Hyunseok Oh [CV]

selected publications

1. Papez: Resource-Efficient Speech Separation with Auditory Working Memory.

   Oh, Hyunseok, Yi, Juehon, and Lee, Youngki

   In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023

   Abs

   Transformer-based models recently reached state-of-the-art single-channel speech separation accuracy; However, their extreme computational load makes it difficult to deploy them in resource-constrained mobile or IoT devices. We thus present Papez, a lightweight and computation-efficient single-channel speech separation model. Papez is based on three key techniques. We first replace the inter-chunk Transformer with small-sized auditory working memory. Second, we adaptively prune the input tokens that do not need further processing. Finally, we reduce the number of parameters through the recurrent transformer. Our extensive evaluation shows that Papez achieves the best resource and accuracy tradeoffs with a large margin. We publicly share our source code at https://github.com/snuhcs/Papez.

2. VECA: A New Benchmark for General Cognitive Development.

   Park, Kwanyoung*, Oh, Hyunseok*, and Lee, Youngki (*Co-primary)

   In Proceedings of the 2022 AAAI Conference on Artificial Intelligence 2022

   Abs PDF

   The developmental approach, simulating a cognitive development of a human, arises as a way to nurture a human-level commonsense and overcome the limitations of data-driven approaches. However, neither a virtual environment nor an evaluation platform exists for the overall development of core cognitive skills. We present the VECA(Virtual Environment for Cognitive Assessment), which consists of two main components: (i) a first benchmark to assess the overall cognitive development of an AI agent, and (ii) a novel toolkit to generate diverse and distinct cognitive tasks. VECA benchmark virtually implements the cognitive scale of Bayley Scales of Infant and Toddler Development-IV(Bayley-4), the gold-standard developmental assessment for human infants and toddlers. Our VECA toolkit provides a human toddler-like embodied agent with various human-like perceptual features crucial to human cognitive development, e.g., binocular vision, 3D-spatial audio, and tactile receptors. We compare several modern RL algorithms on our VECA benchmark and seek their limitations in modeling human-like cognitive development. We further analyze the validity of the VECA benchmark, as well as the effect of human-like sensory characteristics on cognitive skills.

3. Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents

   Park, Junseok, Park, Kwanyoung,  Oh, Hyunseok, Lee, Ganghun, Lee, Minsu, Lee, Youngki, and Zhang, Byoung-Tak

   In Proceedings of the 2021 International Conference on Multimodal Interaction 2021

   Abs HTML PDF

   Critical periods are phases during which a toddler?�s brain develops in spurts. To promote children?�s cognitive development, proper guidance is critical in this stage. However, it is not clear whether such a critical period also exists for the training of AI agents. Similar to human toddlers, well-timed guidance and multimodal interactions might significantly enhance the training efficiency of AI agents as well. To validate this hypothesis, we adapt this notion of critical periods to learning in AI agents and investigate the critical period in the virtual environment for AI agents. We formalize the critical period and Toddler-guidance learning in the reinforcement learning (RL) framework. Then, we built up a toddler-like environment with VECA toolkit to mimic human toddlers??learning characteristics.We study three discrete levels of mutual interaction: weak-mentor guidance (sparse reward), moderate mentor guidance (helper-reward), and mentor demonstration (behavioral cloning). We also introduce the EAVE dataset consisting of 30,000 real-world images to fully reflect the toddler?�s viewpoint. We evaluate the impact of critical periods on AI agents from two perspectives: how and when they are guided best in both uni- and multimodal learning. Our experimental results show that both uni- and multimodal agents with moderate mentor guidance and critical period on 1 million and 2 million training steps show a noticeable improvement. We validate these results with transfer learning on the EAVE dataset and find the performance advancement on the same critical period and the guidance.

4. Learning task-agnostic representation via toddler-inspired learning

   Park, Kwanyoung, Park, Junseok,  Oh, Hyunseok, Zhang, Byoung-Tak, and Lee, Youngki

   NeurIPS 2020 Workshop on BabyMind 2020

   Abs HTML PDF

   One of the inherent limitations of current AI systems, stemming from the passive learning mechanisms (e.g., supervised learning), is that they perform well on labeled datasets but cannot deduce knowledge on their own. To tackle this problem, we derive inspiration from a highly intentional learning system via action: the toddler. Inspired by the toddler?�s learning procedure, we design an interactive agent that can learn and store task-agnostic visual representation while exploring and interacting with objects in the virtual environment. Experimental results show that such obtained representation was expandable to various vision tasks such as image classification, object localization, and distance estimation tasks. In specific, the proposed model achieved 100%, 75.1% accuracy and 1.62% relative error, respectively, which is noticeably better than autoencoder-based model (99.7%, 66.1%, 1.95%), and also comparable with those of supervised models (100%, 87.3%, 0.71%).