Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to a different unlabeled target domain. Most existing UDA methods focus on learning domain-invariant feature representation, either from the domain l
evel or category level, using convolution neural networks (CNNs)-based frameworks. One fundamental problem for the category level based UDA is the production of pseudo labels for samples in target domain, which are usually too noisy for accurate domain alignment, inevitably compromising the UDA performance. With the success of Transformer in various tasks, we find that the cross-attention in Transformer is robust to the noisy input pairs for better feature alignment, thus in this paper Transformer is adopted for the challenging UDA task. Specifically, to generate accurate input pairs, we design a two-way center-aware labeling algorithm to produce pseudo labels for target samples. Along with the pseudo labels, a weight-sharing triple-branch transformer framework is proposed to apply self-attention and cross-attention for source/target feature learning and source-target domain alignment, respectively. Such design explicitly enforces the framework to learn discriminative domain-specific and domain-invariant representations simultaneously. The proposed method is dubbed CDTrans (cross-domain transformer), and it provides one of the first attempts to solve UDA tasks with a pure transformer solution. Extensive experiments show that our proposed method achieves the best performance on Office-Home, VisDA-2017, and DomainNet datasets.
We study the construction of the Gibbs measures for the {it focusing} mass-critical fractional nonlinear Schrodinger equation on the multi-dimensional torus. We identify the sharp mass threshold for normalizability and non-normalizability of the focu
sing Gibbs measures, which generalizes the influential works of Lebowitz-Rose-Speer (1988), Bourgain (1994), and Oh-Sosoe-Tolomeo (2021) on the one-dimensional nonlinear Schrodinger equations. To this purpose, we establish an almost sharp fractional Gagliardo-Nirenberg-Sobolev inequality on the torus, which is of independent interest.
Gaze is an intuitive and direct way to represent the intentions of an individual. However, when it comes to assistive aerial teleoperation which aims to perform operators intention, rare attention has been paid to gaze. Existing methods obtain intent
ion directly from the remote controller (RC) input, which is inaccurate, unstable, and unfriendly to non-professional operators. Further, most teleoperation works do not consider environment perception which is vital to guarantee safety. In this paper, we present GPA-Teleoperation, a gaze enhanced perception-aware assistive teleoperation framework, which addresses the above issues systematically. We capture the intention utilizing gaze information, and generate a topological path matching it. Then we refine the path into a safe and feasible trajectory which simultaneously enhances the perception awareness to the environment operators are interested in. Additionally, the proposed method is integrated into a customized quadrotor system. Extensive challenging indoor and outdoor real-world experiments and benchmark comparisons verify that the proposed system is reliable, robust and applicable to even unskilled users. We will release the source code of our system to benefit related researches.
We study the problem of generating arithmetic math word problems (MWPs) given a math equation that specifies the mathematical computation and a context that specifies the problem scenario. Existing approaches are prone to generating MWPs that are eit
her mathematically invalid or have unsatisfactory language quality. They also either ignore the context or require manual specification of a problem template, which compromises the diversity of the generated MWPs. In this paper, we develop a novel MWP generation approach that leverages i) pre-trained language models and a context keyword selection model to improve the language quality of the generated MWPs and ii) an equation consistency constraint for math equations to improve the mathematical validity of the generated MWPs. Extensive quantitative and qualitative experiments on three real-world MWP datasets demonstrate the superior performance of our approach compared to various baselines.
Vision transformers (ViTs) have been an alternative design paradigm to convolutional neural networks (CNNs). However, the training of ViTs is much harder than CNNs, as it is sensitive to the training parameters, such as learning rate, optimizer and w
armup epoch. The reasons for training difficulty are empirically analysed in ~cite{xiao2021early}, and the authors conjecture that the issue lies with the textit{patchify-stem} of ViT models and propose that early convolutions help transformers see better. In this paper, we further investigate this problem and extend the above conclusion: only early convolutions do not help for stable training, but the scaled ReLU operation in the textit{convolutional stem} (textit{conv-stem}) matters. We verify, both theoretically and empirically, that scaled ReLU in textit{conv-stem} not only improves training stabilization, but also increases the diversity of patch tokens, thus boosting peak performance with a large margin via adding few parameters and flops. In addition, extensive experiments are conducted to demonstrate that previous ViTs are far from being well trained, further showing that ViTs have great potential to be a better substitute of CNNs.
The paradox of the plankton highlights the apparent contradiction between Gauses law of competitive exclusion and the observed diversity of phytoplankton. It is well known that phytoplankton dynamics depend heavily on two main resources: light and nu
trients. Here we treat light as a continuum of resources rather than a single resource by considering the visible light spectrum. We propose a spatially explicit reaction-diffusion-advection model to explore under what circumstance coexistence is possible from mathematical and biological perspectives. Furthermore, we provide biological context as to when coexistence is expected based on the degree of niche differentiation within the light spectrum and overall turbidity of the water.
Completely randomized experiments have been the gold standard for drawing causal inference because they can balance all potential confounding on average. However, they can often suffer from unbalanced covariates for realized treatment assignments. Re
randomization, a design that rerandomizes the treatment assignment until a prespecified covariate balance criterion is met, has recently got attention due to its easy implementation, improved covariate balance and more efficient inference. Researchers have then suggested to use the assignments that minimize the covariate imbalance, namely the optimally balanced design. This has caused again the long-time controversy between two philosophies for designing experiments: randomization versus optimal and thus almost deterministic designs. Existing literature argued that rerandomization with overly balanced observed covariates can lead to highly imbalanced unobserved covariates, making it vulnerable to model misspecification. On the contrary, rerandomization with properly balanced covariates can provide robust inference for treatment effects while sacrificing some efficiency compared to the ideally optimal design. In this paper, we show it is possible that, by making the covariate imbalance diminishing at a proper rate as the sample size increases, rerandomization can achieve its ideally optimal precision that one can expect with perfectly balanced covariates while still maintaining its robustness. In particular, we provide the sufficient and necessary condition on the number of covariates for achieving the desired optimality. Our results rely on a more dedicated asymptotic analysis for rerandomization. The derived theory for rerandomization provides a deeper understanding of its large-sample property and can better guide its practical implementation. Furthermore, it also helps reconcile the controversy between randomized and optimal designs.
Many context-sensitive data flow analyses can be formulated as a variant of the all-pairs Dyck-CFL reachability problem, which, in general, is of sub-cubic time complexity and quadratic space complexity. Such high complexity significantly limits the
scalability of context-sensitive data flow analysis and is not affordable for analyzing large-scale software. This paper presents textsc{Flare}, a reduction from the CFL reachability problem to the conventional graph reachability problem for context-sensitive data flow analysis. This reduction allows us to benefit from recent advances in reachability indexing schemes, which often consume almost linear space for answering reachability queries in almost constant time. We have applied our reduction to a context-sensitive alias analysis and a context-sensitive information-flow analysis for C/C++ programs. Experimental results on standard benchmarks and open-source software demonstrate that we can achieve orders of magnitude speedup at the cost of only moderate space to store the indexes. The implementation of our approach is publicly available.
Colour changes can be achieved by straining photonic crystals or gratings embedded in stretchable materials. However, the multiple repeat units and the need for a volumetric assembly of nanostructures limit the density of information content. Inspire
d by surface reliefs on oracle bones and music records as means of information archival, here we endow surface-relief elastomers with multiple sets of information that are accessible by mechanical straining along in-plane axes. Distinct from Bragg diffraction effects from periodic structures, we report trenches that generate colour due to variations in trench depth, enabling individual trench segments to support a single colour. Using 3D printed cuboids, we replicated trenches of varying geometric parameters in elastomers. These parameters determine the initial colour (or lack thereof), the response to capillary forces, and the appearance when strained along or across the trenches. Strain induces modulation in trench depth or the opening and closure of a trench, resulting in surface reliefs with up to six distinct states, and an initially featureless surface that reveals two distinct images when stretched along different axes. The highly reversible structural colours are promising in optical data archival, anti-counterfeiting, and strain-sensing applications.
As an effective way to integrate the information contained in multiple medical images under different modalities, medical image synthesis and fusion have emerged in various clinical applications such as disease diagnosis and treatment planning. In th
is paper, an invertible and variable augmented network (iVAN) is proposed for medical image synthesis and fusion. In iVAN, the channel number of the network input and output is the same through variable augmentation technology, and data relevance is enhanced, which is conducive to the generation of characterization information. Meanwhile, the invertible network is used to achieve the bidirectional inference processes. Due to the invertible and variable augmentation schemes, iVAN can not only be applied to the mappings of multi-input to one-output and multi-input to multi-output, but also be applied to one-input to multi-output. Experimental results demonstrated that the proposed method can obtain competitive or superior performance in comparison to representative medical image synthesis and fusion methods.
