HyunJin Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
HyunJin Kim has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Alberto Antonio Del Barrio
Universidad Complutense de Madrid Facultad de Informatica
4 shared publications - Nader Bagherzadeh
University of California, Irvine
3 shared publications Seung-Rohk Oh
Dankook University
3 shared publications- SuMin Oh
Dept. of Electronics and Electrical Engineering, Dankook University, Yongin-si, Republic of Korea
3 shared publications ThienLuan Ho
Dankook University
3 shared publications- WanSoo Kim
Dept. of Electronics and Electrical Engineering, Dankook University, Yongin-si, Republic of Korea
3 shared publications
Latest Publications
- 16 October 2026
- Published by Elsevier in Microprocessors and Microsystems
- Vol. 125
Hardware-software co-design of posit arithmetic with diverse exponent sizes for DSP
- 16 October 2026
- Published by Elsevier in Microprocessors and Microsystems
- Vol. 125
Hardware-software co-design of posit arithmetic with diverse exponent sizes for DSP
- 29 August 2026
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 85 (9) , 724
DoTCoM: high-performance mobile vision transformers with co-bias
- 29 August 2026
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 85 (9) , 724
DoTCoM: high-performance mobile vision transformers with co-bias
- 10 May 2025
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 138 (5-6) , 2139-2156
Recognition and ranking using similarity on defective wafer bin maps
- 10 May 2025
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 138 (5-6) , 2139-2156
Recognition and ranking using similarity on defective wafer bin maps
- 8 December 2024
- Published by Springer Nature
- p. 252-269
HARD: Hardware-Aware Lightweight Real-Time Semantic Segmentation Model Deployable from Edge to GPU
- 8 December 2024
- Published by Springer Nature
- p. 252-269
HARD: Hardware-Aware Lightweight Real-Time Semantic Segmentation Model Deployable from Edge to GPU
- Open Access
A Temporally Correlated Latent Exploration for Reinforcement Learning
Efficient exploration remains one of the longstanding problems of deep reinforcement learning. Instead of depending solely on extrinsic rewards from the environments, existing methods use intrinsic rewards to enhance exploration. However, we demonstrate that these methods are vulnerable to Noisy TV and stochasticity. To tackle this problem, we propose Temporally Correlated Latent Exploration (TeCLE), which is a novel intrinsic reward formulation that employs an action-conditioned latent space and temporal correlation. The action-conditioned latent space estimates the probability distribution of states, thereby avoiding the assignment of excessive intrinsic rewards to unpredictable states and effectively addressing both problems. Whereas previous works inject temporal correlation for action selection, the proposed method injects it for intrinsic reward computation. We find that the injected temporal correlation determines the exploratory behaviors of agents. Various experiments show that the environment where the agent performs well depends on the amount of temporal correlation. To the best of our knowledge, the proposed TeCLE is the first approach to consider the action conditioned latent space and temporal correlation for curiosity-driven exploration. We prove that the proposed TeCLE can be robust to the Noisy TV and stochasticity in benchmark environments, including Minigrid and Stochastic Atari.
Open AccessA Temporally Correlated Latent Exploration for Reinforcement Learning
Efficient exploration remains one of the longstanding problems of deep reinforcement learning. Instead of depending solely on extrinsic rewards from the environments, existing methods use intrinsic rewards to enhance exploration. However, we demonstrate that these methods are vulnerable to Noisy TV and stochasticity. To tackle this problem, we propose Temporally Correlated Latent Exploration (TeCLE), which is a novel intrinsic reward formulation that employs an action-conditioned latent space and temporal correlation. The action-conditioned latent space estimates the probability distribution of states, thereby avoiding the assignment of excessive intrinsic rewards to unpredictable states and effectively addressing both problems. Whereas previous works inject temporal correlation for action selection, the proposed method injects it for intrinsic reward computation. We find that the injected temporal correlation determines the exploratory behaviors of agents. Various experiments show that the environment where the agent performs well depends on the amount of temporal correlation. To the best of our knowledge, the proposed TeCLE is the first approach to consider the action conditioned latent space and temporal correlation for curiosity-driven exploration. We prove that the proposed TeCLE can be robust to the Noisy TV and stochasticity in benchmark environments, including Minigrid and Stochastic Atari.
- 3 January 2024
- Published by Elsevier in Digital Signal Processing
- Vol. 146
Low-biased probabilistic multipliers using complementary inaccurate compressors
- 3 January 2024
- Published by Elsevier in Digital Signal Processing
- Vol. 146
Low-biased probabilistic multipliers using complementary inaccurate compressors
- Open Access
- 29 March 2022
- Published by PeerJ in PeerJ Computer Science
- Vol. 8, e924
A storage-efficient ensemble classification using filter sharing on binarized convolutional neural networks
This paper proposes a storage-efficient ensemble classification to overcome the low inference accuracy of binary neural networks (BNNs). When external power is enough in a dynamic powered system, classification results can be enhanced by aggregating outputs of multiple BNN classifiers. However, memory requirements for storing multiple classifiers are a significant burden in the lightweight system. The proposed scheme shares the filters from a trained convolutional neural network (CNN) model to reduce storage requirements in the binarized CNNs instead of adopting the fully independent classifier. While several filters are shared, the proposed method only trains unfrozen learnable parameters in the retraining step. We compare and analyze the performances of the proposed ensemble-based systems depending on various ensemble types and BNN structures on CIFAR datasets. Our experiments conclude that the proposed method using the filter sharing can be scalable with the number of classifiers and effective in enhancing classification accuracy. With binarized ResNet-20 and ReActNet-10 on the CIFAR-100 dataset, the proposed scheme can achieve 56.74% and 70.29% Top-1 accuracies with 10 BNN classifiers, which enhances performance by 7.6% and 3.6% compared with that using a single BNN classifier.
- 29 March 2022
- Published by PeerJ in PeerJ Computer Science
- Vol. 8, e924
Open AccessA storage-efficient ensemble classification using filter sharing on binarized convolutional neural networks
This paper proposes a storage-efficient ensemble classification to overcome the low inference accuracy of binary neural networks (BNNs). When external power is enough in a dynamic powered system, classification results can be enhanced by aggregating outputs of multiple BNN classifiers. However, memory requirements for storing multiple classifiers are a significant burden in the lightweight system. The proposed scheme shares the filters from a trained convolutional neural network (CNN) model to reduce storage requirements in the binarized CNNs instead of adopting the fully independent classifier. While several filters are shared, the proposed method only trains unfrozen learnable parameters in the retraining step. We compare and analyze the performances of the proposed ensemble-based systems depending on various ensemble types and BNN structures on CIFAR datasets. Our experiments conclude that the proposed method using the filter sharing can be scalable with the number of classifiers and effective in enhancing classification accuracy. With binarized ResNet-20 and ReActNet-10 on the CIFAR-100 dataset, the proposed scheme can achieve 56.74% and 70.29% Top-1 accuracies with 10 BNN classifiers, which enhances performance by 7.6% and 3.6% compared with that using a single BNN classifier.
- Open Access
- 3 January 2022
- Published by PeerJ in PeerJ Computer Science
- Vol. 8, e842
PresB-Net: parametric binarized neural network with learnable activations and shuffled grouped convolution
In this study, we present a novel performance-enhancing binarized neural network model called PresB-Net: Parametric Binarized Neural Network. A binarized neural network (BNN) model can achieve fast output computation with low hardware costs by using binarized weights and features. However, performance degradation is the most critical problem in BNN models. Our PresB-Net combines several state-of-the-art BNN structures including the learnable activation with additional trainable parameters and shuffled grouped convolution. Notably, we propose a new normalization approach, which reduces the imbalance between the shuffled groups occurring in shuffled grouped convolutions. Besides, the proposed normalization approach helps gradient convergence so that the unstableness of the learning can be amortized when applying the learnable activation. Our novel BNN model enhances the classification performance compared with other existing BNN models. Notably, the proposed PresB-Net-18 achieves 73.84% Top-1 inference accuracy for the CIFAR-100 dataset, outperforming other existing counterparts.
- 3 January 2022
- Published by PeerJ in PeerJ Computer Science
- Vol. 8, e842
Open AccessPresB-Net: parametric binarized neural network with learnable activations and shuffled grouped convolution
In this study, we present a novel performance-enhancing binarized neural network model called PresB-Net: Parametric Binarized Neural Network. A binarized neural network (BNN) model can achieve fast output computation with low hardware costs by using binarized weights and features. However, performance degradation is the most critical problem in BNN models. Our PresB-Net combines several state-of-the-art BNN structures including the learnable activation with additional trainable parameters and shuffled grouped convolution. Notably, we propose a new normalization approach, which reduces the imbalance between the shuffled groups occurring in shuffled grouped convolutions. Besides, the proposed normalization approach helps gradient convergence so that the unstableness of the learning can be amortized when applying the learnable activation. Our novel BNN model enhances the classification performance compared with other existing BNN models. Notably, the proposed PresB-Net-18 achieves 73.84% Top-1 inference accuracy for the CIFAR-100 dataset, outperforming other existing counterparts.
- Open Access
- 1 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 135513-135525
A Cost-Efficient Approximate Dynamic Ranged Multiplication and Approximation-Aware Training on Convolutional Neural Networks
This paper proposes a low-cost approximate dynamic ranged multiplier and describes its use during the training process on convolutional neural networks (CNNs). It has been noted that the approximate multiplier can be used in the convolution of CNN’s forward path. However, in CNN inference on a post-training quantization with a pre-trained model, erroneous convolution output from highly approximate multipliers significantly degrades performance. On the other hand, with the CNN model based on an approximate multiplier, the approximation-aware training process can optimize its learnable parameters, producing better classification results considering the approximate hardware. We analyze the error distribution of the approximate dynamic ranged multiplication and characterize it in order to find the most suitable approximate multiplier design. Considering the effects of normalizing the biased convolution outputs, a low standard deviation of relative errors with respect to the multiplication outputs leads to a negligible accuracy drop. Based on these facts, the hardware costs of the proposed multiplier can be further reduced by adopting the partial products’ inaccurate compression, truncated input fraction, and reduced-width multiplication output. When the proposed approximate multiplier is applied to the residual convolutional neural networks for the CIFAR-100 and Tiny-ImageNet datasets, the accuracy drops of the approximation-aware training results are negligible compared with those using 32-bit floating-point CNNs.
- 1 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 135513-135525
Open AccessA Cost-Efficient Approximate Dynamic Ranged Multiplication and Approximation-Aware Training on Convolutional Neural Networks
This paper proposes a low-cost approximate dynamic ranged multiplier and describes its use during the training process on convolutional neural networks (CNNs). It has been noted that the approximate multiplier can be used in the convolution of CNN’s forward path. However, in CNN inference on a post-training quantization with a pre-trained model, erroneous convolution output from highly approximate multipliers significantly degrades performance. On the other hand, with the CNN model based on an approximate multiplier, the approximation-aware training process can optimize its learnable parameters, producing better classification results considering the approximate hardware. We analyze the error distribution of the approximate dynamic ranged multiplication and characterize it in order to find the most suitable approximate multiplier design. Considering the effects of normalizing the biased convolution outputs, a low standard deviation of relative errors with respect to the multiplication outputs leads to a negligible accuracy drop. Based on these facts, the hardware costs of the proposed multiplier can be further reduced by adopting the partial products’ inaccurate compression, truncated input fraction, and reduced-width multiplication output. When the proposed approximate multiplier is applied to the residual convolutional neural networks for the CIFAR-100 and Tiny-ImageNet datasets, the accuracy drops of the approximation-aware training results are negligible compared with those using 32-bit floating-point CNNs.
- 6 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. 10 (4) , 2079-2085
PLAM: A Posit Logarithm-Approximate Multiplier
The Posit Number System was introduced in 2017 as a replacement for floating-point numbers. Since then, the community has explored its application in several areas, such as deep learning, and produced some unit designs which are still far from being competitive with their floating-point counterparts. This paper proposes a Posit Logarithm-Approximate Multiplication (PLAM) scheme to significantly reduce the complexity of posit multipliers, one of the most power-hungry arithmetic units. The impact of this approach is evaluated in deep neural network inference, where there are no significant accuracy drops. Compared with state-of-the-art posit multipliers, experiments show that the proposed technique reduces the area, power, and delay of 32-bit hardware multipliers up to 72.86%, 81.79%, and 17.01%, respectively.
- 6 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. 10 (4) , 2079-2085
PLAM: A Posit Logarithm-Approximate Multiplier
The Posit Number System was introduced in 2017 as a replacement for floating-point numbers. Since then, the community has explored its application in several areas, such as deep learning, and produced some unit designs which are still far from being competitive with their floating-point counterparts. This paper proposes a Posit Logarithm-Approximate Multiplication (PLAM) scheme to significantly reduce the complexity of posit multipliers, one of the most power-hungry arithmetic units. The impact of this approach is evaluated in deep neural network inference, where there are no significant accuracy drops. Compared with state-of-the-art posit multipliers, experiments show that the proposed technique reduces the area, power, and delay of 32-bit hardware multipliers up to 72.86%, 81.79%, and 17.01%, respectively.