MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation

Text-to-image generation has achieved astonishing results, yet precise spatial controllability and prompt fidelity remain highly challenging. This limitation is typically addressed through cumbersome prompt engineering, scene layout conditioning, or image editing techniques which often require hand drawn masks. Nonetheless, pre-existing works struggle to take advantage of the natural instance-level compositionality of scenes due to the typically flat nature of rasterized RGB output images. Towards adressing this challenge, we introduce MuLAn: a novel dataset comprising over 44K MUlti-Layer ANnotations of RGB images as multilayer, instance-wise RGBA decompositions, and over 100K instance images. To build MuLAn, we developed a training free pipeline which decomposes a monocular RGB image into a stack of RGBA layers comprising of background and isolated instances. We achieve this through the use of pretrained general-purpose models, and by developing three modules: image decomposition for instance discovery and extraction, instance completion to reconstruct occluded areas, and image re-assembly. We use our pipeline to create MuLAn-COCO and MuLAn-LAION datasets, which contain a variety of image decompositions in terms of style, composition and complexity. With MuLAn, we provide the first photorealistic resource providing instance decomposition and occlusion information for high quality images, opening up new avenues for text-to-image generative AI research. With this, we aim to encourage the development of novel generation and editing technology, in particular layer-wise solutions. MuLAn data resources are available at https://MuLAn-dataset.github.io/.

Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview

Imitation Learning (IL), also referred to as Learning from Demonstration (LfD), holds significant promise for capturing expert motor skills through efficient imitation, facilitating adept navigation of complex scenarios. A persistent challenge in IL lies in extending generalization from historical demonstrations, enabling the acquisition of new skills without re-teaching. Dynamical system-based IL (DSIL) emerges as a significant subset of IL methodologies, offering the ability to learn trajectories via movement primitives and policy learning based on experiential abstraction. This paper emphasizes the fusion of theoretical paradigms, integrating control theory principles inherent in dynamical systems into IL. This integration notably enhances robustness, adaptability, and convergence in the face of novel scenarios. This survey aims to present a comprehensive overview of DSIL methods, spanning from classical approaches to recent advanced approaches. We categorize DSIL into autonomous dynamical systems and non-autonomous dynamical systems, surveying traditional IL methods with low-dimensional input and advanced deep IL methods with high-dimensional input. Additionally, we present and analyze three main stability methods for IL: Lyapunov stability, contraction theory, and diffeomorphism mapping. Our exploration also extends to popular policy improvement methods for DSIL, encompassing reinforcement learning, deep reinforcement learning, and evolutionary strategies.

Accelerating Diffusion Sampling with Optimized Time Steps

Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps. While this is a significant development, most sampling methods still employ uniform time steps, which is not optimal when using a small number of steps. To address this issue, we propose a general framework for designing an optimization problem that seeks more appropriate time steps for a specific numerical ODE solver for DPMs. This optimization problem aims to minimize the distance between the ground-truth solution to the ODE and an approximate solution corresponding to the numerical solver. It can be efficiently solved using the constrained trust region method, taking less than $15$ seconds. Our extensive experiments on both unconditional and conditional sampling using pixel- and latent-space DPMs demonstrate that, when combined with the state-of-the-art sampling method UniPC, our optimized time steps significantly improve image generation performance in terms of FID scores for datasets such as CIFAR-10 and ImageNet, compared to using uniform time steps.

TAnet: A New Temporal Attention Network for EEG-based Auditory Spatial Attention Decoding with a Short Decision Window

Auditory spatial attention detection (ASAD) is used to determine the direction of a listener's attention to a speaker by analyzing her/his electroencephalographic (EEG) signals. This study aimed to further improve the performance of ASAD with a short decision window (i.e., <1 s) rather than with long decision windows in previous studies. An end-to-end temporal attention network (i.e., TAnet) was introduced in this work. TAnet employs a multi-head attention (MHA) mechanism, which can more effectively capture the interactions among time steps in collected EEG signals and efficiently assign corresponding weights to those EEG time steps. Experiments demonstrated that, compared with the CNN-based method and recent ASAD methods, TAnet provided improved decoding performance in the KUL dataset, with decoding accuracies of 92.4% (decision window 0.1 s), 94.9% (0.25 s), 95.1% (0.3 s), 95.4% (0.4 s), and 95.5% (0.5 s) with short decision windows (i.e., <1 s). As a new ASAD model with a short decision window, TAnet can potentially facilitate the design of EEG-controlled intelligent hearing aids and sound recognition systems.

Distributed Multi-Object Tracking Under Limited Field of View Heterogeneous Sensors with Density Clustering

We consider the problem of tracking multiple, unknown, and time-varying numbers of objects using a distributed network of heterogeneous sensors. In an effort to derive a formulation for practical settings, we consider limited and unknown sensor field-of-views (FoVs), sensors with limited local computational resources and communication channel capacity. The resulting distributed multi-object tracking algorithm involves solving an NP-hard multidimensional assignment problem either optimally for small-size problems or sub-optimally for general practical problems. For general problems, we propose an efficient distributed multi-object tracking algorithm that performs track-to-track fusion using a clustering-based analysis of the state space transformed into a density space to mitigate the complexity of the assignment problem. The proposed algorithm can more efficiently group local track estimates for fusion than existing approaches. To ensure we achieve globally consistent identities for tracks across a network of nodes as objects move between FoVs, we develop a graph-based algorithm to achieve label consensus and minimise track segmentation. Numerical experiments with a synthetic and a real-world trajectory dataset demonstrate that our proposed method is significantly more computationally efficient than state-of-the-art solutions, achieving similar tracking accuracy and bandwidth requirements but with improved label consistency.

3S-TSE: Efficient Three-Stage Target Speaker Extraction for Real-Time and Low-Resource Applications

Target speaker extraction (TSE) aims to isolate a specific voice from multiple mixed speakers relying on a registerd sample. Since voiceprint features usually vary greatly, current end-to-end neural networks require large model parameters which are computational intensive and impractical for real-time applications, espetially on resource-constrained platforms. In this paper, we address the TSE task using microphone array and introduce a novel three-stage solution that systematically decouples the process: First, a neural network is trained to estimate the direction of the target speaker. Second, with the direction determined, the Generalized Sidelobe Canceller (GSC) is used to extract the target speech. Third, an Inplace Convolutional Recurrent Neural Network (ICRN) acts as a denoising post-processor, refining the GSC output to yield the final separated speech. Our approach delivers superior performance while drastically reducing computational load, setting a new standard for efficient real-time target speaker extraction.

Utilizing Whisper to Enhance Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids

Automated assessment of speech intelligibility in hearing aid (HA) devices is of great importance. Our previous work introduced a non-intrusive multi-branched speech intelligibility prediction model called MBI-Net, which achieved top performance in the Clarity Prediction Challenge 2022. Based on the promising results of the MBI-Net model, we aim to further enhance its performance by leveraging Whisper embeddings to enrich acoustic features. In this study, we propose two improved models, namely MBI-Net+ and MBI-Net++. MBI-Net+ maintains the same model architecture as MBI-Net, but replaces self-supervised learning (SSL) speech embeddings with Whisper embeddings to deploy cross-domain features. On the other hand, MBI-Net++ further employs a more elaborate design, incorporating an auxiliary task to predict frame-level and utterance-level scores of the objective speech intelligibility metric HASPI (Hearing Aid Speech Perception Index) and multi-task learning. Experimental results confirm that both MBI-Net++ and MBI-Net+ achieve better prediction performance than MBI-Net in terms of multiple metrics, and MBI-Net++ is better than MBI-Net+.

ConservationBots: Autonomous Aerial Robot for Fast Robust Wildlife Tracking in Complex Terrains

Today, the most widespread, widely applicable technology for gathering data relies on experienced scientists armed with handheld radio telemetry equipment to locate low-power radio transmitters attached to wildlife from the ground. Although aerial robots can transform labor-intensive conservation tasks, the realization of autonomous systems for tackling task complexities under real-world conditions remains a challenge. We developed ConservationBots-small aerial robots for tracking multiple, dynamic, radio-tagged wildlife. The aerial robot achieves robust localization performance and fast task completion times -- significant for energy-limited aerial systems while avoiding close encounters with potential, counter-productive disturbances to wildlife. Our approach overcomes the technical and practical problems posed by combining a lightweight sensor with new concepts: i) planning to determine both trajectory and measurement actions guided by an information-theoretic objective, which allows the robot to strategically select near-instantaneous range-only measurements to achieve faster localization, and time-consuming sensor rotation actions to acquire bearing measurements and achieve robust tracking performance; ii) a bearing detector more robust to noise and iii) a tracking algorithm formulation robust to missed and false detections experienced in real-world conditions. We conducted extensive studies: simulations built upon complex signal propagation over high-resolution elevation data on diverse geographical terrains; field testing; studies with wombats (Lasiorhinus latifrons; nocturnal, vulnerable species dwelling in underground warrens) and tracking comparisons with a highly experienced biologist to validate the effectiveness of our aerial robot and demonstrate the significant advantages over the manual method.

Complexity Matters: Rethinking the Latent Space for Generative Modeling

In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of the latent space is empirically pivotal, determining the optimal choice and the process of identifying it remain unclear. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity. Our investigation starts with the classic generative adversarial networks (GANs). Inspired by the GAN training objective, we propose a novel "distance" between the latent and data distributions, whose minimization coincides with that of the generator complexity. The minimizer of this distance is characterized as the optimal data-dependent latent that most effectively capitalizes on the generator's capacity. Then, we consider parameterizing such a latent distribution by an encoder network and propose a two-stage training strategy called Decoupled Autoencoder (DAE), where the encoder is only updated in the first stage with an auxiliary decoder and then frozen in the second stage while the actual decoder is being trained. DAE can improve the latent distribution and as a result, improve the generative performance. Our theoretical analyses are corroborated by comprehensive experiments on various models such as VQGAN and Diffusion Transformer, where our modifications yield significant improvements in sample quality with decreased model complexity.

BiRP: Learning Robot Generalized Bimanual Coordination using Relative Parameterization Method on Human Demonstration

Human bimanual manipulation can perform more complex tasks than a simple combination of two single arms, which is credited to the spatio-temporal coordination between the arms. However, the description of bimanual coordination is still an open topic in robotics. This makes it difficult to give an explainable coordination paradigm, let alone applied to robotics. In this work, we divide the main bimanual tasks in human daily activities into two types: leader-follower and synergistic coordination. Then we propose a relative parameterization method to learn these types of coordination from human demonstration. It represents coordination as Gaussian mixture models from bimanual demonstration to describe the change in the importance of coordination throughout the motions by probability. The learned coordinated representation can be generalized to new task parameters while ensuring spatio-temporal coordination. We demonstrate the method using synthetic motions and human demonstration data and deploy it to a humanoid robot to perform a generalized bimanual coordination motion. We believe that this easy-to-use bimanual learning from demonstration (LfD) method has the potential to be used as a data augmentation plugin for robot large manipulation model training. The corresponding codes are open-sourced in https://github.com/Skylark0924/Rofunc.