arXiv subjects

Kun He

Publications and source records attributed to Kun He.

At least 109 records · Page 6Linked to original sources

arXiv2023

An Efficient Solution Space Exploring and Descent Method for Packing Equal Spheres in a Sphere

The problem of packing equal spheres in a spherical container is a classic global optimization problem, which has attracted enormous studies in academia and found various applications in industry. This problem is computationally challenging, and many efforts focus on small-scale instances with the number of spherical items less than 200 in the literature. In this work, we propose an efficient local search heuristic algorithm named solution space exploring and descent for solving this problem, which can quantify the solution's quality to determine the number of exploring actions and quickly discover a high-quality solution. Besides, we propose an adaptive neighbor object maintenance method to speed up the convergence of the continuous optimization process and reduce the time consumption. Computational experiments on a large number of benchmark instances with $5 \leq n \leq 400$ spherical items show that our algorithm significantly outperforms the state-of-the-art algorithm. In particular, it improves the 274 best-known results and matches the 84 best-known results out of the 396 well-known benchmark instances.

cs.CG↗

arXiv2023

AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation

We present AssemblyHands, a large-scale benchmark dataset with accurate 3D hand pose annotations, to facilitate the study of egocentric activities with challenging hand-object interactions. The dataset includes synchronized egocentric and exocentric images sampled from the recent Assembly101 dataset, in which participants assemble and disassemble take-apart toys. To obtain high-quality 3D hand pose annotations for the egocentric images, we develop an efficient pipeline, where we use an initial set of manual annotations to train a model to automatically annotate a much larger dataset. Our annotation model uses multi-view feature fusion and an iterative refinement scheme, and achieves an average keypoint error of 4.20 mm, which is 85% lower than the error of the original annotations in Assembly101. AssemblyHands provides 3.0M annotated images, including 490K egocentric images, making it the largest existing benchmark dataset for egocentric 3D hand pose estimation. Using this data, we develop a strong single-view baseline of 3D hand pose estimation from egocentric images. Furthermore, we design a novel action classification task to evaluate predicted 3D hand poses. Our study shows that having higher-quality hand poses directly improves the ability to recognize actions.

cs.CV↗

arXiv2023

GMConv: Modulating Effective Receptive Fields for Convolutional Kernels

In convolutional neural networks, the convolutions are conventionally performed using a square kernel with a fixed N $\times$ N receptive field (RF). However, what matters most to the network is the effective receptive field (ERF) that indicates the extent with which input pixels contribute to an output pixel. Inspired by the property that ERFs typically exhibit a Gaussian distribution, we propose a Gaussian Mask convolutional kernel (GMConv) in this work. Specifically, GMConv utilizes the Gaussian function to generate a concentric symmetry mask that is placed over the kernel to refine the RF. Our GMConv can directly replace the standard convolutions in existing CNNs and can be easily trained end-to-end by standard back-propagation. We evaluate our approach through extensive experiments on image classification and object detection tasks. Over several tasks and standard base models, our approach compares favorably against the standard convolution. For instance, using GMConv for AlexNet and ResNet-50, the top-1 accuracy on ImageNet classification is boosted by 0.98% and 0.85%, respectively.

cs.CV↗

arXiv2023

Pointerformer: Deep Reinforced Multi-Pointer Transformer for the Traveling Salesman Problem

Traveling Salesman Problem (TSP), as a classic routing optimization problem originally arising in the domain of transportation and logistics, has become a critical task in broader domains, such as manufacturing and biology. Recently, Deep Reinforcement Learning (DRL) has been increasingly employed to solve TSP due to its high inference efficiency. Nevertheless, most of existing end-to-end DRL algorithms only perform well on small TSP instances and can hardly generalize to large scale because of the drastically soaring memory consumption and computation time along with the enlarging problem scale. In this paper, we propose a novel end-to-end DRL approach, referred to as Pointerformer, based on multi-pointer Transformer. Particularly, Pointerformer adopts both reversible residual network in the encoder and multi-pointer network in the decoder to effectively contain memory consumption of the encoder-decoder architecture. To further improve the performance of TSP solutions, Pointerformer employs both a feature augmentation method to explore the symmetries of TSP at both training and inference stages as well as an enhanced context embedding approach to include more comprehensive context information in the query. Extensive experiments on a randomly generated benchmark and a public benchmark have shown that, while achieving comparative results on most small-scale TSP instances as SOTA DRL approaches do, Pointerformer can also well generalize to large-scale TSPs.

cs.AI↗

arXiv2023

Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers

Multi-Object Tracking (MOT) has achieved aggressive progress and derived many excellent deep learning trackers. Meanwhile, most deep learning models are known to be vulnerable to adversarial examples that are crafted with small perturbations but could mislead the model prediction. In this work, we observe that the robustness on the MOT trackers is rarely studied, and it is challenging to attack the MOT system since its mature association algorithms are designed to be robust against errors during the tracking. To this end, we analyze the vulnerability of popular MOT trackers and propose a novel adversarial attack method called Tracklet-Switch (TraSw) against the complete tracking pipeline of MOT. The proposed TraSw can fool the advanced deep pedestrian trackers (i.e., FairMOT and ByteTrack), causing them fail to track the targets in the subsequent frames by perturbing very few frames. Experiments on the MOT-Challenge datasets (i.e., 2DMOT15, MOT17, and MOT20) show that TraSw can achieve an extraordinarily high success attack rate of over 95% by attacking only four frames on average. To our knowledge, this is the first work on the adversarial attack against the pedestrian MOT trackers. Code is available at https://github.com/JHL-HUST/TraSw .

cs.CV↗

arXiv2023

PIAT: Parameter Interpolation based Adversarial Training for Image Classification

Adversarial training has been demonstrated to be the most effective approach to defend against adversarial attacks. However, existing adversarial training methods show apparent oscillations and overfitting issue in the training process, degrading the defense efficacy. In this work, we propose a novel framework, termed Parameter Interpolation based Adversarial Training (PIAT), that makes full use of the historical information during training. Specifically, at the end of each epoch, PIAT tunes the model parameters as the interpolation of the parameters of the previous and current epochs. Besides, we suggest to use the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the clean and adversarial examples. Compared with other regularization methods, NMSE focuses more on the relative magnitude of the logits rather than the absolute magnitude. Extensive experiments on several benchmark datasets and various networks show that our method could prominently improve the model robustness and reduce the generalization error. Moreover, our framework is general and could further boost the robust accuracy when combined with other adversarial training methods.

cs.CV↗

arXiv2023

Sampling Lovász Local Lemma For General Constraint Satisfaction Solutions In Near-Linear Time

We give a fast algorithm for sampling uniform solutions of general constraint satisfaction problems (CSPs) in a local lemma regime. Suppose that the CSP has $n$ variables with domain size at most q, each constraint contains at most k variables, shares variables with at most $Δ$ constraints, and is violated with probability at most $p$ by a uniform random assignment. The algorithm returns an almost uniform satisfying assignment in expected $\mathrm{poly}(q,k,Δ)\cdot\tilde{O}(n)$ time, as long as a local lemma condition is satisfied: \[ k\cdot p\cdot q^2\cdot Δ^5\le C_0\quad\text{for a suitably small absolute constant }C_0. \] Previously, under similar local lemma conditions, sampling algorithms with running time polynomial in both $n$ and $Δ$ were only known for the almost atomic case, where each constraint is violated by a small number of forbidden local configurations. The key term $Δ^5$ in our local lemma condition also improves the previously best known $Δ^7$ for general CSPs [JPV21b] and $Δ^{5.714}$ for atomic CSPs, including the special case of $k$-CNF [JPV21a, HSW21]. Our sampling approach departs from previous fast algorithms for sampling LLL, which were based on Markov chains. A crucial step of our algorithm is a recursive marginal sampler that is of independent interests. Within a local lemma regime, this marginal sampler can draw a random value for a variable according to its marginal distribution, at a cost independent of the size of the CSP.

cs.DS↗

arXiv2023

Geometric Batch Optimization for the Packing Equal Circles in a Circle Problem on Large Scale

The problem of packing equal circles in a circle is a classic and famous packing problem, which is well-studied in academia and has a variety of applications in industry. This problem is computationally challenging, and researchers mainly focus on small-scale instances with the number of circular items n less than 320 in the literature. In this work, we aim to solve this problem on large scale. Specifically, we propose a novel geometric batch optimization method that not only can significantly speed up the convergence process of continuous optimization but also reduce the memory requirement during the program's runtime. Then we propose a heuristic search method, called solution-space exploring and descent, that can discover a feasible solution efficiently on large scale. Besides, we propose an adaptive neighbor object maintenance method to maintain the neighbor structure applied in the continuous optimization process. In this way, we can find high-quality solutions on large scale instances within reasonable computational times. Extensive experiments on the benchmark instances sampled from n = 300 to 1,000 show that our proposed algorithm outperforms the state-of-the-art algorithms and performs excellently on large scale instances. In particular, our algorithm found 10 improved solutions out of the 21 well-studied moderate scale instances and 95 improved solutions out of the 101 sampled large scale instances. Furthermore, our geometric batch optimization, heuristic search, and adaptive maintenance methods are general and can be adapted to other packing and continuous optimization problems.

cs.CG↗

arXiv2023

NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs

The graph Transformer emerges as a new architecture and has shown superior performance on various graph mining tasks. In this work, we observe that existing graph Transformers treat nodes as independent tokens and construct a single long sequence composed of all node tokens so as to train the Transformer model, causing it hard to scale to large graphs due to the quadratic complexity on the number of nodes for the self-attention computation. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGphormer) that treats each node as a sequence containing a series of tokens constructed by our proposed Hop2Token module. For each node, Hop2Token aggregates the neighborhood features from different hops into different representations and thereby produces a sequence of token vectors as one input. In this way, NAGphormer could be trained in a mini-batch manner and thus could scale to large graphs. Moreover, we mathematically show that as compared to a category of advanced Graph Neural Networks (GNNs), the decoupled Graph Convolutional Network, NAGphormer could learn more informative node representations from the multi-hop neighborhoods. Extensive experiments on benchmark datasets from small to large are conducted to demonstrate that NAGphormer consistently outperforms existing graph Transformers and mainstream GNNs. Code is available at https://github.com/JHL-HUST/NAGphormer.

cs.LG↗

arXiv2023

All in Tokens: Unifying Output Space of Visual Tasks via Soft Token

Unlike language tasks, where the output space is usually limited to a set of tokens, the output space of visual tasks is more complicated, making it difficult to build a unified visual model for various visual tasks. In this paper, we seek to unify the output space of visual tasks, so that we can also build a unified model for visual tasks. To this end, we demonstrate a single unified model that simultaneously handles two typical visual tasks of instance segmentation and depth estimation, which have discrete/fixed-length and continuous/varied-length outputs, respectively. We propose several new techniques that take into account the particularity of visual tasks: 1) Soft token. We employ soft token to represent the task output. Unlike hard tokens in the common VQ-VAE which are assigned one-hot to discrete codebooks/vocabularies, the soft token is assigned softly to the codebook embeddings. Soft token can improve the accuracy of both the next token inference and decoding of the task output; 2) Mask augmentation. Many visual tasks have corruption, undefined or invalid values in label annotations, i.e., occluded area of depth maps. We show that a mask augmentation technique can greatly benefit these tasks. With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well. Particularly, we achieve 0.279 RMSE on the specific task of NYUv2 depth estimation, setting a new record on this benchmark. The general-purpose task-solver, dubbed AiT, is available at \url{https://github.com/SwinTransformer/AiT}.

cs.CV↗

arXiv2023

Semantic Adversarial Attacks on Face Recognition through Significant Attributes

Face recognition is known to be vulnerable to adversarial face images. Existing works craft face adversarial images by indiscriminately changing a single attribute without being aware of the intrinsic attributes of the images. To this end, we propose a new Semantic Adversarial Attack called SAA-StarGAN that tampers with the significant facial attributes for each image. We predict the most significant attributes by applying the cosine similarity or probability score. The probability score method is based on training a Face Verification model for an attribute prediction task to obtain a class probability score for each attribute. The prediction process will help craft adversarial face images more easily and efficiently, as well as improve the adversarial transferability. Then, we change the most significant facial attributes, with either one or more of the facial attributes for impersonation and dodging attacks in white-box and black-box settings. Experimental results show that our method could generate diverse and realistic adversarial face images meanwhile avoid affecting human perception of the face recognition. SAA-StarGAN achieves an 80.5% attack success rate against black-box models, outperforming existing methods by 35.5% under the impersonation attack. Concerning the black-box setting, SAA-StarGAN achieves high attack success rates on various models. The experiments confirm that predicting the most important attributes significantly affects the success of adversarial attacks in both white-box and black-box settings and could enhance the transferability of the crafted adversarial examples.

cs.CV↗

arXiv2023

Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Training

Pose estimation of the human body and hands is a fundamental problem in computer vision, and learning-based solutions require a large amount of annotated data. In this work, we improve the efficiency of the data annotation process for 3D pose estimation problems with Active Learning (AL) in a multi-view setting. AL selects examples with the highest value to annotate under limited annotation budgets (time and cost), but choosing the selection strategy is often nontrivial. We present a framework to efficiently extend existing single-view AL strategies. We then propose two novel AL strategies that make full use of multi-view geometry. Moreover, we demonstrate additional performance gains by incorporating pseudo-labels computed during the AL process, which is a form of self-training. Our system significantly outperforms simulated annotation baselines in 3D body and hand pose estimation on two large-scale benchmarks: CMU Panoptic Studio and InterHand2.6M. Notably, on CMU Panoptic Studio, we are able to reduce the turn-around time by 60% and annotation cost by 80% when compared to the conventional annotation process.

cs.CV↗

arXiv2022

Deterministic counting Lovász local lemma beyond linear programming

We give a simple combinatorial algorithm to deterministically approximately count the number of satisfying assignments of general constraint satisfaction problems (CSPs). Suppose that the CSP has domain size $q=O(1)$, each constraint contains at most $k=O(1)$ variables, shares variables with at most $Δ=O(1)$ constraints, and is violated with probability at most $p$ by a uniform random assignment. The algorithm returns in polynomial time in an improved local lemma regime: \[ q^2\cdot k\cdot p\cdotΔ^5\le C_0\quad\text{for a suitably small absolute constant }C_0. \] Here the key term $Δ^5$ improves the previously best known $Δ^7$ for general CSPs [JPV21b] and $Δ^{5.714}$ for the special case of $k$-CNF [JPV21a, HSW21]. Our deterministic counting algorithm is a derandomization of the very recent fast sampling algorithm in [HWY22]. It departs substantially from all previous deterministic counting Lovász local lemma algorithms which relied on linear programming, and gives a deterministic approximate counting algorithm that straightforwardly derandomizes a fast sampling algorithm, hence unifying the fast sampling and deterministic approximate counting in the same algorithmic framework. To obtain the improved regime, in our analysis we develop a refinement of the $\{2,3\}$-trees that were used in the previous analyses of counting/sampling LLL. Similar techniques can be applied to the previous LP-based algorithms to obtain the same improved regime and may be of independent interests.

cs.DS↗

arXiv2022

Incorporating Multi-armed Bandit with Local Search for MaxSAT

Partial MaxSAT (PMS) and Weighted PMS (WPMS) are two practical generalizations of the MaxSAT problem. In this paper, we propose a local search algorithm for these problems, called BandHS, which applies two multi-armed bandits to guide the search directions when escaping local optima. One bandit is combined with all the soft clauses to help the algorithm select to satisfy appropriate soft clauses, and the other bandit with all the literals in hard clauses to help the algorithm select appropriate literals to satisfy the hard clauses. These two bandits can improve the algorithm's search ability in both feasible and infeasible solution spaces. We further propose an initialization method for (W)PMS that prioritizes both unit and binary clauses when producing the initial solutions. Extensive experiments demonstrate the excellent performance and generalization capability of our proposed methods, that greatly boost the state-of-the-art local search algorithm, SATLike3.0, and the state-of-the-art SAT-based incomplete solver, NuWLS-c.

cs.AI↗

arXiv2022

Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks

Heterogeneous information networks (HINs) are widely employed for describing real-world data with intricate entities and relationships. To automatically utilize their semantic information, graph neural architecture search has recently been developed on various tasks of HINs. Existing works, on the other hand, show weaknesses in instability and inflexibility. To address these issues, we propose a novel method called Partial Message Meta Multigraph search (PMMM) to automatically optimize the neural architecture design on HINs. Specifically, to learn how graph neural networks (GNNs) propagate messages along various types of edges, PMMM adopts an efficient differentiable framework to search for a meaningful meta multigraph, which can capture more flexible and complex semantic relations than a meta graph. The differentiable search typically suffers from performance instability, so we further propose a stable algorithm called partial message search to ensure that the searched meta multigraph consistently surpasses the manually designed meta-structures, i.e., meta-paths. Extensive experiments on six benchmark datasets over two representative tasks, including node classification and recommendation, demonstrate the effectiveness of the proposed method. Our approach outperforms the state-of-the-art heterogeneous GNNs, finds out meaningful meta multigraphs, and is significantly more stable.

cs.LG↗

arXiv2022

Class-aware Information for Logit-based Knowledge Distillation

Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown its superiority over logit-based distillation. However, due to the cumbersome computation and storage of extra feature transformation, the training overhead of feature-based methods is much higher than that of logit-based distillation. In this work, we revisit the logit-based knowledge distillation, and observe that the existing logit-based distillation methods treat the prediction logits only in the instance level, while many other useful semantic information is overlooked. To address this issue, we propose a Class-aware Logit Knowledge Distillation (CLKD) method, that extents the logit distillation in both instance-level and class-level. CLKD enables the student model mimic higher semantic information from the teacher model, hence improving the distillation performance. We further introduce a novel loss called Class Correlation Loss to force the student learn the inherent class-level correlation of the teacher. Empirical comparisons demonstrate the superiority of the proposed method over several prevailing logit-based methods and feature-based methods, in which CLKD achieves compelling results on various visual classification tasks and outperforms the state-of-the-art baselines.

cs.CV↗

arXiv2022

On the Complexity of Bayesian Generalization

We consider concept generalization at a large scale in the diverse and natural visual spectrum. Established computational modes (i.e., rule-based or similarity-based) are primarily studied isolated and focus on confined and abstract problem spaces. In this work, we study these two modes when the problem space scales up, and the $complexity$ of concepts becomes diverse. Specifically, at the $representational \ level$, we seek to answer how the complexity varies when a visual concept is mapped to the representation space. Prior psychology literature has shown that two types of complexities (i.e., subjective complexity and visual complexity) (Griffiths and Tenenbaum, 2003) build an inverted-U relation (Donderi, 2006; Sun and Firestone, 2021). Leveraging Representativeness of Attribute (RoA), we computationally confirm the following observation: Models use attributes with high RoA to describe visual concepts, and the description length falls in an inverted-U relation with the increment in visual complexity. At the $computational \ level$, we aim to answer how the complexity of representation affects the shift between the rule- and similarity-based generalization. We hypothesize that category-conditioned visual modeling estimates the co-occurrence frequency between visual and categorical attributes, thus potentially serving as the prior for the natural visual world. Experimental results show that representations with relatively high subjective complexity outperform those with relatively low subjective complexity in the rule-based generalization, while the trend is the opposite in the similarity-based generalization.

cs.AI↗

arXiv2022

Farsighted Probabilistic Sampling: A General Strategy for Boosting Local Search MaxSAT Solvers

Local search has been demonstrated as an efficient approach for two practical generalizations of the MaxSAT problem, namely Partial MaxSAT (PMS) and Weighted PMS (WPMS). In this work, we observe that most local search (W)PMS solvers usually flip a single variable per iteration. Such a mechanism may lead to relatively low-quality local optimal solutions, and may limit the diversity of search directions to escape from local optima. To address this issue, we propose a general strategy, called farsighted probabilistic sampling (FPS), to replace the single flipping mechanism so as to boost the local search (W)PMS algorithms. FPS considers the benefit of continuously flipping a pair of variables in order to find higher-quality local optimal solutions. Moreover, FPS proposes an effective approach to escape from local optima by preferring the best to flip among the best sampled single variable and the best sampled variable pair. Extensive experiments demonstrate that our proposed FPS strategy significantly improves the state-of-the-art (W)PMS solvers, and FPS has an excellent generalization capability to various local search MaxSAT solvers.

cs.AI↗