition, due...
POEM: Polarization of Embeddings for Domain-Invariant Representations Sang-Yeong Jo, Sung Whan Yoon Handling out-of-distribution samples is a long-lasting challenge for deep visual models. In particular, domain generalization (DG) is one of the most relevant tasks that aims to train a model with a generalization capability on novel domains....
TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models Pum Jun Kim, Yoojin Jang, Jisu Kim, Jaejun Yoo We propose a robust and reliable evaluation metric for generative models by introducing topological and statistical treatments for rigorous support estimation. Existing metrics, such as Inception Score (IS),...
Can We Find Strong Lottery Tickets in Generative Models? Authors : Sangyeop Yeo , Yoojin Jang , Jy-yong Sohn , Dongyoon Han , Jaejun Yoo Abstract Yes. In this paper, we investigate strong lottery tickets in generative models, the subnetworks that achieve good generative performance without any weight update....
Can We Use Diffusion Probabilistic Models for 3D Motion Prediction? Hyemin Ahn, Esteve Valls Mascaro, Dongheui Lee After many researchers observed fruitfulness from the recent diffusion probabilistic model, its effectiveness in image generation is actively studied these days. In this paper, our objective is to evaluate the potential of...
