联合学习（FL）支持地理分布式设备的培训模型。然而，传统的FL系统采用集中式同步策略，提高了高通信压力和模型泛化挑战。 FL的现有优化未能加速异构设备的培训或遭受差的通信效率。在本文中，我们提出了一个支持在异构设备上分散的异步训练的框架的Hadfl。使用本地数据的异质性感知本地步骤本地培训设备。在每个聚合循环中，基于执行模型同步和聚合的概率来选择它们。与传统的FL系统相比，HADFL可以减轻中心服务器的通信压力，有效地利用异构计算能力，并且可以分别实现比Pytorch分布式训练方案分别的最大加速度为3.15倍，而不是Pytorch分布式训练方案，几乎没有损失收敛准确性。

Projection operations are a typical computation bottleneck in online learning. In this paper, we enable projection-free online learning within the framework of Online Convex Optimization with Memory (OCO-M) -- OCO-M captures how the history of decisions affects the current outcome by allowing the online learning loss functions to depend on both current and past decisions. Particularly, we introduce the first projection-free meta-base learning algorithm with memory that minimizes dynamic regret, i.e., that minimizes the suboptimality against any sequence of time-varying decisions. We are motivated by artificial intelligence applications where autonomous agents need to adapt to time-varying environments in real-time, accounting for how past decisions affect the present. Examples of such applications are: online control of dynamical systems; statistical arbitrage; and time series prediction. The algorithm builds on the Online Frank-Wolfe (OFW) and Hedge algorithms. We demonstrate how our algorithm can be applied to the online control of linear time-varying systems in the presence of unpredictable process noise. To this end, we develop the first controller with memory and bounded dynamic regret against any optimal time-varying linear feedback control policy. We validate our algorithm in simulated scenarios of online control of linear time-invariant systems.

Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and ({even more importantly}) explainable predictions. Existing approaches typically explicate network outputs in a post-hoc fashion, under an implicit assumption that faithful explanations come from accurate predictions/classifications. We have an opposite claim that explanations boost (or even determine) classification. That is, end-to-end learning of explanation factors to augment discriminative representation extraction could be a more intuitive strategy to inversely assure fine-grained explainability, e.g., in those neuroimaging and neuroscience studies with high-dimensional data containing noisy, redundant, and task-irrelevant information. In this paper, we propose such an explainable geometric deep network dubbed as NeuroExplainer, with applications to uncover altered infant cortical development patterns associated with preterm birth. Given fundamental cortical attributes as network input, our NeuroExplainer adopts a hierarchical attention-decoding framework to learn fine-grained attentions and respective discriminative representations to accurately recognize preterm infants from term-born infants at term-equivalent age. NeuroExplainer learns the hierarchical attention-decoding modules under subject-level weak supervision coupled with targeted regularizers deduced from domain knowledge regarding brain development. These prior-guided constraints implicitly maximizes the explainability metrics (i.e., fidelity, sparsity, and stability) in network training, driving the learned network to output detailed explanations and accurate classifications. Experimental results on the public dHCP benchmark suggest that NeuroExplainer led to quantitatively reliable explanation results that are qualitatively consistent with representative neuroimaging studies.

In the field of cross-modal retrieval, single encoder models tend to perform better than dual encoder models, but they suffer from high latency and low throughput. In this paper, we present a dual encoder model called BagFormer that utilizes a cross modal interaction mechanism to improve recall performance without sacrificing latency and throughput. BagFormer achieves this through the use of bag-wise interactions, which allow for the transformation of text to a more appropriate granularity and the incorporation of entity knowledge into the model. Our experiments demonstrate that BagFormer is able to achieve results comparable to state-of-the-art single encoder models in cross-modal retrieval tasks, while also offering efficient training and inference with 20.72 times lower latency and 25.74 times higher throughput.

Body Mass Index (BMI), age, height and weight are important indicators of human health conditions, which can provide useful information for plenty of practical purposes, such as health care, monitoring and re-identification. Most existing methods of health indicator prediction mainly use front-view body or face images. These inputs are hard to be obtained in daily life and often lead to the lack of robustness for the models, considering their strict requirements on view and pose. In this paper, we propose to employ gait videos to predict health indicators, which are more prevalent in surveillance and home monitoring scenarios. However, the study of health indicator prediction from gait videos using deep learning was hindered due to the small amount of open-sourced data. To address this issue, we analyse the similarity and relationship between pose estimation and health indicator prediction tasks, and then propose a paradigm enabling deep learning for small health indicator datasets by pre-training on the pose estimation task. Furthermore, to better suit the health indicator prediction task, we bring forward Global-Local Aware aNd Centrosymmetric Encoder (GLANCE) module. It first extracts local and global features by progressive convolutions and then fuses multi-level features by a centrosymmetric double-path hourglass structure in two different ways. Experiments demonstrate that the proposed paradigm achieves state-of-the-art results for predicting health indicators on MoVi, and that the GLANCE module is also beneficial for pose estimation on 3DPW.

Developing autonomous vehicles (AVs) helps improve the road safety and traffic efficiency of intelligent transportation systems (ITS). Accurately predicting the trajectories of traffic participants is essential to the decision-making and motion planning of AVs in interactive scenarios. Recently, learning-based trajectory predictors have shown state-of-the-art performance in highway or urban areas. However, most existing learning-based models trained with fixed datasets may perform poorly in continuously changing scenarios. Specifically, they may not perform well in learned scenarios after learning the new one. This phenomenon is called "catastrophic forgetting". Few studies investigate trajectory predictions in continuous scenarios, where catastrophic forgetting may happen. To handle this problem, first, a novel continual learning (CL) approach for vehicle trajectory prediction is proposed in this paper. Then, inspired by brain science, a dynamic memory mechanism is developed by utilizing the measurement of traffic divergence between scenarios, which balances the performance and training efficiency of the proposed CL approach. Finally, datasets collected from different locations are used to design continual training and testing methods in experiments. Experimental results show that the proposed approach achieves consistently high prediction accuracy in continuous scenarios without re-training, which mitigates catastrophic forgetting compared to non-CL approaches. The implementation of the proposed approach is publicly available at https://github.com/BIT-Jack/D-GSM

We present IMAS, a method that segments the primary objects in videos without manual annotation in training or inference. Previous methods in unsupervised video object segmentation (UVOS) have demonstrated the effectiveness of motion as either input or supervision for segmentation. However, motion signals may be uninformative or even misleading in cases such as deformable objects and objects with reflections, causing unsatisfactory segmentation. In contrast, IMAS achieves Improved UVOS with Motion-Appearance Synergy. Our method has two training stages: 1) a motion-supervised object discovery stage that deals with motion-appearance conflicts through a learnable residual pathway; 2) a refinement stage with both low- and high-level appearance supervision to correct model misconceptions learned from misleading motion cues. Additionally, we propose motion-semantic alignment as a model-agnostic annotation-free hyperparam tuning method. We demonstrate its effectiveness in tuning critical hyperparams previously tuned with human annotation or hand-crafted hyperparam-specific metrics. IMAS greatly improves the segmentation quality on several common UVOS benchmarks. For example, we surpass previous methods by 8.3% on DAVIS16 benchmark with only standard ResNet and convolutional heads. We intend to release our code for future research and applications.

Training a Neural Radiance Field (NeRF) without pre-computed camera poses is challenging. Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes. However, these methods still face difficulties during dramatic camera movement. We tackle this challenging problem by incorporating undistorted monocular depth priors. These priors are generated by correcting scale and shift parameters during training, with which we are then able to constrain the relative poses between consecutive frames. This constraint is achieved using our proposed novel loss functions. Experiments on real-world indoor and outdoor scenes show that our method can handle challenging camera trajectories and outperforms existing methods in terms of novel view rendering quality and pose estimation accuracy.

In this paper, we propose an end-to-end Retrieval-Augmented Visual Language Model (REVEAL) that learns to encode world knowledge into a large-scale memory, and to retrieve from it to answer knowledge-intensive queries. REVEAL consists of four key components: the memory, the encoder, the retriever and the generator. The large-scale memory encodes various sources of multimodal world knowledge (e.g. image-text pairs, question answering pairs, knowledge graph triplets, etc) via a unified encoder. The retriever finds the most relevant knowledge entries in the memory, and the generator fuses the retrieved knowledge with the input query to produce the output. A key novelty in our approach is that the memory, encoder, retriever and generator are all pre-trained end-to-end on a massive amount of data. Furthermore, our approach can use a diverse set of multimodal knowledge sources, which is shown to result in significant gains. We show that REVEAL achieves state-of-the-art results on visual question answering and image captioning.

This work explores an efficient approach to establish a foundational video-text model for tasks including open-vocabulary video classification, text-to-video retrieval, video captioning and video question-answering. We present VideoCoCa that reuses a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules (for example, cross-frame attention layer or perceiver resampler) and finetune the modified architecture on video-text data, we surprisingly find that the generative attentional pooling and contrastive attentional pooling layers in the image-text CoCa design are instantly adaptable to ``flattened frame embeddings'', yielding a strong zero-shot transfer baseline for many video-text tasks. Specifically, the frozen image encoder of a pretrained image-text CoCa takes each video frame as inputs and generates \(N\) token embeddings per frame for totally \(T\) video frames. We flatten \(N \times T\) token embeddings as a long sequence of frozen video representation and apply CoCa's generative attentional pooling and contrastive attentional pooling on top. All model weights including pooling layers are directly loaded from an image-text CoCa pretrained model. Without any video or video-text data, VideoCoCa's zero-shot transfer baseline already achieves state-of-the-art results on zero-shot video classification on Kinetics 400/600/700, UCF101, HMDB51, and Charades, as well as zero-shot text-to-video retrieval on MSR-VTT and ActivityNet Captions. We also explore lightweight finetuning on top of VideoCoCa, and achieve strong results on video question-answering (iVQA, MSRVTT-QA, MSVD-QA) and video captioning (MSR-VTT, ActivityNet, Youcook2). Our approach establishes a simple and effective video-text baseline for future research.