Abstracts of papers published in 2024

Transactions of the International Society for Music Information Retrieval （ISMIR）, April 2024

The Sound Demixing Challenge 2023 – Music Demixing Track
Fabbro, Giorgio and Uhlich, Stefan and Lai, Chieh-Hsin and Choi, Woosung and Martínez-Ramírez, Marco and Liao, Weihsiang and Gadelha, Igor and Ramos, Geraldo and Hsu, Eddie and Rodrigues, Hugo and Stöter, Fabian-Robert and Défossez, Alexandre and Luo, Yi and Yu, Jianwei and Chakraborty, Dipam and Mohanty, Sharada and Solovyev, Roman and Stempkovskiy, Alexander and Habruseva, Tatiana and Goswami, Nabarun and Harada, Tatsuya and Kim, Minseok and Lee, Jun Hyung and Dong, Yuanliang and Zhang, Xinran and Liu, Jiafeng and Mitsufuji, Yuki
　 This paper summarizes the music demixing (MDX) track of the Sound Demixing Challenge (SDX'23). We provide a summary of the challenge setup and introduce the task of robust music source separation (MSS), i.e., training MSS models in the presence of errors in the training data. We propose a formalization of the errors that can occur in the design of a training dataset for MSS systems and introduce two new datasets that simulate such errors: SDXDB23_LabelNoise and SDXDB23_Bleeding. We describe the methods that achieved the highest scores in the competition. Moreover, we present a direct comparison with the previous edition of the challenge (the Music Demixing Challenge 2021): the best performing system achieved an improvement of over 1.6dB in signal-to-distortion ratio over the winner of the previous competition, when evaluated on MDXDB21. Besides relying on the signal-to-distortion ratio as objective metric, we also performed a listening test with renowned producers and musicians to study the perceptual quality of the systems and report here the results. Finally, we provide our insights into the organization of the competition and our prospects for future editions. Link

Proceedings of the IEEE International Conferences on Robotics and Automation (ICRA), 2024

Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behavior and Adversarial Style Sampling for Assistive Tasks
Takayuki Osa and Tatsuya Harada
　 Autonomous assistance of people with motor impairments is one of the most promising applications of autonomous robotic systems. Recent studies have reported encouraging results using deep reinforcement learning (RL) in the healthcare domain. Previous studies showed that assistive tasks can be formulated as multi-agent RL, wherein there are two agents: a caregiver and a care-receiver. However, policies trained in multi-agent RL are often sensitive to the policies of other agents. In such a case, a trained caregiver’s policy may not work for different care-receivers. To alleviate this issue, we propose a framework that learns a robust caregiver’s policy by training it for diverse care-receiver responses. In our framework, diverse care-receiver responses are autonomously learned through trials and errors. In addition, to robustify the care-giver’s policy, we propose a strategy for sampling a care-receiver’s response in an adversarial manner during the training. We evaluated the proposed method using tasks in an Assistive Gym. We demonstrate that policies trained with a popular deep RL method are vulnerable to changes in policies of other agents and that the proposed framework improves the robustness against such changes.

Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Open X-Embodiment Collaboration (173 authors, including Takayuki Osa, Yujin Tang, and Tatsuya Harada)
　 Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train “generalist” X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms.

The 12th International Conference on Learning Representations (ICLR), 2024

GPAvatar: Generalizable and Precise Head Avatar from Image(s)
Xuangeng Chu, Yu Li, Ailing Zeng, Tianyu Yang, Lijian Lin, Yunfei Liu, Tatsuya Harada
　 Head avatar reconstruction, crucial for applications in virtual reality, online meetings, gaming, and film industries, has garnered substantial attention within the computer vision community. The fundamental objective of this field is to faithfully recreate the head avatar and precisely control expressions and postures. Existing methods, categorized into 2D-based warping, mesh-based, and neural rendering approaches, present challenges in maintaining multi-view consistency, incorporating non-facial information, and generalizing to new identities. In this paper, we propose a framework named GPAvatar that reconstructs 3D head avatars from one or several images in a single forward pass. The key idea of this work is to introduce a dynamic point-based expression field driven by a point cloud to precisely and effectively capture expressions. Furthermore, we use a Multi Tri-planes Attention (MTA) fusion module in tri-planes canonical field to leverage information from multiple input images. The proposed method achieves faithful identity reconstruction, precise expression control, and multi-view consistency, demonstrating promising results for free-viewpoint rendering and novel view synthesis.

Medical Image Analysis

Sketch-based semantic retrieval of medical images
Kazuma Kobayashi, Lin Gu, Ryuichiro Hataya, Takaaki Mizuno, Mototaka Miyake, Hirokazu Watanabe, Masamichi Takahashi, Yasuyuki Takamizawa, Yukihiro Yoshida, Satoshi Nakamura, Nobuji Kouno, Amina Bolatkan, Yusuke Kurose, Tatsuya Harada, Ryuji Hamamoto
　 The volume of medical images stored in hospitals is rapidly increasing; however, the utilization of these accumulated medical images remains limited. Existing content-based medical image retrieval (CBMIR) systems typically require example images, leading to practical limitations, such as the lack of customizable, fine-grained image retrieval, the inability to search without example images, and difficulty in retrieving rare cases. In this paper, we introduce a sketch-based medical image retrieval (SBMIR) system that enables users to find images of interest without the need for example images. The key concept is feature decomposition of medical images, which allows the entire feature of a medical image to be decomposed into and reconstructed from normal and abnormal features. Building on this concept, our SBMIR system provides an easy-to-use two-step graphical user interface: users first select a template image to specify a normal feature and then draw a semantic sketch of the disease on the template image to represent an abnormal feature. The system integrates both types of input to construct a query vector and retrieves reference images. For evaluation, ten healthcare professionals participated in a user test using two datasets. Consequently, our SBMIR system enabled users to overcome previous challenges, including image retrieval based on fine-grained image characteristics, image retrieval without example images, and image retrieval for rare cases. Our SBMIR system provides on-demand, customizable medical image retrieval, thereby expanding the utility of medical image databases.

IJCV Special Issue on Multimodal Learning

Learning by Asking Questions for Knowledge-based Novel Object Recognition
Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada
　 In real-world object recognition, there are numerous object classes to be recognized. Traditional image recognition methods based on supervised learning can only recognize object classes present in the training data, and have limited applicability in the real world. In contrast, humans can recognize novel objects by questioning and acquiring knowledge about them. Inspired by this, we propose a framework for acquiring external knowledge by generating questions that enable the model to instantly recognize novel objects. Our framework comprises three components: the Object Classifier (OC), which performs knowledge-based object recognition, the Question Generator (QG), which generates knowledge-aware questions to acquire novel knowledge, and the Policy Decision (PD) Model, which determines the policy'' of questions to be asked. The PD model utilizes two strategies, namely confirmation'' and ``exploration'' --- the former confirms candidate knowledge while the latter explores completely new knowledge. Our experiments demonstrate that the proposed pipeline effectively acquires knowledge about novel objects compared to several baselines, and realizes novel object recognition utilizing the obtained knowledge. We also performed a real-world evaluation in which humans responded to the generated questions, and the model used the acquired knowledge to retrain the OC, which is a fundamental step toward a real-world human-in-the-loop learning-by-asking framework.

AAAI Conference on Artificial Intelligence (AAAI-24)

Symmetric Q-Learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning
Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada
In deep reinforcement learning, estimating the value function to evaluate the quality of states and actions is essential. The value function is often trained using the least squares method, which implicitly assumes a Gaussian error distribution. However, a recent study suggested that the error distribution for training the value function is often skewed because of the properties of the Bellman operator, and violates the implicit assumption of normal error distribution in the least squares method. To address this, we proposed a method called Symmetric Q-learning, in which the synthetic noise generated from a zero-mean distribution is added to the target values to generate a Gaussian error distribution. We evaluated the proposed method on continuous control benchmark tasks in MuJoCo. It improved the sample efficiency of a state-of-the-art reinforcement learning method by reducing the skewness of the error distribution.

Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption
Ziteng Cui, Lin Gu, Xiao Sun, Xianzheng Ma, Yu Qiao, Tatsuya Harada
The standard Neural Radiance Fields (NeRF) paradigm employs a viewer-centered methodology, entangling the aspects of illumination and material reflectance into emission solely from 3D points. This simplified rendering approach presents challenges in accurately modeling images captured under adverse lighting conditions, such as low light or over-exposure. Motivated by the ancient Greek emission theory that posits visual perception as a result of rays emanating from the eyes, we slightly refine the conventional NeRF framework to train NeRF under challenging light conditions and generate normal-light condition novel views unsupervised. We introduce the concept of a ”Concealing Field,” which assigns transmittance values to the surrounding air to account for illumination effects. In dark scenarios, we assume that object emissions maintain a standard lighting level but are attenuated as they traverse the air during the rendering process. Concealing Field thus compel NeRF to learn reasonable density and colour estimations for objects even in dimly lit situations. Similarly, the Concealing Field can mitigate over-exposed emissions during the rendering stage. Furthermore, we present a comprehensive multi-view dataset captured under challenging illumination conditions for evaluation.

Winter Conference on Applications of Computer Vision (WACV), 2024

Gradual Source Domain Expansion for Unsupervised Domain Adaptation
Thomas Westfechtel, Hao-Wei Yeh, Dexuan Zhang, Tatsuya Harada
Unsupervised domain adaptation (UDA) tries to overcome the need for a large labeled dataset by transferring knowledge from a source dataset, with lots of labeled data, to a target dataset, that has no labeled data. Since there are no labels in the target domain, early misalignment might propagate into the later stages and lead to an error build-up. In order to overcome this problem, we propose a gradual source domain expansion (GSDE) algorithm. GSDE trains the UDA task several times from scratch, each time reinitializing the network weights, but each time expands the source dataset with target data. In particular, the highest-scoring target data of the previous run are employed as pseudo-source samples with their respective pseudo-label. Using this strategy, the pseudo-source samples induce knowledge extracted from the previous run directly from the start of the new training. This helps align the two domains better, especially in the early training epochs. In this study, we first introduce a strong baseline network and apply our GSDE strategy to it. We conduct experiments and ablation studies on three benchmarks (Office-31, OfficeHome, and DomainNet) and outperform state-of-the-art methods. We further show that the proposed GSDE strategy can improve the accuracy of a variety of different state-of-the-art UDA approaches.