Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) in computer vision has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the extremely simple ViTs' fine-tuning performance with a small-scale architecture can also benefit from this pre-training paradigm, which is considerably less studied yet in contrast to the well-established lightweight architecture design methodology with sophisticated components introduced. By carefully adapting various typical MIM pre-training methods to this lightweight regime and comparing them with the contrastive learning (CL) pre-training on various downstream image classification and dense prediction tasks, we systematically observe different behaviors between MIM and CL with respect to the downstream fine-tuning data scales. Furthermore, we analyze the frozen features under linear probing evaluation and also the layer representation similarities and attention maps across the obtained models, which clearly show the inferior learning of MIM pre-training on higher layers, leading to unsatisfactory fine-tuning performance on data-insufficient downstream tasks. This finding is naturally a guide to choosing appropriate distillation strategies during pre-training to solve the above deterioration problem. Extensive experiments on various vision tasks demonstrate the effectiveness of our observation-analysis-solution flow. In particular, our pre-training with distillation on pure lightweight ViTs with vanilla/hierarchical design (5.7M/6.5M) can achieve 79.4%/78.9% top-1 accuracy on ImageNet-1K. It also enables SOTA performance on the ADE20K semantic segmentation task (42.8% mIoU) and LaSOT visual tracking task (66.1% AUC) in the lightweight regime. The latter even surpasses all the current SOTA lightweight CPU-realtime trackers.
Recently, the transformer has enabled the speed-oriented trackers to approach state-of-the-art (SOTA) performance with high-speed thanks to the smaller input size or the lighter feature extraction backbone, though they still substantially lag behind their corresponding performance-oriented versions. In this paper, we demonstrate that it is possible to narrow or even close this gap while achieving high tracking speed based on the smaller input size. To this end, we non-uniformly resize the cropped image to have a smaller input size while the resolution of the area where the target is more likely to appear is higher and vice versa. This enables us to solve the dilemma of attending to a larger visual field while retaining more raw information for the target despite a smaller input size. Our formulation for the non-uniform resizing can be efficiently solved through quadratic programming (QP) and naturally integrated into most of the crop-based local trackers. Comprehensive experiments on five challenging datasets based on two kinds of transformer trackers, \ie, OSTrack and TransT, demonstrate consistent improvements over them. In particular, applying our method to the speed-oriented version of OSTrack even outperforms its performance-oriented counterpart by 0.6% AUC on TNL2K, while running 50% faster and saving over 55% MACs. Codes and models are available at https://github.com/Kou-99/ZoomTrack.
Proteins play a pivotal role in biological systems. The use of machine learning algorithms for protein classification can assist and even guide biological experiments, offering crucial insights for biotechnological applications. We propose a support bio-sequence machine for proteins, a model specifically designed for biological sequence classification. This model starts with raw sequences and groups amino acids based on their physicochemical properties. It incorporates sequence alignment to measure the similarities between proteins and uses a novel MKL approach to integrate various types of information, utilizing support vector machines for classification prediction. The results indicate that our model demonstrates commendable performance across 10 datasets in terms of the identification of protein function and posttranslational modification. This research not only showcases state-of-the-art work in protein classification but also paves the way for new directions in this domain, representing a beneficial endeavour in the development of platforms tailored for biological sequence classification. SBSM-Pro is available for access at http://lab.malab.cn/soft/SBSM-Pro/.
To combat global warming and mitigate the risks associated with climate change, carbon capture and storage (CCS) has emerged as a crucial technology. However, safely sequestering CO2 in geological formations for long-term storage presents several challenges. In this study, we address these issues by modeling the decision-making process for carbon storage operations as a partially observable Markov decision process (POMDP). We solve the POMDP using belief state planning to optimize injector and monitoring well locations, with the goal of maximizing stored CO2 while maintaining safety. Empirical results in simulation demonstrate that our approach is effective in ensuring safe long-term carbon storage operations. We showcase the flexibility of our approach by introducing three different monitoring strategies and examining their impact on decision quality. Additionally, we introduce a neural network surrogate model for the POMDP decision-making process to handle the complex dynamics of the multi-phase flow. We also investigate the effects of different fidelity levels of the surrogate model on decision qualities.
The principle of minimum potential and complementary energy are the most important variational principles in solid mechanics. The deep energy method (DEM), which has received much attention, is based on the principle of minimum potential energy, but it lacks the important form of minimum complementary energy. To fill the gap, we propose a deep complementary energy method (DCM) based on the principle of minimum complementary energy. The output function of DCM is the stress function that naturally satisfies the equilibrium equation. We extend the proposed DCM algorithm to DCM-Plus (DCM-P), adding the terms that naturally satisfy the biharmonic equation in the Airy stress function. We combine operator learning with physical equations and propose a deep complementary energy operator method (DCM-O), including branch net, trunk net, basis net, and particular net. DCM-O first combines existing high-fidelity numerical results to train DCM-O through data. Then the complementary energy is used to train the branch net and trunk net in DCM-O. To analyze DCM performance, we present the numerical result of the most common stress functions, the Prandtl and Airy stress function. The proposed method DCM is used to model the representative mechanical problems with different types of boundary conditions. We compare DCM with the existing PINNs and DEM algorithms. The result shows the advantage of the proposed DCM is suitable for dealing with problems of dominated displacement boundary conditions, which is proved by mathematical derivations, as well as with numerical experiments. DCM-P and DCM-O can improve the accuracy and efficiency of DCM. DCM is an essential supplementary energy form to the deep energy method. Operator learning based on the energy method can balance data and physical equations well, giving computational mechanics broad research prospects.
The principle of minimum potential and complementary energy are the most important variational principles in solid mechanics. The deep energy method (DEM), which has received much attention, is based on the principle of minimum potential energy and lacks the important form of minimum complementary energy. Thus, we propose the deep energy method based on the principle of minimum complementary energy (DCM). The output function of DCM is the stress function that naturally satisfies the equilibrium equation. We extend the proposed DCM algorithm (DCM-P), adding the terms that naturally satisfy the biharmonic equation in the Airy stress function. We combine operator learning with physical equations and propose a deep complementary energy operator method (DCM-O), including branch net, trunk net, basis net, and particular net. DCM-O first combines existing high-fidelity numerical results to train DCM-O through data. Then the complementary energy is used to train the branch net and trunk net in DCM-O. To analyze DCM performance, we present the numerical result of the most common stress functions, the Prandtl and Airy stress function. The proposed method DCM is used to model the representative mechanical problems with the different types of boundary conditions. We compare DCM with the existing PINNs and DEM algorithms. The result shows the advantage of the proposed DCM is suitable for dealing with problems of dominated displacement boundary conditions, which is reflected in theory and our numerical experiments. DCM-P and DCM-O improve the accuracy of DCM and the speed of calculation convergence. DCM is an essential supplementary energy form of the deep energy method. We believe that operator learning based on the energy method can balance data and physical equations well, giving computational mechanics broad research prospects.
We proposed the boundary-integral type neural networks (BINN) for the boundary value problems in computational mechanics. The boundary integral equations are employed to transfer all the unknowns to the boundary, then the unknowns are approximated using neural networks and solved through a training process. The loss function is chosen as the residuals of the boundary integral equations. Regularization techniques are adopted to efficiently evaluate the weakly singular and Cauchy principle integrals in boundary integral equations. Potential problems and elastostatic problems are mainly concerned in this article as a demonstration. The proposed method has several outstanding advantages: First, the dimensions of the original problem are reduced by one, thus the freedoms are greatly reduced. Second, the proposed method does not require any extra treatment to introduce the boundary conditions, since they are naturally considered through the boundary integral equations. Therefore, the method is suitable for complex geometries. Third, BINN is suitable for problems on the infinite or semi-infinite domains. Moreover, BINN can easily handle heterogeneous problems with a single neural network without domain decomposition.
Millions of stray animals suffer on the streets or are euthanized in shelters every day around the world. In order to better adopt stray animals, scoring the pawpularity (cuteness) of stray animals is very important, but evaluating the pawpularity of animals is a very labor-intensive thing. Consequently, there has been an urgent surge of interest to develop an algorithm that scores pawpularity of animals. However, the dataset in Kaggle not only has images, but also metadata describing images. Most methods basically focus on the most advanced image regression methods in recent years, but there is no good method to deal with the metadata of images. To address the above challenges, the paper proposes an image regression model called PETS-SWINF that considers metadata of the images. Our results based on a dataset of Kaggle competition, "PetFinder.my", show that PETS-SWINF has an advantage over only based images models. Our results shows that the RMSE loss of the proposed model on the test dataset is 17.71876 but 17.76449 without metadata. The advantage of the proposed method is that PETS-SWINF can consider both low-order and high-order features of metadata, and adaptively adjust the weights of the image model and the metadata model. The performance is promising as our leadboard score is ranked 15 out of 3545 teams (Gold medal) currently for 2021 Kaggle competition on the challenge "PetFinder.my".
We propose a conservative energy method based on a neural network with subdomains (CENN), where the admissible function satisfying the essential boundary condition without boundary penalty is constructed by the radial basis function, particular solution neural network, and general neural network. The loss term at the interfaces has the lower order derivative compared to the strong form PINN with subdomains. We apply the proposed method to some representative examples to demonstrate the ability of the proposed method to model strong discontinuity, singularity, complex boundary, non-linear, and heterogeneous PDE problems. The advantage of the method is the efficiency and accuracy compared to the strong form PINN. It is worth emphasizing that the method has a natural advantage in dealing with heterogeneous problems.