General image fusion aims at integrating important information from multi-source images. However, due to the significant cross-task gap, the respective fusion mechanism varies considerably in practice, resulting in limited performance across subtasks. To handle this problem, we propose a novel task-customized mixture of adapters (TC-MoA) for general image fusion, adaptively prompting various fusion tasks in a unified model. We borrow the insight from the mixture of experts (MoE), taking the experts as efficient tuning adapters to prompt a pre-trained foundation model. These adapters are shared across different tasks and constrained by mutual information regularization, ensuring compatibility with different tasks while complementarity for multi-source images. The task-specific routing networks customize these adapters to extract task-specific information from different sources with dynamic dominant intensity, performing adaptive visual feature prompt fusion. Notably, our TC-MoA controls the dominant intensity bias for different fusion tasks, successfully unifying multiple fusion tasks in a single model. Extensive experiments show that TC-MoA outperforms the competing approaches in learning commonalities while retaining compatibility for general image fusion (multi-modal, multi-exposure, and multi-focus), and also demonstrating striking controllability on more generalization experiments. The code is available at https://github.com/YangSun22/TC-MoA .
In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty. However, in the presence of environmental stochasticity (noise), purely optimistic exploration may lead to excessive probing of high-noise areas, consequently impeding exploration efficiency. Hence, in exploring noisy environments, while optimism-driven exploration serves as a foundation, prudent attention to alleviating unnecessary over-exploration in high-noise areas becomes beneficial. In this work, we propose Optimistic Value Distribution Explorer (OVD-Explorer) to achieve a noise-aware optimistic exploration for continuous control. OVD-Explorer proposes a new measurement of the policy's exploration ability considering noise in optimistic perspectives, and leverages gradient ascent to drive exploration. Practically, OVD-Explorer can be easily integrated with continuous control RL algorithms. Extensive evaluations on the MuJoCo and GridChaos tasks demonstrate the superiority of OVD-Explorer in achieving noise-aware optimistic exploration.
With the increasing ageing population, fall events classification has drawn much research attention. In the development of deep learning, the quality of data labels is crucial. Most of the datasets are labelled automatically or semi-automatically, and the samples may be mislabeled, which constrains the performance of Deep Neural Networks (DNNs). Recent research on noisy label learning confirms that neural networks first focus on the clean and simple instances and then follow the noisy and hard instances in the training stage. To address the learning with noisy label problem and protect the human subjects' privacy, we propose a simple but effective approach named Joint Cooperative training with Trinity Networks (JoCoT). To mitigate the privacy issue, human skeleton data are used. The robustness and performance of the noisy label learning framework is improved by using the two teacher modules and one student module in the proposed JoCoT. To mitigate the incorrect selections, the predictions from the teacher modules are applied with the consensus-based method to guide the student module training. The performance evaluation on the widely used UP-Fall dataset and comparison with the state-of-the-art, confirms the effectiveness of the proposed JoCoT in high noise rates. Precisely, JoCoT outperforms the state-of-the-art by 5.17% and 3.35% with the averaged pairflip and symmetric noises, respectively.
Significant strides have been made in enhancing the accuracy of Multi-View Stereo (MVS)-based 3D reconstruction. However, untextured areas with unstable photometric consistency often remain incompletely reconstructed. In this paper, we propose a resilient and effective multi-view stereo approach (MP-MVS). We design a multi-scale windows PatchMatch (mPM) to obtain reliable depth of untextured areas. In contrast with other multi-scale approaches, which is faster and can be easily extended to PatchMatch-based MVS approaches. Subsequently, we improve the existing checkerboard sampling schemes by limiting our sampling to distant regions, which can effectively improve the efficiency of spatial propagation while mitigating outlier generation. Finally, we introduce and improve planar prior assisted PatchMatch of ACMP. Instead of relying on photometric consistency, we utilize geometric consistency information between multi-views to select reliable triangulated vertices. This strategy can obtain a more accurate planar prior model to rectify photometric consistency measurements. Our approach has been tested on the ETH3D High-res multi-view benchmark with several state-of-the-art approaches. The results demonstrate that our approach can reach the state-of-the-art. The associated codes will be accessible at https://github.com/RongxuanTan/MP-MVS.
Multi-task learning (MTL) has shown great potential in medical image analysis, improving the generalizability of the learned features and the performance in individual tasks. However, most of the work on MTL focuses on either architecture design or gradient manipulation, while in both scenarios, features are learned in a competitive manner. In this work, we propose to formulate MTL as a multi/bi-level optimization problem, and therefore force features to learn from each task in a cooperative approach. Specifically, we update the sub-model for each task alternatively taking advantage of the learned sub-models of the other tasks. To alleviate the negative transfer problem during the optimization, we search for flat minima for the current objective function with regard to features from other tasks. To demonstrate the effectiveness of the proposed approach, we validate our method on three publicly available datasets. The proposed method shows the advantage of cooperative learning, and yields promising results when compared with the state-of-the-art MTL approaches. The code will be available online.
Microwave photonic (MWP) transversal signal processors offer a compelling solution for realizing versatile high-speed information processing by combining the advantages of reconfigurable electrical digital signal processing and high-bandwidth photonic processing. With the capability of generating a number of discrete wavelengths from micro-scale resonators, optical microcombs are powerful multi-wavelength sources for implementing MWP transversal signal processors with significantly reduced size, power consumption, and complexity. By using microcomb-based MWP transversal signal processors, a diverse range of signal processing functions have been demonstrated recently. In this paper, we provide a detailed analysis for the processing inaccuracy that is induced by the imperfect response of experimental components. First, we investigate the errors arising from different sources including imperfections in the microcombs, the chirp of electro-optic modulators, chromatic dispersion of the dispersive module, shaping errors of the optical spectral shapers, and noise of the photodetector. Next, we provide a global picture quantifying the impact of different error sources on the overall system performance. Finally, we introduce feedback control to compensate the errors caused by experimental imperfections and achieve significantly improved accuracy. These results provide a guide for optimizing the accuracy of microcomb-based MWP transversal signal processors.
This paper describes the TSUP team's submission to the ISCSLP 2022 conversational short-phrase speaker diarization (CSSD) challenge which particularly focuses on short-phrase conversations with a new evaluation metric called conversational diarization error rate (CDER). In this challenge, we explore three kinds of typical speaker diarization systems, which are spectral clustering(SC) based diarization, target-speaker voice activity detection(TS-VAD) and end-to-end neural diarization(EEND) respectively. Our major findings are summarized as follows. First, the SC approach is more favored over the other two approaches under the new CDER metric. Second, tuning on hyperparameters is essential to CDER for all three types of speaker diarization systems. Specifically, CDER becomes smaller when the length of sub-segments setting longer. Finally, multi-system fusion through DOVER-LAP will worsen the CDER metric on the challenge data. Our submitted SC system eventually ranks the third place in the challenge.
Fall detection and classification become an imper- ative problem for healthcare applications particularity with the increasingly ageing population. Currently, most of the fall clas- sification algorithms provide binary fall or no-fall classification. For better healthcare, it is thus not enough to do binary fall classification but to extend it to multiple fall events classification. In this work, we utilize the privacy mitigating human skeleton data for multiple fall events classification. The skeleton features are extracted from the original RGB images to not only mitigate the personal privacy, but also to reduce the impact of the dynamic illuminations. The proposed fall events classification method is divided into two stages. In the first stage, the model is trained to achieve the binary classification to filter out the no-fall events. Then, in the second stage, the deep neural network (DNN) model is trained to further classify the five types of fall events. In order to confirm the efficiency of the proposed method, the experiments on the UP-Fall dataset outperform the state-of-the-art.
Self-supervised learning (SSL) achieves great success in monaural speech enhancement, while the accuracy of the target speech estimation, particularly for unseen speakers, remains inadequate with existing pre-tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, and spoken content, the latent representation for speech enhancement becomes a tough task. In this paper, we study the effectiveness of each feature which is commonly used in speech enhancement and exploit the feature combination in the SSL case. Besides, we propose an ensemble training strategy. The latent representation of the clean speech signal is learned, meanwhile, the dereverberated mask and the estimated ratio mask are exploited to denoise and dereverberate the mixture. The latent representation learning and the masks estimation are considered as two pre-tasks in the training stage. In addition, to study the effectiveness between the pre-tasks, we compare different training routines to train the model and further refine the performance. The NOISEX and DAPS corpora are used to evaluate the efficacy of the proposed method, which also outperforms the state-of-the-art methods.