arXiv subjects

Qiyu Sun

Publications and source records attributed to Qiyu Sun.

At least 37 records · Page 2Linked to original sources

arXiv2023

RoMa: Robust Dense Feature Matching

Feature matching is an important computer vision task that involves estimating correspondences between two images of a 3D scene, and dense methods estimate all such correspondences. The aim is to learn a robust model, i.e., a model able to match under challenging real-world changes. In this work, we propose such a model, leveraging frozen pretrained features from the foundation model DINOv2. Although these features are significantly more robust than local features trained from scratch, they are inherently coarse. We therefore combine them with specialized ConvNet fine features, creating a precisely localizable feature pyramid. To further improve robustness, we propose a tailored transformer match decoder that predicts anchor probabilities, which enables it to express multimodality. Finally, we propose an improved loss formulation through regression-by-classification with subsequent robust regression. We conduct a comprehensive set of experiments that show that our method, RoMa, achieves significant gains, setting a new state-of-the-art. In particular, we achieve a 36% improvement on the extremely challenging WxBS benchmark. Code is provided at https://github.com/Parskatt/RoMa

cs.CV↗

arXiv2023

Barron Space for Graph Convolution Neural Networks

Graph convolutional neural network (GCNN) operates on graph domain and it has achieved a superior performance to accomplish a wide range of tasks. In this paper, we introduce a Barron space of functions on a compact domain of graph signals. We prove that the proposed Barron space is a reproducing kernel Banach space, it can be decomposed into the union of a family of reproducing kernel Hilbert spaces with neuron kernels, and it could be dense in the space of continuous functions on the domain. Approximation property is one of the main principles to design neural networks. In this paper, we show that outputs of GCNNs are contained in the Barron space and functions in the Barron space can be well approximated by outputs of some GCNNs in the integrated square and uniform measurements. We also estimate the Rademacher complexity of functions with bounded Barron norm and conclude that functions in the Barron space could be learnt from their random samples efficiently.

stat.ML↗

arXiv2023

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture. We ease the learning process by obtaining coarse camera poses from monocular sequences through multi-view geometry to deal with the former. However, we found that limited by the scale ambiguity across different scenes in the training dataset, a naïve introduction of geometric coarse poses cannot play a positive role in performance improvement, which is counter-intuitive. To address this problem, we propose to refine those poses during training through rotation and translation/scale optimization. To soften the effect of the low texture, we combine the global reasoning of vision transformers with an overfitting-aware, iterative self-distillation mechanism, providing more accurate depth guidance coming from the network itself. Experiments on NYUv2, ScanNet, 7scenes, and KITTI datasets support the effectiveness of each component in our framework, which sets a new state-of-the-art for indoor self-supervised monocular depth estimation, as well as outstanding generalization ability. Code and models are available at https://github.com/zxcqlf/GasMono

cs.CV↗

arXiv2023

Learning to Augment: Hallucinating Data for Domain Generalized Segmentation

Domain generalized semantic segmentation (DGSS) is an essential but highly challenging task, in which the model is trained only on source data and any target data is not available. Existing DGSS methods primarily standardize the feature distribution or utilize extra domain data for augmentation. However, the former sacrifices valuable information and the latter introduces domain biases. Therefore, generating diverse-style source data without auxiliary data emerges as an attractive strategy. In light of this, we propose GAN-based feature augmentation (GBFA) that hallucinates stylized feature maps while preserving their semantic contents with a feature generator. The impressive generative capability of GANs enables GBFA to perform inter-channel and trainable feature synthesis in an end-to-end framework. To enable learning GBFA, we introduce random image color augmentation (RICA), which adds a diverse range of variations to source images during training. These augmented images are then passed through a feature extractor to obtain features tailored for GBFA training. Both GBFA and RICA operate exclusively within the source domain, eliminating the need for auxiliary datasets. We conduct extensive experiments, and the generalization results from the synthetic GTAV and SYNTHIA to the real Cityscapes, BDDS, and Mapillary datasets show that our method achieves state-of-the-art performance in DGSS.

cs.CV↗

arXiv2023

IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentation

Domain generalized semantic segmentation (DGSS) is a critical yet challenging task, where the model is trained only on source data without access to any target data. Despite the proposal of numerous DGSS strategies, the generalization capability remains limited in CNN architectures. Though some Transformer-based segmentation models show promising performance, they primarily focus on capturing intra-sample attentive relationships, disregarding inter-sample correlations which can potentially benefit DGSS. To this end, we enhance the attention modules in Transformer networks for improving DGSS by incorporating information from other independent samples in the same batch, enriching contextual information, and diversifying the training data for each attention block. Specifically, we propose two alternative intra-batch attention mechanisms, namely mean-based intra-batch attention (MIBA) and element-wise intra-batch attention (EIBA), to capture correlations between different samples, enhancing feature representation and generalization capabilities. Building upon intra-batch attention, we introduce IBAFormer, which integrates self-attention modules with the proposed intra-batch attention for DGSS. Extensive experiments demonstrate that IBAFormer achieves SOTA performance in DGSS, and ablation studies further confirm the effectiveness of each introduced component.

cs.CV↗

arXiv2023

Causal reasoning in typical computer vision tasks

Deep learning has revolutionized the field of artificial intelligence. Based on the statistical correlations uncovered by deep learning-based methods, computer vision has contributed to tremendous growth in areas like autonomous driving and robotics. Despite being the basis of deep learning, such correlation is not stable and is susceptible to uncontrolled factors. In the absence of the guidance of prior knowledge, statistical correlations can easily turn into spurious correlations and cause confounders. As a result, researchers are now trying to enhance deep learning methods with causal theory. Causal theory models the intrinsic causal structure unaffected by data bias and is effective in avoiding spurious correlations. This paper aims to comprehensively review the existing causal methods in typical vision and vision-language tasks such as semantic segmentation, object detection, and image captioning. The advantages of causality and the approaches for building causal paradigms will be summarized. Future roadmaps are also proposed, including facilitating the development of causal theory and its application in other complex scenes and systems.

cs.CV↗

arXiv2023

CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation

Most nighttime semantic segmentation studies are based on domain adaptation approaches and image input. However, limited by the low dynamic range of conventional cameras, images fail to capture structural details and boundary information in low-light conditions. Event cameras, as a new form of vision sensors, are complementary to conventional cameras with their high dynamic range. To this end, we propose a novel unsupervised Cross-Modality Domain Adaptation (CMDA) framework to leverage multi-modality (Images and Events) information for nighttime semantic segmentation, with only labels on daytime images. In CMDA, we design the Image Motion-Extractor to extract motion information and the Image Content-Extractor to extract content information from images, in order to bridge the gap between different modalities (Images to Events) and domains (Day to Night). Besides, we introduce the first image-event nighttime semantic segmentation dataset. Extensive experiments on both the public image dataset and the proposed image-event dataset demonstrate the effectiveness of our proposed approach. We open-source our code, models, and dataset at https://github.com/XiaRho/CMDA.

cs.CV↗

arXiv2022

Molecular Joint Representation Learning via Multi-modal Information

In recent years, artificial intelligence has played an important role on accelerating the whole process of drug discovery. Various of molecular representation schemes of different modals (e.g. textual sequence or graph) are developed. By digitally encoding them, different chemical information can be learned through corresponding network structures. Molecular graphs and Simplified Molecular Input Line Entry System (SMILES) are popular means for molecular representation learning in current. Previous works have done attempts by combining both of them to solve the problem of specific information loss in single-modal representation on various tasks. To further fusing such multi-modal imformation, the correspondence between learned chemical feature from different representation should be considered. To realize this, we propose a novel framework of molecular joint representation learning via Multi-Modal information of SMILES and molecular Graphs, called MMSG. We improve the self-attention mechanism by introducing bond level graph representation as attention bias in Transformer to reinforce feature correspondence between multi-modal information. We further propose a Bidirectional Message Communication Graph Neural Network (BMC GNN) to strengthen the information flow aggregated from graphs for further combination. Numerous experiments on public property prediction datasets have demonstrated the effectiveness of our model.

cs.LG↗

arXiv2022

Learning Nonlinear Couplings in Network of Agents from a Single Sample Trajectory

We consider a class of stochastic dynamical networks whose governing dynamics can be modeled using a coupling function. It is shown that the dynamics of such networks can generate geometrically ergodic trajectories under some reasonable assumptions. We show that a general class of coupling functions can be learned using only one sample trajectory from the network. This is practically plausible as in numerous applications it is desired to run an experiment only once but for a longer period of time, rather than repeating the same experiment multiple times from different initial conditions. Building upon ideas from the concentration inequalities for geometrically ergodic Markov chains, we formulate several results about the convergence of the empirical estimator to the true coupling function. Our theoretical findings are supported by extensive simulation results.

eess.SY↗

arXiv2022

Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learning

Learning-based image dehazing methods are essential to assist autonomous systems in enhancing reliability. Due to the domain gap between synthetic and real domains, the internal information learned from synthesized images is usually sub-optimal in real domains, leading to severe performance drop of dehaizing models. Driven by the ability on exploring internal information from a few unseen-domain samples, meta-learning is commonly adopted to address this issue via test-time training, which is hyperparameter-sensitive and time-consuming. In contrast, we present a domain generalization framework based on meta-learning to dig out representative and discriminative internal properties of real hazy domains without test-time training. To obtain representative domain-specific information, we attach two entities termed adaptation network and distance-aware aggregator to our dehazing network. The adaptation network assists in distilling domain-relevant information from a few hazy samples and caching it into a collection of features. The distance-aware aggregator strives to summarize the generated features and filter out misleading information for more representative internal properties. To enhance the discrimination of distilled internal information, we present a novel loss function called domain-relevant contrastive regularization, which encourages the internal features generated from the same domain more similar and that from diverse domains more distinct. The generated representative and discriminative features are regarded as some external variables of our dehazing network to regress a particular and powerful function for a given domain. The extensive experiments on real hazy datasets, such as RTTS and URHI, validate that our proposed method has superior generalization ability than the state-of-the-art competitors.

cs.CV↗

arXiv2022

Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview

Visual semantic segmentation aims at separating a visual sample into diverse blocks with specific semantic attributes and identifying the category for each block, and it plays a crucial role in environmental perception. Conventional learning-based visual semantic segmentation approaches count heavily on large-scale training data with dense annotations and consistently fail to estimate accurate semantic labels for unseen categories. This obstruction spurs a craze for studying visual semantic segmentation with the assistance of few/zero-shot learning. The emergence and rapid progress of few/zero-shot visual semantic segmentation make it possible to learn unseen-category from a few labeled or zero-labeled samples, which advances the extension to practical applications. Therefore, this paper focuses on the recently published few/zero-shot visual semantic segmentation methods varying from 2D to 3D space and explores the commonalities and discrepancies of technical settlements under different segmentation circumstances. Specifically, the preliminaries on few/zero-shot visual semantic segmentation, including the problem definitions, typical datasets, and technical remedies, are briefly reviewed and discussed. Moreover, three typical instantiations are involved to uncover the interactions of few/zero-shot learning with visual semantic segmentation, including image semantic segmentation, video object segmentation, and 3D segmentation. Finally, the future challenges of few/zero-shot visual semantic segmentation are discussed.

cs.CV↗

arXiv2022

Graph Fourier transforms on directed product graphs

Graph Fourier transform (GFT) is one of the fundamental tools in graph signal processing to decompose graph signals into different frequency components and to represent graph signals with strong correlation by different modes of variation effectively. The GFT on undirected graphs has been well studied and several approaches have been proposed to define GFTs on directed graphs. In this paper, based on the singular value decompositions of some graph Laplacians, we propose two GFTs on the Cartesian product graph of two directed graphs. We show that the proposed GFTs could represent spatial-temporal data sets on directed networks with strong correlation efficiently, and in the undirected graph setting they are essentially the joint GFT in the literature. In this paper, we also consider the bandlimiting procedure in the spectral domain of the proposed GFTs, and demonstrate its performance to denoise the temperature data set in the region of Brest (France) on January 2014.

cs.IT↗

arXiv2022

Carleman Linearization of Nonlinear Systems and Its Finite-Section Approximations

The Carleman linearization is one of the mainstream approaches to lift a finite-dimensional nonlinear dynamical system into an infinite-dimensional linear system with the promise of providing accurate approximations of the original nonlinear system over larger regions around the equilibrium for longer time horizons with respect to the conventional first-order linearization approach. Finite-section approximations of the lifted system has been widely used to study dynamical and control properties of the original nonlinear system. In this context, some of the outstanding problems are to determine under what conditions, as the finite-section order (i.e., truncation length) increases, the trajectory of the resulting approximate linear system from the finite-section scheme converges to that of the original nonlinear system and whether the time interval over which the convergence happens can be quantified explicitly. In this paper, we provide explicit error bounds for the finite-section approximation and prove that the convergence is indeed exponential with respect to the finite-section order. For a class of nonlinear systems, it is shown that one can achieve exponential convergence over the entire time horizon up to infinity. Our results are practically plausible as our proposed error bound estimates can be used to compute proper truncation lengths for a given application, e.g., determining proper sampling period for model predictive control and reachability analysis for safety verifications. We validate our theoretical findings through several illustrative simulations.

math.DS↗

arXiv2022

Unsupervised Monocular Depth Estimation in Highly Complex Environments

With the development of computational intelligence algorithms, unsupervised monocular depth and pose estimation framework, which is driven by warped photometric consistency, has shown great performance in the daytime scenario. While in some challenging environments, like night and rainy night, the essential photometric consistency hypothesis is untenable because of the complex lighting and reflection, so that the above unsupervised framework cannot be directly applied to these complex scenarios. In this paper, we investigate the problem of unsupervised monocular depth estimation in highly complex scenarios and address this challenging problem by adopting an image transfer-based domain adaptation framework. We adapt the depth model trained on day-time scenarios to be applicable to night-time scenarios, and constraints on both feature space and output space promote the framework to learn the key features for depth decoding. Meanwhile, we further tackle the effects of unstable image transfer quality on domain adaptation, and an image adaptation approach is proposed to evaluate the quality of transferred images and re-weight the corresponding losses, so as to improve the performance of the adapted depth model. Extensive experiments show the effectiveness of the proposed unsupervised framework in estimating the dense depth map from highly complex images.

cs.CV↗

arXiv2022

Graph Fourier transform based on singular value decomposition of directed Laplacian

Graph Fourier transform (GFT) is a fundamental concept in graph signal processing. In this paper, based on singular value decomposition of Laplacian, we introduce a novel definition of GFT on directed graphs, and use singular values of Laplacian to carry the notion of graph frequencies. % of the proposed GFT. The proposed GFT is consistent with the conventional GFT in the undirected graph setting, and on directed circulant graphs, the proposed GFT is the classical discrete Fourier transform, up to some rotation, permutation and phase adjustment. We show that frequencies and frequency components of the proposed GFT can be evaluated by solving some constrained minimization problems with low computational cost. Numerical demonstrations indicate that the proposed GFT could represent graph signals with different modes of variation efficiently.

eess.SP↗

arXiv2022

Wiener filters on graphs and distributed polynomial approximation algorithms

In this paper, we consider Wiener filters to reconstruct deterministic and (wide-band) stationary graph signals from their observations corrupted by random noises, and we propose distributed algorithms to implement Wiener filters and inverse filters on networks in which agents are equipped with a data processing subsystem for limited data storage and computation power, and with a one-hop communication subsystem for direct data exchange only with their adjacent agents. The proposed distributed polynomial approximation algorithm is an exponential convergent quasi-Newton method based on Jacobi polynomial approximation and Chebyshev interpolation polynomial approximation to analytic functions on a cube. Our numerical simulations show that Wiener filtering procedure performs better on denoising (wide-band) stationary signals than the Tikhonov regularization approach does, and that the proposed polynomial approximation algorithms converge faster than the Chebyshev polynomial approximation algorithm and gradient decent algorithm do in the implementation of an inverse filtering procedure associated with a polynomial filter of commutative graph shifts.

eess.SP↗

arXiv2022

Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey

Autonomous systems possess the features of inferring their own state, understanding their surroundings, and performing autonomous navigation. With the applications of learning systems, like deep learning and reinforcement learning, the visual-based self-state estimation, environment perception and navigation capabilities of autonomous systems have been efficiently addressed, and many new learning-based algorithms have surfaced with respect to autonomous visual perception and navigation. In this review, we focus on the applications of learning-based monocular approaches in ego-motion perception, environment perception and navigation in autonomous systems, which is different from previous reviews that discussed traditional methods. First, we delineate the shortcomings of existing classical visual simultaneous localization and mapping (vSLAM) solutions, which demonstrate the necessity to integrate deep learning techniques. Second, we review the visual-based environmental perception and understanding methods based on deep learning, including deep learning-based monocular depth estimation, monocular ego-motion prediction, image enhancement, object detection, semantic segmentation, and their combinations with traditional vSLAM frameworks. Then, we focus on the visual navigation based on learning systems, mainly including reinforcement learning and deep reinforcement learning. Finally, we examine several challenges and promising directions discussed and concluded in related research of learning systems in the era of computer science and robotics.

cs.CV↗

arXiv2022

CoDGraD: A Code-based Distributed Gradient Descent Scheme for Decentralized Convex Optimization

In this paper, we consider a large network containing many regions such that each region is equipped with a worker with some data processing and communication capability. For such a network, some workers may become stragglers due to the failure or heavy delay on computing or communicating. To resolve the above straggling problem, a coded scheme that introduces certain redundancy for every worker was recently proposed, and a gradient coding paradigm was developed to solve convex optimization problems when the network has a centralized fusion center. In this paper, we propose an iterative distributed algorithm, referred as Code-Based Distributed Gradient Descent algorithm (CoDGraD), to solve convex optimization problems over distributed networks. In each iteration of the proposed algorithm, an active worker shares the coded local gradient and approximated solution of the convex optimization problem with non-straggling workers at the adjacent regions only. In this paper, we also provide the consensus and convergence analysis for the CoDGraD algorithm and we demonstrate its performance via numerical simulations.

eess.SY↗