Lei Yu

Chao Ding, Mingyuan Lin, Haijian Zhang et al.

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.

Lei Yu

The meaning of polysemous words often varies in a highly productive yet predictable way. Generalizing the regularity between conventional senses to derive novel word meaning is crucial for automated processing of non-literal language uses such as figurative expressions. We introduce a novel task called systematic word meta-sense extension (SWORME) to test and improve language models' ability to extend word meaning to denote new semantic domains (also called meta-senses) that bear regular semantic relations with existing senses. We found that language models prefer incremental lexical semantic change toward conceptually similar meta-senses such as logical metonymy, and are much worse at predicting highly non-literal meaning extensions such as metaphors. We propose a novel analogy-based method of word meaning extension, and show that it effectively improves language model systematicity in making both gradual and radical types of meta-sense extension. We further demonstrate that learning systematic meta-sense extensions benefits language models on multiple benchmarks of figurative language understanding.

Yihuai Hong, Lei Yu, Haiqin Yang et al.

The task of "unlearning" certain concepts in large language models (LLMs) has attracted immense attention recently, due to its importance in mitigating undesirable model behaviours, such as the generation of harmful, private, or incorrect information. Current protocols to evaluate unlearning methods largely rely on behavioral tests, without monitoring the presence of unlearned knowledge within the model's parameters. This residual knowledge can be adversarially exploited to recover the erased information post-unlearning. We argue that unlearning should also be evaluated internally, by considering changes in the parametric knowledge traces of the unlearned concepts. To this end, we propose a general evaluation methodology that leverages vocabulary projections to inspect concepts encoded in model parameters. We use this approach to localize "concept vectors" - parameter vectors that encode concrete concepts - and construct ConceptVectors, a benchmark dataset containing hundreds of common concepts and their parametric knowledge traces within two open-source LLMs. Evaluation on ConceptVectors shows that existing unlearning methods minimally impact concept vectors and mostly suppress them during inference, while directly ablating these vectors demonstrably removes the associated knowledge and significantly reduces the model's susceptibility to adversarial manipulation. Our results highlight limitations in behavioral-based unlearning evaluations and call for future work to include parameter-based evaluations. To support this, we release our code and benchmark at https://github.com/yihuaihong/ConceptVectors.

Xiqiang Qu, Jun Chen, Lei Yu et al.

We establish a single-letter characterization of the fundamental distortion-rate-perception tradeoff with limited common randomness under the squared error distortion measure and the squared Wasserstein-2 perception measure. Moreover, it is shown that this single-letter characterization can be explicitly evaluated for the Gaussian source. Various notions of universal representation are also clarified.

Feiyu Yin, Yu Lei, Siyuan Dai et al.

Brain connectivity alternations associated with brain disorders have been widely reported in resting-state functional imaging (rs-fMRI) and diffusion tensor imaging (DTI). While many dual-modal fusion methods based on graph neural networks (GNNs) have been proposed, they generally follow homogenous fusion ways ignoring rich heterogeneity of dual-modal information. To address this issue, we propose a novel method that integrates functional and structural connectivity based on heterogeneous graph neural networks (HGNNs) to better leverage the rich heterogeneity in dual-modal images. We firstly use blood oxygen level dependency and whiter matter structure information provided by rs-fMRI and DTI to establish homo-meta-path, capturing node relationships within the same modality. At the same time, we propose to establish hetero-meta-path based on structure-function coupling and brain community searching to capture relations among cross-modal nodes. Secondly, we further introduce a heterogeneous graph pooling strategy that automatically balances homo- and hetero-meta-path, effectively leveraging heterogeneous information and preventing feature confusion after pooling. Thirdly, based on the flexibility of heterogeneous graphs, we propose a heterogeneous graph data augmentation approach that can conveniently address the sample imbalance issue commonly seen in clinical diagnosis. We evaluate our method on ADNI-3 dataset for mild cognitive impairment (MCI) diagnosis. Experimental results indicate the proposed method is effective and superior to other algorithms, with a mean classification accuracy of 93.3%.

Kerui Wu, Ka-Ho Chow, Wenqi Wei et al. · gatech

As Graph Neural Networks (GNNs) become increasingly popular for learning from large-scale graph data across various domains, their susceptibility to adversarial attacks when using graph reduction techniques for scalability remains underexplored. In this paper, we present an extensive empirical study to investigate the impact of graph reduction techniques, specifically graph coarsening and sparsification, on the robustness of GNNs against adversarial attacks. Through extensive experiments involving multiple datasets and GNN architectures, we examine the effects of four sparsification and six coarsening methods on the poisoning attacks. Our results indicate that, while graph sparsification can mitigate the effectiveness of certain poisoning attacks, such as Mettack, it has limited impact on others, like PGD. Conversely, graph coarsening tends to amplify the adversarial impact, significantly reducing classification accuracy as the reduction ratio decreases. Additionally, we provide a novel analysis of the causes driving these effects and examine how defensive GNN models perform under graph reduction, offering practical insights for designing robust GNNs within graph acceleration systems.

Haitian Zhang, Xiangyuan Wang, Chang Xu et al.

Fusing Events and RGB images for object detection leverages the robustness of Event cameras in adverse environments and the rich semantic information provided by RGB cameras. However, two critical mismatches: low-latency Events \textit{vs.}~high-latency RGB frames; temporally sparse labels in training \textit{vs.}~continuous flow in inference, significantly hinder the high-frequency fusion-based object detection. To address these challenges, we propose the \textbf{F}requency-\textbf{A}daptive Low-Latency \textbf{O}bject \textbf{D}etector (FAOD). FAOD aligns low-frequency RGB frames with high-frequency Events through an Align Module, which reinforces cross-modal style and spatial proximity to address the Event-RGB Mismatch. We further propose a training strategy, Time Shift, which enforces the module to align the prediction from temporally shifted Event-RGB pairs and their original representation, that is, consistent with Event-aligned annotations. This strategy enables the network to use high-frequency Event data as the primary reference while treating low-frequency RGB images as supplementary information, retaining the low-latency nature of the Event stream toward high-frequency detection. Furthermore, we observe that these corrected Event-RGB pairs demonstrate better generalization from low training frequency to higher inference frequencies compared to using Event data alone. Extensive experiments on the PKU-DAVIS-SOD and DSEC-Detection datasets demonstrate that our FAOD achieves SOTA performance. Specifically, in the PKU-DAVIS-SOD Dataset, FAOD achieves 9.8 points improvement in terms of the mAP in fully paired Event-RGB data with only a quarter of the parameters compared to SODFormer, and even maintains robust performance (only a 3 points drop in mAP) under 80$\times$ Event-RGB frequency mismatch.

Huijiao Wang, Shenghao Zhao, Lei Yu et al.

Image quality degradation caused by raindrops is one of the most important but challenging problems that reduce the performance of vision systems. Most existing raindrop removal algorithms are based on a supervised learning method using pairwise images, which are hard to obtain in real-world applications. This study proposes a deep neural network for raindrop removal based on unsupervised learning, which only requires two unpaired image sets with and without raindrops. Our proposed model performs layer separation based on cycle network architecture, which aims to separate a rainy image into a raindrop layer, a transparency mask, and a clean background layer. The clean background layer is the target raindrop removal result, while the transparency mask indicates the spatial locations of the raindrops. In addition, the proposed model applies a feedback mechanism to benefit layer separation by refining low-level representation with high-level information. i.e., the output of the previous iteration is used as input for the next iteration, together with the input image with raindrops. As a result, raindrops could be gradually removed through this feedback manner. Extensive experiments on raindrop benchmark datasets demonstrate the effectiveness of the proposed method on quantitative metrics and visual quality.

Lei Yu, Vincent Y. F. Tan

The random variable simulation problem consists in using a $k$-dimensional i.i.d. random vector $X^{k}$ with distribution $P_{X}^{k}$ to simulate an $n$-dimensional i.i.d. random vector $Y^{n}$ so that its distribution is approximately $Q_{Y}^{n}$. In contrast to previous works, in this paper we consider the standard Rényi divergence and two variants of all orders to measure the level of approximation. These two variants are the max-Rényi divergence $D_α^{\mathsf{max}}(P,Q)$ and the sum-Rényi divergence $D_α^{+}(P,Q)$. When $α=\infty$, these two measures are strong because for any $ε>0$, $D_{\infty}^{\mathsf{max}}(P,Q)\leqε$ or $D_{\infty}^{+}(P,Q)\leqε$ implies $e^{-ε}\leq\frac{P(x)}{Q(x)}\leq e^ε$ for all $x$. Under these Rényi divergence measures, we characterize the asymptotics of normalized divergences as well as the Rényi conversion rates. The latter is defined as the supremum of $\frac{n}{k}$ such that the Rényi divergences vanish asymptotically. In addition, when the Rényi parameter is in the interval $(0,1)$, the Rényi conversion rates equal the ratio of the Shannon entropies $\frac{H\left(P_{X}\right)}{H\left(Q_{Y}\right)}$, which is consistent with traditional results in which the total variation measure was adopted. When the Rényi parameter is in the interval $(1,\infty]$, the Rényi conversion rates are, in general, smaller than $\frac{H\left(P_{X}\right)}{H\left(Q_{Y}\right)}$. When specialized to the case in which either $P_{X}$ or $Q_{Y}$ is uniform, the simulation problem reduces to the source resolvability and intrinsic randomness problems. The preceding results are used to characterize the asymptotics of Rényi divergences and the Rényi conversion rates for these two cases.

Lei Yu, Vincent Y. F. Tan

A coupling of two distributions $P_{X}$ and $P_{Y}$ is a joint distribution $P_{XY}$ with marginal distributions equal to $P_{X}$ and $P_{Y}$. Given marginals $P_{X}$ and $P_{Y}$ and a real-valued function $f$ of the joint distribution $P_{XY}$, what is its minimum over all couplings $P_{XY}$ of $P_{X}$ and $P_{Y}$? We study the asymptotics of such coupling problems with different $f$'s and with $X$ and $Y$ replaced by $X^{n}=(X_{1},\ldots,X_{n})$ and $Y^{n}=(Y_{1},\ldots,Y_{n})$ where $X_{i}$ and $Y_{i}$ are i.i.d.\ copies of random variables $X$ and $Y$ with distributions $P_{X}$ and $P_{Y}$ respectively. These include the maximal coupling, minimum distance coupling, maximal guessing coupling, and minimum entropy coupling problems. We characterize the limiting values of these coupling problems as $n$ tends to infinity. We show that they typically converge at least exponentially fast to their limits. Moreover, for the problems of maximal coupling and minimum excess-distance probability coupling, we also characterize (or bound) the optimal convergence rates (exponents). Furthermore, for the maximal guessing coupling problem we show that it is equivalent to the distribution approximation problem. Therefore, some existing results for the latter problem can be used to derive the asymptotics of the maximal guessing coupling problem. We also study the asymptotics of the maximal guessing coupling problem for two \emph{general} sources and a generalization of this problem, named the \emph{maximal guessing coupling through a channel problem}. We apply the preceding results to several new information-theoretic problems, including exact intrinsic randomness, exact resolvability, channel capacity with input distribution constraint, and perfect stealth and secrecy communication.

Lei Yu, Houqiang Li, Chang Wen Chen

In literature, different common informations were defined by Gács and Körner, by Wyner, and by Kumar, Li, and Gamal, respectively. In this paper, we define two generalized versions of common informations, named approximate and exact information-correlation functions, by exploiting the conditional maximal correlation as a commonness or privacy measure. These two generalized common informations encompass the notions of Gács-Körner's, Wyner's, and Kumar-Li-Gamal's common informations as special cases. Furthermore, to give operational characterizations of these two generalized common informations, we also study the problems of private sources synthesis and common information extraction, and show that the information-correlation functions are equal to the minimum rates of commonness needed to ensure that some conditional maximal correlation constraints are satisfied for the centralized setting versions of these problems. As a byproduct, the conditional maximal correlation has been studied as well.

Lei Yu, Houqiang Li, Weiping Li

This paper investigates a joint source-channel secrecy problem for the Shannon cipher broadcast system. We suppose list secrecy is applied, i.e., a wiretapper is allowed to produce a list of reconstruction sequences and the secrecy is measured by the minimum distortion over the entire list. For discrete communication cases, we propose a permutation-based uncoded scheme, which cascades a random permutation with a symbol-by-symbol mapping. Using this scheme, we derive an inner bound for the admissible region of secret key rate, list rate, wiretapper distortion, and distortions of legitimate users. For the converse part, we easily obtain an outer bound for the admissible region from an existing result. Comparing the outer bound with the inner bound shows that the proposed scheme is optimal under certain conditions. Besides, we extend the proposed scheme to the scalar and vector Gaussian communication scenarios, and characterize the corresponding performance as well. For these two cases, we also propose another uncoded scheme, orthogonal-transform-based scheme, which achieves the same performance as the permutation-based scheme. Interestingly, by introducing the random permutation or the random orthogonal transform into the traditional uncoded scheme, the proposed uncoded schemes, on one hand, provide a certain level of secrecy, and on the other hand, do not lose any performance in terms of the distortions for legitimate users.

Lei Yu, Houqiang Li, Weiping Li

Recently, a secrecy measure based on list-reconstruction has been proposed [2], in which a wiretapper is allowed to produce a list of $2^{mR_{L}}$ reconstruction sequences and the secrecy is measured by the minimum distortion over the entire list. In this paper, we show that this list secrecy problem is equivalent to the one with secrecy measured by a new quantity \emph{lossy-equivocation}, which is proven to be the minimum optimistic 1-achievable source coding rate (the minimum coding rate needed to reconstruct the source within target distortion with positive probability for \emph{infinitely many blocklengths}) of the source with the wiretapped signal as two-sided information, and also can be seen as a lossy extension of conventional equivocation. Upon this (or list) secrecy measure, we study source-channel secrecy problem in the discrete memoryless Shannon cipher system with \emph{noisy} wiretap channel. Two inner bounds and an outer bound on the achievable region of secret key rate, list rate, wiretapper distortion, and distortion of legitimate user are given. The inner bounds are derived by using uncoded scheme and (operationally) separate scheme, respectively. Thanks to the equivalence between lossy-equivocation secrecy and list secrecy, information spectrum method is leveraged to prove the outer bound. As special cases, the admissible region for the case of degraded wiretap channel or lossless communication for legitimate user has been characterized completely. For both these two cases, separate scheme is proven to be optimal. Interestingly, however, separation indeed suffers performance loss for other certain cases. Besides, we also extend our results to characterize the achievable region for Gaussian communication case. As a side product optimistic lossy source coding has also been addressed.