Federated learning (FL) involves multiple distributed devices jointly training a shared model without any of the participants having to reveal their local data to a centralized server. Most of previous FL approaches assume that data on devices are fixed and stationary during the training process. However, this assumption is unrealistic because these devices usually have varying sampling rates and different system configurations. In addition, the underlying distribution of the device data can change dynamically over time, which is known as concept drift. Concept drift makes the learning process complicated because of the inconsistency between existing and upcoming data. Traditional concept drift handling techniques such as chunk based and ensemble learning-based methods are not suitable in the federated learning frameworks due to the heterogeneity of local devices. We propose a novel approach, FedConD, to detect and deal with the concept drift on local devices and minimize the effect on the performance of models in asynchronous FL. The drift detection strategy is based on an adaptive mechanism which uses the historical performance of the local models. The drift adaptation is realized by adjusting the regularization parameter of objective function on each local device. Additionally, we design a communication strategy on the server side to select local updates in a prudent fashion and speed up model convergence. Experimental evaluations on three evolving data streams and two image datasets show that \model~detects and handles concept drift, and also reduces the overall communication cost compared to other baseline methods.
Multi-modal pre-training models have been intensively explored to bridge vision and language in recent years. However, most of them explicitly model the cross-modal interaction between image-text pairs, by assuming that there exists strong semantic correlation between the text and image modalities. Since this strong assumption is often invalid in real-world scenarios, we choose to implicitly model the cross-modal correlation for large-scale multi-modal pre-training, which is the focus of the Chinese project `WenLan' led by our team. Specifically, with the weak correlation assumption over image-text pairs, we propose a two-tower pre-training model within the cross-modal contrastive learning (CMCL) framework. Unlike OpenAI CLIP that adopts a simple contrastive learning method, we devise a more advanced algorithm by adapting the latest method MoCo into the cross-modal scenario. By building a large queue-based dictionary, our CMCL can incorporate more negative samples in limited GPU resources. We further construct a large Chinese multi-source image-text dataset called RUC-CAS-WenLan for pre-training our CMCL model. Extensive experiments demonstrate that the pre-trained CMCL model outperforms both UNITER and OpenAI CLIP on various downstream tasks.
Most of the classical denoising methods restore clear results by selecting and averaging pixels in the noisy input. Instead of relying on hand-crafted selecting and averaging strategies, we propose to explicitly learn this process with deep neural networks. Specifically, we propose deformable 2D kernels for image denoising where the sampling locations and kernel weights are both learned. The proposed kernel naturally adapts to image structures and could effectively reduce the oversmoothing artifacts. Furthermore, we develop 3D deformable kernels for video denoising to more efficiently sample pixels across the spatial-temporal space. Our method is able to solve the misalignment issues of large motion from dynamic scenes. For better training our video denoising model, we introduce the trilinear sampler and a new regularization term. We demonstrate that the proposed method performs favorably against the state-of-the-art image and video denoising approaches on both synthetic and real-world data.
We study a worst-case scenario in generalization: Out-of-domain generalization from a single source. The goal is to learn a robust model from a single source and expect it to generalize over many unknown distributions. This challenging problem has been seldom investigated while existing solutions suffer from various limitations such as the ignorance of uncertainty assessment and label augmentation. In this paper, we propose uncertainty-guided domain generalization to tackle the aforementioned limitations. The key idea is to augment the source capacity in both feature and label spaces, while the augmentation is guided by uncertainty assessment. To the best of our knowledge, this is the first work to (1) quantify the generalization uncertainty from a single source and (2) leverage it to guide both feature and label augmentation for robust generalization. The model training and deployment are effectively organized in a Bayesian meta-learning framework. We conduct extensive comparisons and ablation study to validate our approach. The results prove our superior performance in a wide scope of tasks including image classification, semantic segmentation, text classification, and speech recognition.
In this work, we propose FastDPM, a unified framework for fast sampling in diffusion probabilistic models. FastDPM generalizes previous methods and gives rise to new algorithms with improved sample quality. We systematically investigate the fast sampling methods under this framework across different domains, on different datasets, and with different amount of conditional information provided for generation. We find the performance of a particular method depends on data domains (e.g., image or audio), the trade-off between sampling speed and sample quality, and the amount of conditional information. We further provide insights and recipes on the choice of methods for practitioners.
Co-training, extended from self-training, is one of the frameworks for semi-supervised learning. It works at the cost of training extra classifiers, where the algorithm should be delicately designed to prevent individual classifiers from collapsing into each other. In this paper, we present a simple and efficient co-training algorithm, named Multi-Head Co-Training, for semi-supervised image classification. By integrating base learners into a multi-head structure, the model is in a minimal amount of extra parameters. Every classification head in the unified model interacts with its peers through a "Weak and Strong Augmentation" strategy, achieving single-view co-training without promoting diversity explicitly. The effectiveness of Multi-Head Co-Training is demonstrated in an empirical study on standard semi-supervised learning benchmarks.
As climate change increases the intensity of natural disasters, society needs better tools for adaptation. Floods, for example, are the most frequent natural disaster, and better tools for flood risk communication could increase the support for flood-resilient infrastructure development. Our work aims to enable more visual communication of large-scale climate impacts via visualizing the output of coastal flood models as satellite imagery. We propose the first deep learning pipeline to ensure physical-consistency in synthetic visual satellite imagery. We advanced a state-of-the-art GAN called pix2pixHD, such that it produces imagery that is physically-consistent with the output of an expert-validated storm surge model (NOAA SLOSH). By evaluating the imagery relative to physics-based flood maps, we find that our proposed framework outperforms baseline models in both physical-consistency and photorealism. We envision our work to be the first step towards a global visualization of how climate change shapes our landscape. Continuing on this path, we show that the proposed pipeline generalizes to visualize arctic sea ice melt. We also publish a dataset of over 25k labelled image-pairs to study image-to-image translation in Earth observation.
Multi-modal image registration is a challenging problem yet important clinical task in many real applications and scenarios. For medical imaging based diagnosis, deformable registration among different image modalities is often required in order to provide complementary visual information, as the first step. During the registration, the semantic information is the key to match homologous points and pixels. Nevertheless, many conventional registration methods are incapable to capture the high-level semantic anatomical dense correspondences. In this work, we propose a novel multi-task learning system, JSSR, based on an end-to-end 3D convolutional neural network that is composed of a generator, a register and a segmentor, for the tasks of synthesis, registration and segmentation, respectively. This system is optimized to satisfy the implicit constraints between different tasks unsupervisedly. It first synthesizes the source domain images into the target domain, then an intra-modal registration is applied on the synthesized images and target images. Then we can get the semantic segmentation by applying segmentors on the synthesized images and target images, which are aligned by the same deformation field generated by the registers. The supervision from another fully-annotated dataset is used to regularize the segmentors. We extensively evaluate our JSSR system on a large-scale medical image dataset containing 1,485 patient CT imaging studies of four different phases (i.e., 5,940 3D CT scans with pathological livers) on the registration, segmentation and synthesis tasks. The performance is improved after joint training on the registration and segmentation tasks by $0.9\%$ and $1.9\%$ respectively from a highly competitive and accurate baseline. The registration part also consistently outperforms the conventional state-of-the-art multi-modal registration methods.
In ultrasound tomography, the speed of sound inside an object is estimated based on acoustic measurements carried out by sensors surrounding the object. An accurate forward model is a prominent factor for high-quality image reconstruction, but it can make computations far too time-consuming in many applications. Using approximate forward models, it is possible to speed up the computations, but the quality of the reconstruction may have to be compromised. In this paper, a neural network -based approach is proposed, that can compensate for modeling errors caused by the approximate forward models. The approach is tested with various different imaging scenarios in a simulated two-dimensional domain. The results show that with fairly small training data sets, the proposed approach can be utilized to approximate the modelling errors, and to significantly improve the image reconstruction quality in ultrasound tomography, compared to commonly used inversion algorithms.
This paper addresses the problem of media retrieval using a multimodal query (a query which combines visual input with additional semantic information in natural language feedback). We propose a SynthTriplet GAN framework which resolves this task by expanding the multimodal query with a synthetically generated image that captures semantic information from both image and text input. We introduce a novel triplet mining method that uses a synthetic image as an anchor to directly optimize for embedding distances of generated and target images. We demonstrate that apart from the added value of retrieval illustration with synthetic image with the focus on customization and user feedback, the proposed method greatly surpasses other multimodal generation methods and achieves state of the art results in the multimodal retrieval task. We also show that in contrast to other retrieval methods, our method provides explainable embeddings.