Search

In many real-world problems and applications, finding only a single element, even though the best, among all possible candidates, cannot fully meet the requirements. We may wish to have a collection where each individual is not only outstanding but also distinctive. Diversified Top-k (DTk) problems are a kind of combinatorial optimization problem for finding such a promising collection of multiple sub-structures, such as subgraphs like cliques and social communities. In this paper, we address two representative and practical DTk problems, DTk Clique search (DTkC) and DTk Weight Clique search (DTkWC), and propose an efficient algorithm called Diversified Top-k Evolutionary AlgorithM (DiverTEAM) for these two problems. DiverTEAM consists of a local search algorithm, which focuses on generating high-quality and diverse individuals and sub-structures, and a genetic algorithm that makes individuals work as a team and converge to (near-)optima efficiently. Extensive experiments show that DiverTEAM exhibits an excellent and robust performance across various benchmarks of DTkC and DTkWC., Comment: 8 pages, 3 figures, 4 tables

Image and video inpainting is a classic problem in computer vision and computer graphics, aiming to fill in the plausible and realistic content in the missing areas of images and videos. With the advance of deep learning, this problem has achieved significant progress recently. The goal of this paper is to comprehensively review the deep learning-based methods for image and video inpainting. Specifically, we sort existing methods into different categories from the perspective of their high-level inpainting pipeline, present different deep learning architectures, including CNN, VAE, GAN, diffusion models, etc., and summarize techniques for module design. We review the training objectives and the common benchmark datasets. We present evaluation metrics for low-level pixel and high-level perceptional similarity, conduct a performance evaluation, and discuss the strengths and weaknesses of representative inpainting methods. We also discuss related real-world applications. Finally, we discuss open challenges and suggest potential future research directions., Comment: accepted to IJCV

Recent approaches such as ControlNet offer users fine-grained spatial control over text-to-image (T2I) diffusion models. However, auxiliary modules have to be trained for each type of spatial condition, model architecture, and checkpoint, putting them at odds with the diverse intents and preferences a human designer would like to convey to the AI models during the content creation process. In this work, we present FreeControl, a training-free approach for controllable T2I generation that supports multiple conditions, architectures, and checkpoints simultaneously. FreeControl designs structure guidance to facilitate the structure alignment with a guidance image, and appearance guidance to enable the appearance sharing between images generated using the same seed. Extensive qualitative and quantitative experiments demonstrate the superior performance of FreeControl across a variety of pre-trained T2I models. In particular, FreeControl facilitates convenient training-free control over many different architectures and checkpoints, allows the challenging input conditions on which most of the existing training-free methods fail, and achieves competitive synthesis quality with training-based approaches., Comment: Project Page: https://genforce.github.io/freecontrol/

Convolutional neural networks (CNNs) and vision transformers (ViTs) have achieved remarkable success in various vision tasks. However, many architectures do not consider interactions between feature maps from different stages and scales, which may limit their performance. In this work, we propose a simple add-on attention module to overcome these limitations via multi-stage and cross-scale interactions. Specifically, the proposed Multi-Stage Cross-Scale Attention (MSCSA) module takes feature maps from different stages to enable multi-stage interactions and achieves cross-scale interactions by computing self-attention at different scales based on the multi-stage feature maps. Our experiments on several downstream tasks show that MSCSA provides a significant performance boost with modest additional FLOPs and runtime.

Deep models have demonstrated recent success in single-image dehazing. Most prior methods consider fully supervised training and learn from paired clean and hazy images, where a hazy image is synthesized based on a clean image and its estimated depth map. This paradigm, however, can produce low-quality hazy images due to inaccurate depth estimation, resulting in poor generalization of the trained models. In this paper, we explore an alternative approach for generating paired clean-hazy images by leveraging computer graphics. Using a modern game engine, our approach renders crisp clean images and their precise depth maps, based on which high-quality hazy images can be synthesized for training dehazing models. To this end, we present SimHaze: a new synthetic haze dataset. More importantly, we show that training with SimHaze alone allows the latest dehazing models to achieve significantly better performance in comparison to previous dehazing datasets. Our dataset and code will be made publicly available., Comment: Submitted to ICIP 2023

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.

Given an arbitrary choice of two sets of nonzero Boltzmann weights for $n$-color lattice models, we provide explicit algebraic conditions on these Boltzmann weights which guarantee a solution (i.e., a third set of weights) to the Yang-Baxter equation. Furthermore we provide an explicit one-dimensional parametrization of all solutions in this case. These $n$-color lattice models are so named because their admissible vertices have adjacent edges labeled by one of $n$ colors with additional restrictions. The two-colored case specializes to the six-vertex model, in which case our results recover the familiar quadric condition of Baxter for solvability. The general $n$-color case includes important solutions to the Yang-Baxter equation like the evaluation modules for the quantum affine Lie algebra $U_q(\hat{\mathfrak{sl}}_n)$. Finally, we demonstrate the invariance of this class of solutions under natural transformations, including those associated with Drinfeld twisting., Comment: 39 pages, 8 figures

In this paper, we revisit and improve the convergence of policy gradient (PG), natural PG (NPG) methods, and their variance-reduced variants, under general smooth policy parametrizations. More specifically, with the Fisher information matrix of the policy being positive definite: i) we show that a state-of-the-art variance-reduced PG method, which has only been shown to converge to stationary points, converges to the globally optimal value up to some inherent function approximation error due to policy parametrization; ii) we show that NPG enjoys a lower sample complexity; iii) we propose SRVR-NPG, which incorporates variance-reduction into the NPG update. Our improvements follow from an observation that the convergence of (variance-reduced) PG and NPG methods can improve each other: the stationary convergence analysis of PG can be applied to NPG as well, and the global convergence analysis of NPG can help to establish the global convergence of (variance-reduced) PG methods. Our analysis carefully integrates the advantages of these two lines of works. Thanks to this improvement, we have also made variance-reduction for NPG possible, with both global convergence and an efficient finite-sample complexity., Comment: NeurIPS 2020 (improve the proof of Lemma B.1 and Proposition G.1.)

Maximum Common induced Subgraph (MCS) is an important NP-hard problem with wide real-world applications. Branch-and-Bound (BnB) is the basis of a class of efficient algorithms for MCS, consisting in successively selecting vertices to match and pruning when it is discovered that a solution better than the best solution found so far does not exist. The method of selecting the vertices to match is essential for the performance of BnB. In this paper, we propose a new value function and a hybrid selection strategy used in reinforcement learning to define a new vertex selection method, and propose a new BnB algorithm, called McSplitDAL, for MCS. Extensive experiments show that McSplitDAL significantly improves the current best BnB algorithms, McSplit+LL and McSplit+RL. An empirical analysis is also performed to illustrate why the new value function and the hybrid selection strategy are effective.

We propose a new and strengthened Branch-and-Bound (BnB) algorithm for the maximum common (connected) induced subgraph problem based on two new operators, Long-Short Memory (LSM) and Leaf vertex Union Match (LUM). Given two graphs for which we search for the maximum common (connected) induced subgraph, the first operator of LSM maintains a score for the branching node using the short-term reward of each vertex of the first graph and the long-term reward of each vertex pair of the two graphs. In this way, the BnB process learns to reduce the search tree size significantly and improve the algorithm performance. The second operator of LUM further improves the performance by simultaneously matching the leaf vertices connected to the current matched vertices, and allows the algorithm to match multiple vertex pairs without affecting the solution optimality. We incorporate the two operators into the state-of-the-art BnB algorithm McSplit, and denote the resulting algorithm as McSplit+LL. Experiments show that McSplit+LL outperforms McSplit+RL, a more recent variant of McSplit using reinforcement learning that is superior than McSplit.