Tung Minh Luu

Mr. Tung Minh Luu

KAIST, Daejeon, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 October 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
TVThang Vu
Thang Vu
KKKookhoi Kim
Kookhoi Kim
TNThanh Xuan Nguyen
Thanh Xuan Nguyen
Tung Minh LuuTung Minh Luu
Tung Minh Luu
JKJunyeong Kim
Junyeong Kim
CYChang D. Yoo
Chang D. Yoo
This paper considers a network referred to as SoftGroup for accurate and scalable 3D instance segmentation. Existing state-of-the-art methods produce hard semantic predictions followed by grouping instance segmentation results. Unfortunately, errors stemming from hard decisions propagate into the grouping, resulting in poor overlap between predicted instances and ground truth and substantial false positives. To address the abovementioned problems, SoftGroup allows each point to be associated with multiple classes to mitigate the uncertainty stemming from semantic prediction. It also suppresses false positive instances by learning to categorize them as background. Regarding scalability, the existing fast methods require computational time on the order of tens of seconds on large-scale scenes, which is unsatisfactory and far from applicable for real-time. Our finding is that the $k$ -Nearest Neighbor ( $k$ -NN) module, which serves as the prerequisite of grouping, introduces a computational bottleneck. SoftGroup is extended to resolve this computational bottleneck, referred to as SoftGroup++. The proposed SoftGroup++ reduces time complexity with octree $k$ -NN and reduces search space with class-aware pyramid scaling and late devoxelization. Experimental results on various indoor and outdoor datasets demonstrate the efficacy and generality of the proposed SoftGroup and SoftGroup++. Their performances surpass the best-performing baseline by a large margin (6% $\sim$ 16%) in terms of AP $_{50}$ . On datasets with large-scale scenes, SoftGroup++ achieves a 6× speed boost on average compared to SoftGroup. Furthermore, SoftGroup can be extended to perform object detection and panoptic segmentation with nontrivial improvements over existing methods.

31 March 2021 in IEEE Access
Verified
Journal Article
Open access
Tung Minh LuuTung Minh Luu
Tung Minh Luu
CYChang D. Yoo
Chang D. Yoo
This paper proposes a method for prioritizing the replay experience referred to as Hindsight Goal Ranking (HGR) in overcoming the limitation of Hindsight Experience Replay (HER) that generates hindsight goals based on uniform sampling. HGR samples with higher probability on the states visited in an episode with larger temporal difference (TD) error, which is considered as a proxy measure of the amount which the RL agent can learn from an experience. The actual sampling for large TD error is performed in two steps: first, an episode is sampled from the relay buffer according to the average TD error of its experiences, and then, for the sampled episode, the hindsight goal leading to larger TD error is sampled with higher probability from future visited states. The proposed method combined with Deep Deterministic Policy Gradient (DDPG), an off-policy model-free actor-critic algorithm, accelerates learning significantly faster than that without any prioritization on four challenging simulated robotic manipulation tasks. The empirical results show that HGR uses samples more efficiently than previous methods across all tasks.

27 September 2021
Verified
Conference Paper
Open access
TNThanh Xuan Nguyen
Thanh Xuan Nguyen
Tung Minh LuuTung Minh Luu
Tung Minh Luu
TVThang Vu
Thang Vu
CYChang D. Yoo
Chang D. Yoo
Developing an agent in reinforcement learning (RL) that is capable of performing complex control tasks directly from high-dimensional observation such as raw pixels is a challenge as efforts still need to be made towards improving sample efficiency and generalization of RL algorithm. This paper considers a learning framework for a Curiosity Contrastive Forward Dynamics Model (CCFDM) to achieve a more sample-efficient RL based directly on raw pixels. CCFDM incorporates a forward dynamics model (FDM) and performs contrastive learning to train its deep convolutional neural network-based image encoder (IE) to extract conducive spatial and temporal information to achieve a more sample efficiency for RL. In addition, during training, CCFDM provides intrinsic rewards, produced based on FDM prediction error, and encourages the curiosity of the RL agent to improve exploration. The diverge and less-repetitive observations provided by both our exploration strategy and data augmentation available in contrastive learning improve not only the sample efficiency but also the generalization . Performance of existing model-free RL methods such as Soft Actor-Critic built on top of CCFDM outperforms prior state-of-the-art pixel-based RL methods on the DeepMind Control Suite benchmark.

11 January 2023 in IEEE Access
Verified
Journal Article
Open access
TNThanh Xuan Nguyen
Thanh Xuan Nguyen
TPTrung Pham
Trung Pham
CZChaoning Zhang
Chaoning Zhang
Tung Minh LuuTung Minh Luu
Tung Minh Luu
TVThang Vu
Thang Vu
CYChang D. Yoo
Chang D. Yoo
Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role. However, the recent development of new non-CL frameworks has achieved comparable or better performance, prompting researchers to enhance these frameworks further. Assimilating CL into non-CL frameworks has been thought to be beneficial, but empirical evidence indicates no visible improvements. In view of that, this paper proposes a strategy of performing CL along the dimensional direction instead of along the batch direction as done in convention contrastive learning, named Dimensional Contrastive Learning (DimCL). DimCL aims to enhance the feature diversity, and it can serve as a regularizer to prior SSL frameworks. DimCL has been found to be effective, and the hardness-aware property is identified as a critical reason for its success. Extensive experimental results reveal that assimilating DimCL into SSL frameworks leads to performance improvement by a non-trivial margin on various datasets and backbone architectures.

10 June 2022 in IEEE Access
Verified
Journal Article
Open access
Tung Minh LuuTung Minh Luu
Tung Minh Luu
TNThanh Nguyen
Thanh Nguyen
TVThang Vu
Thang Vu
CYChang D. Yoo
Chang D. Yoo
Action repeat has become the de-facto mechanism in deep reinforcement learning (RL) for stabilizing training and enhancing exploration. Here, the action is taken at the action-decision point and is executed repeatedly for a designated number of times until the next decision point. Although showing several advantages, in this mechanism, the intermediate states which stem from repeated actions are discarded in training agents, causing sample inefficiency. To utilize the discarded states as training data is nontrivial as the action, which causes the transition between these states, is unavailable. This paper proposes to infer the action at the intermediate states via an inverse dynamic model. The proposed method is simple and easily incorporated into the existing off-policy RL algorithms - integrating the proposed method with SAC shows consistent improvement across various tasks.

29 August 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Tung Minh LuuTung Minh Luu
Tung Minh Luu
TVThang Vu
Thang Vu
TNThanh Xuan Nguyen
Thanh Xuan Nguyen
CYChang D. Yoo
Chang D. Yoo
In an attempt to overcome the limitations of reward-driven representation learning in vision-based reinforcement learning (RL), an unsupervised learning framework referred to as the visual pretraining via contrastive predictive model (VPCPM) is proposed to learn the representations detached from the policy learning. Our method enables the convolutional encoder to perceive the underlying dynamics through a pair of forward and inverse models under the supervision of the contrastive loss, thus resulting in better representations. In experiments with a diverse set of vision control tasks, by initializing the encoders with VPCPM, the performance of state-of-the-art vision-based RL algorithms is significantly boosted, with 44% and 10% improvement for RAD and DrQ at 100 steps, respectively. In comparison to the prior unsupervised methods, the performance of VPCPM matches or outperforms all the baselines. We further demonstrate that the learned representations successfully generalize to the new tasks that share a similar observation and action space.