Searcharxiv⌕ Search

arXiv subjects

Lei Yu

Publications and source records attributed to Lei Yu.

At least 163 records · Page 9Linked to original sources
arXiv2023

Generalizing Event-Based Motion Deblurring in Real-World Scenarios

Event-based motion deblurring has shown promising results by exploiting low-latency events. However, current approaches are limited in their practical usage, as they assume the same spatial resolution of inputs and specific blurriness distributions. This work addresses these limitations and aims to generalize the performance of event-based deblurring in real-world scenarios. We propose a scale-aware network that allows flexible input spatial scales and enables learning from different temporal scales of motion blur. A two-stage self-supervised learning scheme is then developed to fit real-world data distribution. By utilizing the relativity of blurriness, our approach efficiently ensures the restored brightness and structure of latent images and further generalizes deblurring performance to handle varying spatial and temporal scales of motion blur in a self-distillation manner. Our method is extensively evaluated, demonstrating remarkable performance, and we also introduce a real-world dataset consisting of multi-scale blurry frames and events to facilitate research in event-based deblurring.

cs.CV↗
arXiv2023

Video Frame Interpolation with Stereo Event and Intensity Camera

The stereo event-intensity camera setup is widely applied to leverage the advantages of both event cameras with low latency and intensity cameras that capture accurate brightness and texture information. However, such a setup commonly encounters cross-modality parallax that is difficult to be eliminated solely with stereo rectification especially for real-world scenes with complex motions and varying depths, posing artifacts and distortion for existing Event-based Video Frame Interpolation (E-VFI) approaches. To tackle this problem, we propose a novel Stereo Event-based VFI (SE-VFI) network (SEVFI-Net) to generate high-quality intermediate frames and corresponding disparities from misaligned inputs consisting of two consecutive keyframes and event streams emitted between them. Specifically, we propose a Feature Aggregation Module (FAM) to alleviate the parallax and achieve spatial alignment in the feature domain. We then exploit the fused features accomplishing accurate optical flow and disparity estimation, and achieving better interpolated results through flow-based and synthesis-based ways. We also build a stereo visual acquisition system composed of an event camera and an RGB-D camera to collect a new Stereo Event-Intensity Dataset (SEID) containing diverse scenes with complex motions and varying depths. Experiments on public real-world stereo datasets, i.e., DSEC and MVSEC, and our SEID dataset demonstrate that our proposed SEVFI-Net outperforms state-of-the-art methods by a large margin.

cs.CV↗
arXiv2023

Gray--Wyner and Mutual Information Regions for Doubly Symmetric Binary Sources and Gaussian Sources

Nonconvex optimization plays a key role in multi-user information theory and related fields, but it is usually difficult to solve. The rate region of the Gray--Wyner source coding system (or almost equivalently, the mutual information region) is a typical example in nonconvex optimization, whose single-letter expression was given by Gray and Wyner. However, due to the nonconvexity of the optimization involved in this expression, previously, there was none nontrivial discrete source for which the analytic expression is known. In this paper, we propose a new strategy to solve nonconvex optimization problems. By this strategy, we provide the analytic expression for the doubly symmetric binary source (DSBS), which confirms positively a conjecture of Gray and Wyner in 1974. We also provide the analytic expression of the mutual information region for the Gaussian source, and provide (or recover) the analytic expressions of the lossy Gray--Wyner region for both the DSBS and Gaussian source. Our proof strategy relies on an auxiliary measure technique and the analytical expression of the optimal-transport divergence region.

cs.IT↗
arXiv2023

Motion Robust High-Speed Light-Weighted Object Detection With Event Camera

In this work, we propose a motion robust and high-speed detection pipeline which better leverages the event data. First, we design an event stream representation called temporal active focus (TAF), which efficiently utilizes the spatial-temporal asynchronous event stream, constructing event tensors robust to object motions. Then, we propose a module called the bifurcated folding module (BFM), which encodes the rich temporal information in the TAF tensor at the input layer of the detector. Following this, we design a high-speed lightweight detector called agile event detector (AED) plus a simple but effective data augmentation method, to enhance the detection accuracy and reduce the model's parameter. Experiments on two typical real-scene event camera object detection datasets show that our method is competitive in terms of accuracy, efficiency, and the number of parameters. By classifying objects into multiple motion levels based on the optical flow density metric, we further illustrated the robustness of our method for objects with different velocities relative to the camera. The codes and trained models are available at https://github.com/HarmoniaLeo/FRLW-EvD .

cs.CV↗
arXiv2023

A Natural Bias for Language Generation Models

After just a few hundred training updates, a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, making it difficult to estimate the probability distribution over next tokens. Yet around this point, these models have identified a simple, loss-minimising behaviour: to output the unigram distribution of the target training corpus. The use of such a heuristic raises the question: Can we initialise our models with this behaviour and save precious compute resources and model capacity? Here we show that we can effectively endow standard neural language generation models with a separate module that reflects unigram frequency statistics as prior knowledge, simply by initialising the bias term in a model's final linear layer with the log-unigram distribution. We use neural machine translation as a test bed for this simple technique and observe that it: (i) improves learning efficiency; (ii) achieves better overall performance; and perhaps most importantly (iii) appears to disentangle strong frequency effects by encouraging the model to specialise in non-frequency-related aspects of language.

cs.CL↗
arXiv2023

Word sense extension

Humans often make creative use of words to express novel senses. A long-standing effort in natural language processing has been focusing on word sense disambiguation (WSD), but little has been explored about how the sense inventory of a word may be extended toward novel meanings. We present a paradigm of word sense extension (WSE) that enables words to spawn new senses toward novel context. We develop a framework that simulates novel word sense extension by first partitioning a polysemous word type into two pseudo-tokens that mark its different senses, and then inferring whether the meaning of a pseudo-token can be extended to convey the sense denoted by the token partitioned from the same word type. Our framework combines cognitive models of chaining with a learning scheme that transforms a language model embedding space to support various types of word sense extension. We evaluate our framework against several competitive baselines and show that it is superior in predicting plausible novel senses for over 7,500 English words. Furthermore, we show that our WSE framework improves performance over a range of transformer-based WSD models in predicting rare word senses with few or zero mentions in the training data.

cs.CL↗
arXiv2023

Dimension-Free Bounds for the Union-Closed Sets Conjecture

The union-closed sets conjecture states that in any nonempty union-closed family $\mathcal{F}$ of subsets of a finite set, there exists an element contained in at least a proportion $1/2$ of the sets of $\mathcal{F}$. Using the information-theoretic method, Gilmer \cite{gilmer2022constant} recently showed that there exists an element contained in at least a proportion $0.01$ of the sets of such $\mathcal{F}$. He conjectured that his technique can be pushed to the constant $\frac{3-\sqrt{5}}{2}$ which was subsequently confirmed by several researchers \cite{sawin2022improved,chase2022approximate,alweiss2022improved,pebody2022extension}. Furthermore, Sawin \cite{sawin2022improved} showed that Gilmer's technique can be improved to obtain a bound better than $\frac{3-\sqrt{5}}{2}$, but this new bound is not explicitly given by Sawin. This paper further improves Gilmer's technique to derive new bounds in the optimization form for the union-closed sets conjecture. These bounds include Sawin's improvement as a special case. By providing cardinality bounds on auxiliary random variables, we make Sawin's improvement computable, and then evaluate it numerically which yields a bound around $0.38234$, slightly better than $\frac{3-\sqrt{5}}{2}\approx0.38197$. }

math.CO↗
arXiv2023

"Seeing'' Electric Network Frequency from Events

Most of the artificial lights fluctuate in response to the grid's alternating current and exhibit subtle variations in terms of both intensity and spectrum, providing the potential to estimate the Electric Network Frequency (ENF) from conventional frame-based videos. Nevertheless, the performance of Video-based ENF (V-ENF) estimation largely relies on the imaging quality and thus may suffer from significant interference caused by non-ideal sampling, motion, and extreme lighting conditions. In this paper, we show that the ENF can be extracted without the above limitations from a new modality provided by the so-called event camera, a neuromorphic sensor that encodes the light intensity variations and asynchronously emits events with extremely high temporal resolution and high dynamic range. Specifically, we first formulate and validate the physical mechanism for the ENF captured in events, and then propose a simple yet robust Event-based ENF (E-ENF) estimation method through mode filtering and harmonic enhancement. Furthermore, we build an Event-Video ENF Dataset (EV-ENFD) that records both events and videos in diverse scenes. Extensive experiments on EV-ENFD demonstrate that our proposed E-ENF method can extract more accurate ENF traces, outperforming the conventional V-ENF by a large margin, especially in challenging environments with object motions and extreme lighting conditions. The code and dataset are available at https://xlx-creater.github.io/E-ENF.

eess.IV↗
arXiv2023

On the $Φ$-Stability and Related Conjectures

Given a convex function $Φ:[0,1]\to\mathbb{R}$ and the mean $\mathbb{E}f(\mathbf{X})=a\in[0,1]$, which Boolean function $f$ maximizes the $Φ$-stability $\mathbb{E}[Φ(T_ρf(\mathbf{X}))]$ of $f$? Here $\mathbf{X}$ is a random vector uniformly distributed on the discrete cube $\{-1,1\}^{n}$ and $T_ρ$ is the Bonami-Beckner operator. Special cases of this problem include the (symmetric and asymmetric) $α$-stability problems and the ``Most Informative Boolean Function'' problem. In this paper, we provide several upper bounds for the maximal $Φ$-stability. When specializing $Φ$ to some particular forms, by these upper bounds, we partially resolve Mossel and O'Donnell's conjecture on $α$-stability with $α>2$, Li and Médard's conjecture on $α$-stability with $1<α<2$, and Courtade and Kumar's conjecture on the ``Most Informative Boolean Function'' which corresponds to a conjecture on $α$-stability with $α=1$. Our proofs are based on discrete Fourier analysis, optimization theory, and improvements of the Friedgut--Kalai--Naor (FKN) theorem. Our improvements of the FKN theorem are sharp or asymptotically sharp for certain cases.

math.PR↗
arXiv2023

Self-Supervised Scene Dynamic Recovery from Rolling Shutter Images and Events

Scene Dynamic Recovery (SDR) by inverting distorted Rolling Shutter (RS) images to an undistorted high frame-rate Global Shutter (GS) video is a severely ill-posed problem due to the missing temporal dynamic information in both RS intra-frame scanlines and inter-frame exposures, particularly when prior knowledge about camera/object motions is unavailable. Commonly used artificial assumptions on scenes/motions and data-specific characteristics are prone to producing sub-optimal solutions in real-world scenarios. To address this challenge, we propose an event-based SDR network within a self-supervised learning paradigm, i.e., SelfUnroll. We leverage the extremely high temporal resolution of event cameras to provide accurate inter/intra-frame dynamic information. Specifically, an Event-based Inter/intra-frame Compensator (E-IC) is proposed to predict the per-pixel dynamic between arbitrary time intervals, including the temporal transition and spatial translation. Exploring connections in terms of RS-RS, RS-GS, and GS-RS, we explicitly formulate mutual constraints with the proposed E-IC, resulting in supervisions without ground-truth GS images. Extensive evaluations over synthetic and real datasets demonstrate that the proposed method achieves state-of-the-art and shows remarkable performance for event-based RS2GS inversion in real-world scenarios. The dataset and code are available at https://w3un.github.io/selfunroll/.

cs.CV↗
arXiv2023

Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection

Detecting arbitrarily oriented tiny objects poses intense challenges to existing detectors, especially for label assignment. Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce severe mismatch and imbalance issues. Specifically, the position prior, positive sample feature, and instance are mismatched, and the learning of extreme-shaped objects is biased and unbalanced due to little proper feature supervision. To tackle these issues, we propose a dynamic prior along with the coarse-to-fine assigner, dubbed DCFL. For one thing, we model the prior, label assignment, and object representation all in a dynamic manner to alleviate the mismatch issue. For another, we leverage the coarse prior matching and finer posterior constraint to dynamically assign labels, providing appropriate and relatively balanced supervision for diverse instances. Extensive experiments on six datasets show substantial improvements to the baseline. Notably, we obtain the state-of-the-art performance for one-stage detectors on the DOTA-v1.5, DOTA-v2.0, and DIOR-R datasets under single-scale training and testing. Codes are available at https://github.com/Chasel-Tsui/mmrotate-dcfl.

cs.CV↗
arXiv2023

DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution

Efficient deep learning-based approaches have achieved remarkable performance in single image super-resolution. However, recent studies on efficient super-resolution have mainly focused on reducing the number of parameters and floating-point operations through various network designs. Although these methods can decrease the number of parameters and floating-point operations, they may not necessarily reduce actual running time. To address this issue, we propose a novel multi-stage lightweight network boosting method, which can enable lightweight networks to achieve outstanding performance. Specifically, we leverage enhanced high-resolution output as additional supervision to improve the learning ability of lightweight student networks. Upon convergence of the student network, we further simplify our network structure to a more lightweight level using reparameterization techniques and iterative network pruning. Meanwhile, we adopt an effective lightweight network training strategy that combines multi-anchor distillation and progressive learning, enabling the lightweight network to achieve outstanding performance. Ultimately, our proposed method achieves the fastest inference time among all participants in the NTIRE 2023 efficient super-resolution challenge while maintaining competitive super-resolution performance. Additionally, extensive experiments are conducted to demonstrate the effectiveness of the proposed components. The results show that our approach achieves comparable performance in representative dataset DIV2K, both qualitatively and quantitatively, with faster inference and fewer number of network parameters.

cs.CV↗
arXiv2023

Recovering Continuous Scene Dynamics from A Single Blurry Image with Events

This paper aims at demystifying a single motion-blurred image with events and revealing temporally continuous scene dynamics encrypted behind motion blurs. To achieve this end, an Implicit Video Function (IVF) is learned to represent a single motion blurred image with concurrent events, enabling the latent sharp image restoration of arbitrary timestamps in the range of imaging exposures. Specifically, a dual attention transformer is proposed to efficiently leverage merits from both modalities, i.e., the high temporal resolution of event features and the smoothness of image features, alleviating temporal ambiguities while suppressing the event noise. The proposed network is trained only with the supervision of ground-truth images of limited referenced timestamps. Motion- and texture-guided supervisions are employed simultaneously to enhance restorations of the non-referenced timestamps and improve the overall sharpness. Experiments on synthetic, semi-synthetic, and real-world datasets demonstrate that our proposed method outperforms state-of-the-art methods by a large margin in terms of both objective PSNR and SSIM measurements and subjective evaluations.

cs.CV↗
arXiv2023

High-level semantic feature matters few-shot unsupervised domain adaptation

In few-shot unsupervised domain adaptation (FS-UDA), most existing methods followed the few-shot learning (FSL) methods to leverage the low-level local features (learned from conventional convolutional models, e.g., ResNet) for classification. However, the goal of FS-UDA and FSL are relevant yet distinct, since FS-UDA aims to classify the samples in target domain rather than source domain. We found that the local features are insufficient to FS-UDA, which could introduce noise or bias against classification, and not be used to effectively align the domains. To address the above issues, we aim to refine the local features to be more discriminative and relevant to classification. Thus, we propose a novel task-specific semantic feature learning method (TSECS) for FS-UDA. TSECS learns high-level semantic features for image-to-class similarity measurement. Based on the high-level features, we design a cross-domain self-training strategy to leverage the few labeled samples in source domain to build the classifier in target domain. In addition, we minimize the KL divergence of the high-level feature distributions between source and target domains to shorten the distance of the samples between the two domains. Extensive experiments on DomainNet show that the proposed method significantly outperforms SOTA methods in FS-UDA by a large margin (i.e., 10%).

cs.CV↗
arXiv2023

Learning to Super-Resolve Blurry Images with Events

Super-Resolution from a single motion Blurred image (SRB) is a severely ill-posed problem due to the joint degradation of motion blurs and low spatial resolution. In this paper, we employ events to alleviate the burden of SRB and propose an Event-enhanced SRB (E-SRB) algorithm, which can generate a sequence of sharp and clear images with High Resolution (HR) from a single blurry image with Low Resolution (LR). To achieve this end, we formulate an event-enhanced degeneration model to consider the low spatial resolution, motion blurs, and event noises simultaneously. We then build an event-enhanced Sparse Learning Network (eSL-Net++) upon a dual sparse learning scheme where both events and intensity frames are modeled with sparse representations. Furthermore, we propose an event shuffle-and-merge scheme to extend the single-frame SRB to the sequence-frame SRB without any additional training process. Experimental results on synthetic and real-world datasets show that the proposed eSL-Net++ outperforms state-of-the-art methods by a large margin. Datasets, codes, and more results are available at https://github.com/ShinyWang33/eSL-Net-Plusplus.

cs.CV↗
arXiv2023

A Comparison of Decision Forest Inference Platforms from A Database Perspective

Decision forest, including RandomForest, XGBoost, and LightGBM, is one of the most popular machine learning techniques used in many industrial scenarios, such as credit card fraud detection, ranking, and business intelligence. Because the inference process is usually performance-critical, a number of frameworks were developed and dedicated for decision forest inference, such as ONNX, TreeLite from Amazon, TensorFlow Decision Forest from Google, HummingBird from Microsoft, Nvidia FIL, and lleaves. However, these frameworks are all decoupled with data management frameworks. It is unclear whether in-database inference will improve the overall performance. In addition, these frameworks used different algorithms, optimization techniques, and parallelism models. It is unclear how these implementations will affect the overall performance and how to make design decisions for an in-database inference framework. In this work, we investigated the above questions by comprehensively comparing the end-to-end performance of the aforementioned inference frameworks and netsDB, an in-database inference framework we implemented. Through this study, we identified that netsDB is best suited for handling small-scale models on large-scale datasets and all-scale models on small-scale datasets, for which it achieved up to hundreds of times of speedup. In addition, the relation-centric representation we proposed significantly improved netsDB's performance in handling large-scale models, while the model reuse optimization we proposed further improved netsDB's performance in handling small-scale datasets.

cs.DB↗
arXiv2022

QPanda: high-performance quantum computing framework for multiple application scenarios

With the birth of Noisy Intermediate Scale Quantum (NISQ) devices and the verification of "quantum supremacy" in random number sampling and boson sampling, more and more fields hope to use quantum computers to solve specific problems, such as aerodynamic design, route allocation, financial option prediction, quantum chemical simulation to find new materials, and the challenge of quantum cryptography to automotive industry security. However, these fields still need to constantly explore quantum algorithms that adapt to the current NISQ machine, so a quantum programming framework that can face multi-scenarios and application needs is required. Therefore, this paper proposes QPanda, an application scenario-oriented quantum programming framework with high-performance simulation. Such as designing quantum chemical simulation algorithms based on it to explore new materials, building a quantum machine learning framework to serve finance, etc. This framework implements high-performance simulation of quantum circuits, a configuration of the fusion processing backend of quantum computers and supercomputers, and compilation and optimization methods of quantum programs for NISQ machines. Finally, the experiment shows that quantum jobs can be executed with high fidelity on the quantum processor using quantum circuit compile and optimized interface and have better simulation performance.

cs.PL↗
arXiv2022

Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features

While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power. Training dynamics, i.e., the traces left by iterations of optimization algorithms, have recently been proved to be effective to localize mislabeled samples with hand-crafted features. In this paper, beyond manually designed features, we introduce a novel learning-based solution, leveraging a noise detector, instanced by an LSTM network, which learns to predict whether a sample was mislabeled using the raw training dynamics as input. Specifically, the proposed method trains the noise detector in a supervised manner using the dataset with synthesized label noises and can adapt to various datasets (either naturally or synthesized label-noised) without retraining. We conduct extensive experiments to evaluate the proposed method. We train the noise detector based on the synthesized label-noised CIFAR dataset and test such noise detector on Tiny ImageNet, CUB-200, Caltech-256, WebVision and Clothing1M. Results show that the proposed method precisely detects mislabeled samples on various datasets without further adaptation, and outperforms state-of-the-art methods. Besides, more experiments demonstrate that the mislabel identification can guide a label correction, namely data debugging, providing orthogonal improvements of algorithm-centric state-of-the-art techniques from the data aspect.

cs.CV↗