채널톡 ML Engineer 채용설명회 (전문연구요원 포함, 비전문연도 참여 가능) Build Real-World AI, 채널톡과 함께하세요. 아시아에서 가장 빠르게 성장하는 B2B SaaS, 채널톡에서 Machine Learning Engineer(전문연구요원) 채용 설명회를 진행합니다. ✔ 실제 서비스에 적용되는 AI는 어떻게 만들어질까? ✔ ML Engineer는 어떤 문제를 풀고 있을까? 제품, 팀, 그리고 실제 업무까지 직접 들을 수 있는 자리입니다. 설명회 이후에는 AI팀과의...
Domain Adaptive Imitation Learning with Visual Observation Sungho Choi, Seungyul Han, Woojun Kim, Jongseong Chae, Whiyoung Jung, Youngchul Sung In this paper, we consider domain-adaptive imitation learning with visual observation, where an agent in a target domain learns to perform a task by observing expert demonstrations in a source domain. Domain adaptive...
SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments Jongsung Lee, Gyeongsu Cho, Jeongin Park, Kyongjun Kim, Seongoh Lee, Jung-Hee Kim, Seong-Gyun Jeong, Kyungdon Joo; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 8765-8774 Abstract Although 3D perception for autonomous vehicles has focused...
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....
