Transition role of entangled data in quantum machine learning.

Entanglement serves as the resource to empower quantum computing. Recent progress has highlighted its positive impact on learning quantum dynamics, wherein the integration of entanglement into quantum operations or measurements of quantum machine learning (QML) models leads to substantial reductions in training data size, surpassing a specified prediction error threshold. However, an analytical understanding of how the entanglement degree in data affects model performance remains elusive. In this study, we address this knowledge gap by establishing a quantum no-free-lunch (NFL) theorem for learning quantum dynamics using entangled data. Contrary to previous findings, we prove that the impact of entangled data on prediction error exhibits a dual effect, depending on the number of permitted measurements. With a sufficient number of measurements, increasing the entanglement of training data consistently reduces the prediction error or decreases the required size of the training data to achieve the same prediction error. Conversely, when few measurements are allowed, employing highly entangled data could lead to an increased prediction error. The achieved results provide critical guidance for designing advanced QML protocols, especially for those tailored for execution on early-stage quantum computers with limited access to quantum resources.

Federated Learning With Only Positive Labels by Exploring Label Correlations.

Federated learning (FL) aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this article, we study the multilabel classification (MLC) problem under the FL setting, where trivial solution and extremely poor performance may be obtained, especially when only positive data with respect to a single class label is provided for each client. This issue can be addressed by adding a specially designed regularizer on the server side. Although effective sometimes, the label correlations are simply ignored and thus suboptimal performance may be obtained. Besides, it is expensive and unsafe to exchange user's private embeddings between server and clients frequently, especially when training model in the contrastive way. To remedy these drawbacks, we propose a novel and generic method termed federated averaging (FedAvg) by exploring label correlations (FedALCs). Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training. To further improve the safety and also reduce the communication overhead, we propose a variant to learn fixed class embedding for each client, so that the server and clients only need to exchange class embeddings once. Extensive experiments on multiple popular datasets demonstrate that our FedALC can significantly outperform the existing counterparts.

Hierarchical Perceptual Noise Injection for Social Media Fingerprint Privacy Protection.

Billions of people share images from their daily lives on social media every day. However, their biometric information (e.g., fingerprints) could be easily stolen from these images. The threat of fingerprint leakage from social media has created a strong desire to anonymize shared images while maintaining image quality, since fingerprints act as a lifelong individual biometric password. To guard the fingerprint leakage, adversarial attack that involves adding imperceptible perturbations to fingerprint images have emerged as a feasible solution. However, existing works of this kind are either weak in black-box transferability or cause the images to have an unnatural appearance. Motivated by the visual perception hierarchy (i.e., high-level perception exploits model-shared semantics that transfer well across models while low-level perception extracts primitive stimuli that result in high visual sensitivity when a suspicious stimulus is provided), we propose FingerSafe, a hierarchical perceptual protective noise injection framework to address the above mentioned problems. For black-box transferability, we inject protective noises into the fingerprint orientation field to perturb the model-shared high-level semantics (i.e., fingerprint ridges). Considering visual naturalness, we suppress the low-level local contrast stimulus by regularizing the response of the Lateral Geniculate Nucleus. Our proposed FingerSafe is the first to provide feasible fingerprint protection in both digital (up to 94.12%) and realistic scenarios (Twitter and Facebook, up to 68.75%). Our code can be found at https://github.com/nlsde-safety-team/FingerSafe.

Toward Robust Referring Image Segmentation.

Referring Image Segmentation (RIS) is a fundamental vision-language task that outputs object masks based on text descriptions. Many works have achieved considerable progress for RIS, including different fusion method designs. In this work, we explore an essential question, "What if the text description is wrong or misleading?" For example, the described objects are not in the image. We term such a sentence as a negative sentence. However, existing solutions for RIS cannot handle such a setting. To this end, we propose a new formulation of RIS, named Robust Referring Image Segmentation (R-RIS). It considers the negative sentence inputs besides the regular positive text inputs. To facilitate this new task, we create three R-RIS datasets by augmenting existing RIS datasets with negative sentences and propose new metrics to evaluate both types of inputs in a unified manner. Furthermore, we propose a new transformer-based model, called RefSegformer, with a token-based vision and language fusion module. Our design can be easily extended to our R-RIS setting by adding extra blank tokens. Our proposed RefSegformer achieves state-of-the-art results on both RIS and R-RIS datasets, establishing a solid baseline for both settings. Our project page is at https://github.com/jianzongwu/robust-ref-seg.

Towards Open Vocabulary Learning: A Survey.

In the field of visual scene understanding, deep neural networks have made impressive advancements in various core tasks like segmentation, tracking, and detection. However, most approaches operate on the close-set assumption, meaning that the model can only identify pre-defined categories that are present in the training set. Recently, open vocabulary settings were proposed due to the rapid progress of vision language pre-training. These new approaches seek to locate and recognize categories beyond the annotated label space. The open vocabulary approach is more general, practical, and effective than weakly supervised and zero-shot settings. This paper thoroughly reviews open vocabulary learning, summarizing and analyzing recent developments in the field. In particular, we begin by juxtaposing open vocabulary learning with analogous concepts such as zero-shot learning, open-set recognition, and out-of-distribution detection. Subsequently, we examine several pertinent tasks within the realms of segmentation and detection, encompassing long-tail problems, few-shot, and zero-shot settings. As a foundation for our method survey, we first elucidate the fundamental principles of detection and segmentation in close-set scenarios. Next, we examine various contexts where open vocabulary learning is employed, pinpointing recurring design elements and central themes. This is followed by a comparative analysis of recent detection and segmentation methodologies in commonly used datasets and benchmarks. Our review culminates with a synthesis of insights, challenges, and discourse on prospective research trajectories. To our knowledge, this constitutes the inaugural exhaustive literature review on open vocabulary learning. We keep tracing related works at https://github.com/jianzongwu/Awesome-Open-Vocabulary.

Attentive Learning Facilitates Generalization of Neural Networks.

This article studies the generalization of neural networks (NNs) by examining how a network changes when trained on a training sample with or without out-of-distribution (OoD) examples. If the network's predictions are less influenced by fitting OoD examples, then the network learns attentively from the clean training set. A new notion, dataset-distraction stability, is proposed to measure the influence. Extensive CIFAR-10/100 experiments on the different VGG, ResNet, WideResNet, ViT architectures, and optimizers show a negative correlation between the dataset-distraction stability and generalizability. With the distraction stability, we decompose the learning process on the training set S into multiple learning processes on the subsets of S drawn from simpler distributions, i.e., distributions of smaller intrinsic dimensions (IDs), and furthermore, a tighter generalization bound is derived. Through attentive learning, miraculous generalization in deep learning can be explained and novel algorithms can also be designed.

PointWavelet: Learning in Spectral Domain for 3-D Point Cloud Analysis.

With recent success of deep learning in 2-D visual recognition, deep-learning-based 3-D point cloud analysis has received increasing attention from the community, especially due to the rapid development of autonomous driving technologies. However, most existing methods directly learn point features in the spatial domain, leaving the local structures in the spectral domain poorly investigated. In this article, we introduce a new method, PointWavelet, to explore local graphs in the spectral domain via a learnable graph wavelet transform. Specifically, we first introduce the graph wavelet transform to form multiscale spectral graph convolution to learn effective local structural representations. To avoid the time-consuming spectral decomposition, we then devise a learnable graph wavelet transform, which significantly accelerates the overall training process. Extensive experiments on four popular point cloud datasets, ModelNet40, ScanObjectNN, ShapeNet-Part, and S3DIS, demonstrate the effectiveness of the proposed method on point cloud classification and segmentation.

Stereo Image Restoration Via Attention-Guided Correspondence Learning.

Although stereo image restoration has been extensively studied, most existing work focuses on restoring stereo images with limited horizontal parallax due to the binocular symmetry constraint. Stereo images with unlimited parallax (e.g., large ranges and asymmetrical types) are more challenging in real-world applications and have rarely been explored so far. To restore high-quality stereo images with unlimited parallax, this paper proposes an attention-guided correspondence learning method, which learns both self- and cross-views feature correspondence guided by parallax and omnidirectional attention. To learn cross-view feature correspondence, a Selective Parallax Attention Module (SPAM) is proposed to interact with cross-view features under the guidance of parallax attention that adaptively selects receptive fields for different parallax ranges. Furthermore, to handle asymmetrical parallax, we propose a Non-local Omnidirectional Attention Module (NOAM) to learn the non-local correlation of both self- and cross-view contexts, which guides the aggregation of global contextual features. Finally, we propose an Attention-guided Correspondence Learning Restoration Network (ACLRNet) upon SPAMs and NOAMs to restore stereo images by associating the features of two views based on the learned correspondence. Extensive experiments on five benchmark datasets demonstrate the effectiveness and generalization of the proposed method on three stereo image restoration tasks including super-resolution, denoising, and compression artifact reduction.

Boosting Factorization Machines via Saliency-Guided Mixup.

Factorization machines (FMs) are widely used in recommender systems due to their adaptability and ability to learn from sparse data. However, for the ubiquitous non-interactive features in sparse data, existing FMs can only estimate the parameters corresponding to these features via the inner product of their embeddings. Undeniably, they cannot learn the direct interactions of these features, which limits the model's expressive power. To this end, we first present MixFM, inspired by Mixup, to generate auxiliary training data to boost FMs. Unlike existing augmentation strategies that require labor costs and expertise to collect additional information such as position and fields, these augmented data are only by the convex combination of the raw ones without any professional knowledge support. More importantly, if non-interactive features exist in parent samples to be mixed respectively, MixFM will establish their direct interactions. Second, considering that MixFM may generate redundant or even detrimental instances, we further put forward a novel Factorization Machine powered by Saliency-guided Mixup (denoted as SMFM). Guided by the customized saliency, SMFM can generate more informative neighbor data. Through theoretical analysis, we prove that the proposed methods minimize the upper bound of the generalization error, which positively enhances FMs. Finally, extensive experiments on seven datasets confirm that our approaches are superior to baselines. Notably, the results also show that "poisoning" mixed data benefits the FM variants.

Vision Transformer With Quadrangle Attention.

Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the design of hand-crafted windows, which is data-agnostic, constrains the flexibility of transformers to adapt to objects of varying sizes, shapes, and orientations. To address this issue, we propose a novel quadrangle attention (QA) method that extends the window-based attention to a general quadrangle formulation. Our method employs an end-to-end learnable quadrangle regression module that predicts a transformation matrix to transform default windows into target quadrangles for token sampling and attention calculation, enabling the network to model various targets with different shapes and orientations and capture rich context information. We integrate QA into plain and hierarchical vision transformers to create a new architecture named QFormer, which offers minor code modifications and negligible extra computational cost. Extensive experiments on public benchmarks demonstrate that QFormer outperforms existing representative vision transformers on various vision tasks, including classification, object detection, semantic segmentation, and pose estimation. The code will be made publicly available at QFormer.

Pruning Self-Attentions Into Convolutional Layers in Single Path.

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive computational resource consumption and the lack of intrinsic inductive bias for modeling local visual patterns. To solve both issues, we devise a simple yet effective method named Single-Path Vision Transformer pruning (SPViT), to efficiently and automatically compress the pre-trained ViTs into compact models with proper locality added. Specifically, we first propose a novel weight-sharing scheme between MSA and convolutional operations, delivering a single-path space to encode all candidate operations. In this way, we cast the operation search problem as finding which subset of parameters to use in each MSA layer, which significantly reduces the computational cost and optimization difficulty, and the convolution kernels can be well initialized using pre-trained MSA parameters. Relying on the single-path space, we introduce learnable binary gates to encode the operation choices in MSA layers. Similarly, we further employ learnable gates to encode the fine-grained MLP expansion ratios of FFN layers. In this way, our SPViT optimizes the learnable gates to automatically explore from a vast and unified search space and flexibly adjust the MSA-FFN pruning proportions for each individual dense model. We conduct extensive experiments on two representative ViTs showing that our SPViT achieves a new SOTA for pruning on ImageNet-1 k. For example, our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously.

AdaSAM: Boosting sharpness-aware minimization with adaptive learning rate and momentum for training deep neural networks.

Sharpness aware minimization (SAM) optimizer has been extensively explored as it can generalize better for training deep neural networks via introducing extra perturbation steps to flatten the landscape of deep learning models. Integrating SAM with adaptive learning rate and momentum acceleration, dubbed AdaSAM, has already been explored empirically to train large-scale deep neural networks without theoretical guarantee due to the triple difficulties in analyzing the coupled perturbation step, adaptive learning rate and momentum step. In this paper, we try to analyze the convergence rate of AdaSAM in the stochastic non-convex setting. We theoretically show that AdaSAM admits a O(1/bT) convergence rate, which achieves linear speedup property with respect to mini-batch size b. Specifically, to decouple the stochastic gradient steps with the adaptive learning rate and perturbed gradient, we introduce the delayed second-order momentum term to decompose them to make them independent while taking an expectation during the analysis. Then we bound them by showing the adaptive learning rate has a limited range, which makes our analysis feasible. To the best of our knowledge, we are the first to provide the non-trivial convergence rate of SAM with an adaptive learning rate and momentum acceleration. At last, we conduct several experiments on several NLP tasks and the synthetic task, which show that AdaSAM could achieve superior performance compared with SGD, AMSGrad, and SAM optimizers.

ViTPose++: Vision Transformer for Generic Body Pose Estimation.

In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model dubbed ViTPose. ViTPose employs the plain and non-hierarchical vision transformer as an encoder to encode features and a lightweight decoder to decode body keypoints in either a top-down or a bottom-up manner. It can be scaled to 1B parameters by taking the advantage of the scalable model capacity and high parallelism, setting a new Pareto front for throughput and performance. Besides, ViTPose is very flexible regarding the attention type, input resolution, and pre-training and fine-tuning strategy. Based on the flexibility, a novel ViTPose++ model is proposed to deal with heterogeneous body keypoint categories via knowledge factorization, i.e., adopting task-agnostic and task-specific feed-forward networks in the transformer. We also demonstrate that the knowledge of large ViTPose models can be easily transferred to small ones via a simple knowledge token. Our largest single model ViTPose-G sets a new record on the MS COCO test set without model ensemble. Furthermore, our ViTPose++ model achieves state-of-the-art performance simultaneously on a series of body pose estimation tasks, including MS COCO, AI Challenger, OCHuman, MPII for human keypoint detection, COCO-Wholebody for whole-body keypoint detection, as well as AP-10K and APT-36K for animal keypoint detection, without sacrificing inference speed.

Stochastic Optimization for Nonconvex Problem With Inexact Hessian Matrix, Gradient, and Function.

Trust region (TR) and adaptive regularization using cubics (ARC) have proven to have some very appealing theoretical properties for nonconvex optimization by concurrently computing function value, gradient, and Hessian matrix to obtain the next search direction and the adjusted parameters. Although stochastic approximations help largely reduce the computational cost, it is challenging to theoretically guarantee the convergence rate. In this article, we explore a family of stochastic TR (STR) and stochastic ARC (SARC) methods that can simultaneously provide inexact computations of the Hessian matrix, gradient, and function values. Our algorithms require much fewer propagations overhead per iteration than TR and ARC. We prove that the iteration complexity to achieve ϵ -approximate second-order optimality is of the same order as the exact computations demonstrated in previous studies. In addition, the mild conditions on inexactness can be met by leveraging a random sampling technology in the finite-sum minimization problem. Numerical experiments with a nonconvex problem support these findings and demonstrate that, with the same or a similar number of iterations, our algorithms require less computational overhead per iteration than current second-order methods.

Variational Distillation for Multi-View Learning.

Information Bottleneck (IB) provides an information-theoretic principle for multi-view learning by revealing the various components contained in each viewpoint. This highlights the necessity to capture their distinct roles to achieve view-invariance and predictive representations but remains under-explored due to the technical intractability of modeling and organizing innumerable mutual information (MI) terms. Recent studies show that sufficiency and consistency play such key roles in multi-view representation learning, and could be preserved via a variational distillation framework. But when it generalizes to arbitrary viewpoints, such strategy fails as the mutual information terms of consistency become complicated. This paper presents Multi-View Variational Distillation (MV 2 D), tackling the above limitations for generalized multi-view learning. Uniquely, MV 2 D can recognize useful consistent information and prioritize diverse components by their generalization ability. This guides an analytical and scalable solution to achieving both sufficiency and consistency. Additionally, by rigorously reformulating the IB objective, MV 2 D tackles the difficulties in MI optimization and fully realizes the theoretical advantages of the information bottleneck principle. We extensively evaluate our model on diverse tasks to verify its effectiveness, where the considerable gains provide key insights into achieving generalized multi-view representations under a rigorous information-theoretic principle.

Robust Commonsense Reasoning Against Noisy Labels Using Adaptive Correction.

Commonsense reasoning based on knowledge graphs (KGs) is a challenging task that requires predicting complex questions over the described textual contexts and relevant knowledge about the world. However, current methods typically assume clean training scenarios with accurately labeled samples, which are often unrealistic. The training set can include mislabeled samples, and the robustness to label noises is essential for commonsense reasoning methods to be practical, but this problem remains largely unexplored. This work focuses on commonsense reasoning with mislabeled training samples and makes several technical contributions: 1) we first construct diverse augmentations from knowledge and model, and offer a simple yet effective multiple-choice alignment method to divide the training samples into clean, semi-clean, and unclean parts; 2) we design adaptive label correction methods for the semi-clean and unclean samples to exploit the supervised potential of noisy information; and 3) finally, we extensively test these methods on noisy versions of commonsense reasoning benchmarks (CommonsenseQA and OpenbookQA). Experimental results show that the proposed method can significantly enhance robustness and improve overall performance. Furthermore, the proposed method is generally applicable to multiple existing commonsense reasoning frameworks to boost their robustness. The code is available at https://github.com/xdxuyang/CR_Noisy_Labels.

Understanding Deep Learning via Decision Boundary.

This article discovers that the neural network (NN) with lower decision boundary (DB) variability has better generalizability. Two new notions, algorithm DB variability and (ϵ, η) -data DB variability, are proposed to measure the DB variability from the algorithm and data perspectives. Extensive experiments show significant negative correlations between the DB variability and the generalizability. From the theoretical view, two lower bounds based on algorithm DB variability are proposed and do not explicitly depend on the sample size. We also prove an upper bound of order O((1/√m)+ϵ+ηlog(1/η)) based on data DB variability. The bound is convenient to estimate without the requirement of labels and does not explicitly depend on the network size which is usually prohibitively large in deep learning.

Problem-Dependent Power of Quantum Neural Networks on Multiclass Classification.

Quantum neural networks (QNNs) have become an important tool for understanding the physical world, but their advantages and limitations are not fully understood. Some QNNs with specific encoding methods can be efficiently simulated by classical surrogates, while others with quantum memory may perform better than classical classifiers. Here we systematically investigate the problem-dependent power of quantum neural classifiers (QCs) on multiclass classification tasks. Through the analysis of expected risk, a measure that weighs the training loss and the generalization error of a classifier jointly, we identify two key findings: first, the training loss dominates the power rather than the generalization ability; second, QCs undergo a U-shaped risk curve, in contrast to the double-descent risk curve of deep neural classifiers. We also reveal the intrinsic connection between optimal QCs and the Helstrom bound and the equiangular tight frame. Using these findings, we propose a method that exploits loss dynamics of QCs to estimate the optimal hyperparameter settings yielding the minimal risk. Numerical results demonstrate the effectiveness of our approach to explain the superiority of QCs over multilayer Perceptron on parity datasets and their limitations over convolutional neural networks on image datasets. Our work sheds light on the problem-dependent power of QNNs and offers a practical tool for evaluating their potential merit.

Learning Visual Affordance Grounding From Demonstration Videos.

Visual affordance grounding aims to segment all possible interaction regions between people and objects from an image/video, which benefits many applications, such as robot grasping and action recognition. Prevailing methods predominantly depend on the appearance feature of the objects to segment each region of the image, which encounters the following two problems: 1) there are multiple possible regions in an object that people interact with and 2) there are multiple possible human interactions in the same object region. To address these problems, we propose a hand-aided affordance grounding network (HAG-Net) that leverages the aided clues provided by the position and action of the hand in demonstration videos to eliminate the multiple possibilities and better locate the interaction regions in the object. Specifically, HAG-Net adopts a dual-branch structure to process the demonstration video and object image data. For the video branch, we introduce hand-aided attention to enhance the region around the hand in each video frame and then use the long short-term memory (LSTM) network to aggregate the action features. For the object branch, we introduce a semantic enhancement module (SEM) to make the network focus on different parts of the object according to the action classes and utilize a distillation loss to align the output features of the object branch with that of the video branch and transfer the knowledge in the video branch to the object branch. Quantitative and qualitative evaluations on two challenging datasets show that our method has achieved state-of-the-art results for affordance grounding. The source code is available at: https://github.com/lhc1224/HAG-Net.

Leveraged Matrix Completion With Noise.

Completing low-rank matrices from subsampled measurements has received much attention in the past decade. Existing works indicate that O(nrlog2(n)) datums are required to theoretically secure the completion of an n ×n noisy matrix of rank r with high probability, under some quite restrictive assumptions: 1) the underlying matrix must be incoherent and 2) observations follow the uniform distribution. The restrictiveness is partially due to ignoring the roles of the leverage score and the oracle information of each element. In this article, we employ the leverage scores to characterize the importance of each element and significantly relax assumptions to: 1) not any other structure assumptions are imposed on the underlying low-rank matrix and 2) elements being observed are appropriately dependent on their importance via the leverage score. Under these assumptions, instead of uniform sampling, we devise an ununiform/biased sampling procedure that can reveal the "importance" of each observed element. Our proofs are supported by a novel approach that phrases sufficient optimality conditions based on the Golfing scheme, which would be of independent interest to the wider areas. Theoretical findings show that we can provably recover an unknown n×n matrix of rank r from just about O(nrlog2 (n)) entries, even when the observed entries are corrupted with a small amount of noisy information. The empirical results align precisely with our theories.