First-Order Methods for Linearly Constrained Bilevel Optimization

Algorithms for bilevel optimization often encounter Hessian computations, which are prohibitive in high dimensions. While recent works offer first-order methods for unconstrained bilevel problems, the constrained setting remains relatively underexplored. We present first-order linearly constrained optimization methods with finite-time hypergradient stationarity guarantees. For linear equality constraints, we attain $\epsilon$-stationarity in $\widetilde{O}(\epsilon^{-2})$ gradient oracle calls, which is nearly-optimal. For linear inequality constraints, we attain $(\delta,\epsilon)$-Goldstein stationarity in $\widetilde{O}(d{\delta^{-1} \epsilon^{-3}})$ gradient oracle calls, where $d$ is the upper-level dimension. Finally, we obtain for the linear inequality setting dimension-free rates of $\widetilde{O}({\delta^{-1} \epsilon^{-4}})$ oracle complexity under the additional assumption of oracle access to the optimal dual variable. Along the way, we develop new nonsmooth nonconvex optimization methods with inexact oracles. We verify these guarantees with preliminary numerical experiments.

Interpretable attributed scattering center extracted via deep unfolding

Most existing sparse representation-based approaches for attributed scattering center (ASC) extraction adopt traditional iterative optimization algorithms, which suffer from lengthy computation times and limited precision. This paper presents a solution by introducing an interpretable network that can effectively and rapidly extract ASC via deep unfolding. Initially, we create a dictionary containing reliable prior knowledge and apply it to the iterative shrinkage-thresholding algorithm (ISTA). Then, we unfold ISTA into a neural network, employing it to autonomously and precisely optimize the hyperparameters. The interpretability of physics is retained by applying a dictionary with physical meaning. The experiments are conducted on multiple test sets with diverse data distributions and demonstrate the superior performance and generalizability of our method.

HPPS: A Hierarchical Progressive Perception System for Luggage Trolley Detection and Localization at Airports

The robotic autonomous luggage trolley collection system employs robots to gather and transport scattered luggage trolleys at airports. However, existing methods for detecting and locating these luggage trolleys often fail when they are not fully visible. To address this, we introduce the Hierarchical Progressive Perception System (HPPS), which enhances the detection and localization of luggage trolleys under partial occlusion. The HPPS processes the luggage trolley's position and orientation separately, which requires only RGB images for labeling and training, eliminating the need for 3D coordinates and alignment. The HPPS can accurately determine the position of the luggage trolley with just one well-detected keypoint and estimate the luggage trolley's orientation when it is partially occluded. Once the luggage trolley's initial pose is detected, HPPS updates this information continuously to refine its accuracy until the robot begins grasping. The experiments on detection and localization demonstrate that HPPS is more reliable under partial occlusion compared to existing methods. Its effectiveness and robustness have also been confirmed through practical tests in actual luggage trolley collection tasks. A website about this work is available at HPPS.

A Robust Super-resolution Gridless Imaging Framework for UAV-borne SAR Tomography

Synthetic aperture radar (SAR) tomography (TomoSAR) retrieves three-dimensional (3-D) information from multiple SAR images, effectively addresses the layover problem, and has become pivotal in urban mapping. Unmanned aerial vehicle (UAV) has gained popularity as a TomoSAR platform, offering distinct advantages such as the ability to achieve 3-D imaging in a single flight, cost-effectiveness, rapid deployment, and flexible trajectory planning. The evolution of compressed sensing (CS) has led to the widespread adoption of sparse reconstruction techniques in TomoSAR signal processing, with a focus on $\ell _1$ norm regularization and other grid-based CS methods. However, the discretization of illuminated scene along elevation introduces modeling errors, resulting in reduced reconstruction accuracy, known as the "off-grid" effect. Recent advancements have introduced gridless CS algorithms to mitigate this issue. This paper presents an innovative gridless 3-D imaging framework tailored for UAV-borne TomoSAR. Capitalizing on the pulse repetition frequency (PRF) redundancy inherent in slow UAV platforms, a multiple measurement vectors (MMV) model is constructed to enhance noise immunity without compromising azimuth-range resolution. Given the sparsely placed array elements due to mounting platform constraints, an atomic norm soft thresholding algorithm is proposed for partially observed MMV, offering gridless reconstruction capability and super-resolution. An efficient alternative optimization algorithm is also employed to enhance computational efficiency. Validation of the proposed framework is achieved through computer simulations and flight experiments, affirming its efficacy in UAV-borne TomoSAR applications.

Two-pass Endpoint Detection for Speech Recognition

Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of users being cut-off early. We propose a novel two-pass solution for endpointing, where the utterance endpoint detected from a first pass endpointer is verified by a 2nd-pass model termed EP Arbitrator. Our method improves the trade-off between early cut-offs and latency over a baseline endpointer, as tested on datasets including voice-assistant transactional queries, conversational speech, and the public SLURP corpus. We demonstrate that our method shows improvements regardless of the first-pass EP model used.

HyperGANStrument: Instrument Sound Synthesis and Editing with Pitch-Invariant Hypernetworks

GANStrument, exploiting GANs with a pitch-invariant feature extractor and instance conditioning technique, has shown remarkable capabilities in synthesizing realistic instrument sounds. To further improve the reconstruction ability and pitch accuracy to enhance the editability of user-provided sound, we propose HyperGANStrument, which introduces a pitch-invariant hypernetwork to modulate the weights of a pre-trained GANStrument generator, given a one-shot sound as input. The hypernetwork modulation provides feedback for the generator in the reconstruction of the input sound. In addition, we take advantage of an adversarial fine-tuning scheme for the hypernetwork to improve the reconstruction fidelity and generation diversity of the generator. Experimental results show that the proposed model not only enhances the generation capability of GANStrument but also significantly improves the editability of synthesized sounds. Audio examples are available at the online demo page.

Identification of morphological fingerprint in perinatal brains using quasi-conformal mapping and contrastive learning

The morphological fingerprint in the brain is capable of identifying the uniqueness of an individual. However, whether such individual patterns are present in perinatal brains, and which morphological attributes or cortical regions better characterize the individual differences of ne-onates remain unclear. In this study, we proposed a deep learning framework that projected three-dimensional spherical meshes of three morphological features (i.e., cortical thickness, mean curvature, and sulcal depth) onto two-dimensional planes through quasi-conformal mapping, and employed the ResNet18 and contrastive learning for individual identification. We used the cross-sectional structural MRI data of 682 infants, incorporating with data augmentation, to train the model and fine-tuned the parameters based on 60 infants who had longitudinal scans. The model was validated on 30 longitudinal scanned infant data, and remarkable Top1 and Top5 accuracies of 71.37% and 84.10% were achieved, respectively. The sensorimotor and visual cortices were recognized as the most contributive regions in individual identification. Moreover, the folding morphology demonstrated greater discriminative capability than the cortical thickness, which could serve as the morphological fingerprint in perinatal brains. These findings provided evidence for the emergence of morphological fingerprints in the brain at the beginning of the third trimester, which may hold promising implications for understanding the formation of in-dividual uniqueness in the brain during early development.

DA-STC: Domain Adaptive Video Semantic Segmentation via Spatio-Temporal Consistency

Video semantic segmentation is a pivotal aspect of video representation learning. However, significant domain shifts present a challenge in effectively learning invariant spatio-temporal features across the labeled source domain and unlabeled target domain for video semantic segmentation. To solve the challenge, we propose a novel DA-STC method for domain adaptive video semantic segmentation, which incorporates a bidirectional multi-level spatio-temporal fusion module and a category-aware spatio-temporal feature alignment module to facilitate consistent learning for domain-invariant features. Firstly, we perform bidirectional spatio-temporal fusion at the image sequence level and shallow feature level, leading to the construction of two fused intermediate video domains. This prompts the video semantic segmentation model to consistently learn spatio-temporal features of shared patch sequences which are influenced by domain-specific contexts, thereby mitigating the feature gap between the source and target domain. Secondly, we propose a category-aware feature alignment module to promote the consistency of spatio-temporal features, facilitating adaptation to the target domain. Specifically, we adaptively aggregate the domain-specific deep features of each category along spatio-temporal dimensions, which are further constrained to achieve cross-domain intra-class feature alignment and inter-class feature separation. Extensive experiments demonstrate the effectiveness of our method, which achieves state-of-the-art mIOUs on multiple challenging benchmarks. Furthermore, we extend the proposed DA-STC to the image domain, where it also exhibits superior performance for domain adaptive semantic segmentation. The source code and models will be made available at \url{https://github.com/ZHE-SAPI/DA-STC}.

Melody-conditioned lyrics generation via fine-tuning language model and its evaluation with ChatGPT

We leverage character-level language models for syllable-level lyrics generation from symbolic melody. By fine-tuning a character-level pre-trained model, we integrate language knowledge into the beam search of a syllable-level Transformer generator. Using ChatGPT-based evaluations, we demonstrate enhanced coherence and correctness in the generated lyrics.

Mani-GPT: A Generative Model for Interactive Robotic Manipulation

In real-world scenarios, human dialogues are multi-round and diverse. Furthermore, human instructions can be unclear and human responses are unrestricted. Interactive robots face difficulties in understanding human intents and generating suitable strategies for assisting individuals through manipulation. In this article, we propose Mani-GPT, a Generative Pre-trained Transformer (GPT) for interactive robotic manipulation. The proposed model has the ability to understand the environment through object information, understand human intent through dialogues, generate natural language responses to human input, and generate appropriate manipulation plans to assist the human. This makes the human-robot interaction more natural and humanized. In our experiment, Mani-GPT outperforms existing algorithms with an accuracy of 84.6% in intent recognition and decision-making for actions. Furthermore, it demonstrates satisfying performance in real-world dialogue tests with users, achieving an average response accuracy of 70%.