Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022

In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for the EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge. Especially, we exploit the recently released Ego4D dataset \cite{grauman2021ego4d} to pioneer Egocentric VLP from pretraining dataset, pretraining objective, and development set. Based on the above three designs, we develop a pretrained video-language model that is able to transfer its egocentric video-text representation to MIR benchmark. Furthermore, we devise an adaptive multi-instance max-margin loss to effectively fine-tune the model and equip the dual-softmax technique for reliable inference. Our best single model obtains strong performance on the challenge test set with 47.39% mAP and 61.44% nDCG. The code is available at https://github.com/showlab/EgoVLP.

Towards Generalizable Person Re-identification with a Bi-stream Generative Model

Generalizable person re-identification (re-ID) has attracted growing attention due to its powerful adaptation capability in the unseen data domain. However, existing solutions often neglect either crossing cameras (e.g., illumination and resolution differences) or pedestrian misalignments (e.g., viewpoint and pose discrepancies), which easily leads to poor generalization capability when adapted to the new domain. In this paper, we formulate these difficulties as: 1) Camera-Camera (CC) problem, which denotes the various human appearance changes caused by different cameras; 2) Camera-Person (CP) problem, which indicates the pedestrian misalignments caused by the same identity person under different camera viewpoints or changing pose. To solve the above issues, we propose a Bi-stream Generative Model (BGM) to learn the fine-grained representations fused with camera-invariant global feature and pedestrian-aligned local feature, which contains an encoding network and two stream decoding sub-networks. Guided by original pedestrian images, one stream is employed to learn a camera-invariant global feature for the CC problem via filtering cross-camera interference factors. For the CP problem, another stream learns a pedestrian-aligned local feature for pedestrian alignment using information-complete densely semantically aligned part maps. Moreover, a part-weighted loss function is presented to reduce the influence of missing parts on pedestrian alignment. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods on the large-scale generalizable re-ID benchmarks, involving domain generalization setting and cross-domain setting.

Hybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization

Multi-objective orienteering problems (MO-OPs) are classical multi-objective routing problems and have received a lot of attention in the past decades. This study seeks to solve MO-OPs through a problem-decomposition framework, that is, a MO-OP is decomposed into a multi-objective knapsack problem (MOKP) and a travelling salesman problem (TSP). The MOKP and TSP are then solved by a multi-objective evolutionary algorithm (MOEA) and a deep reinforcement learning (DRL) method, respectively. While the MOEA module is for selecting cities, the DRL module is for planning a Hamiltonian path for these cities. An iterative use of these two modules drives the population towards the Pareto front of MO-OPs. The effectiveness of the proposed method is compared against NSGA-II and NSGA-III on various types of MO-OP instances. Experimental results show that our method exhibits the best performance on almost all the test instances, and has shown strong generalization ability.

EDITnet: A Lightweight Network for Unsupervised Domain Adaptation in Speaker Verification

Performance degradation caused by language mismatch is a common problem when applying a speaker verification system on speech data in different languages. This paper proposes a domain transfer network, named EDITnet, to alleviate the language-mismatch problem on speaker embeddings without requiring speaker labels. The network leverages a conditional variational auto-encoder to transfer embeddings from the target domain into the source domain. A self-supervised learning strategy is imposed on the transferred embeddings so as to increase the cosine distance between embeddings from different speakers. In the training process of the EDITnet, the embedding extraction model is fixed without fine-tuning, which renders the training efficient and low-cost. Experiments on Voxceleb and CN-Celeb show that the embeddings transferred by EDITnet outperform the un-transferred ones by around 30% with the ECAPA-TDNN512. Performance improvement can also be achieved with other embedding extraction models, e.g., TDNN, SE-ResNet34.

Unsupervised Knowledge Adaptation for Passenger Demand Forecasting

Considering the multimodal nature of transport systems and potential cross-modal correlations, there is a growing trend of enhancing demand forecasting accuracy by learning from multimodal data. These multimodal forecasting models can improve accuracy but be less practical when different parts of multimodal datasets are owned by different institutions who cannot directly share data among them. While various institutions may can not share their data with each other directly, they may share forecasting models trained by their data, where such models cannot be used to identify the exact information from their datasets. This study proposes an Unsupervised Knowledge Adaptation Demand Forecasting framework to forecast the demand of the target mode by utilizing a pre-trained model based on data of another mode, which does not require direct data sharing of the source mode. The proposed framework utilizes the potential shared patterns among multiple transport modes to improve forecasting performance while avoiding the direct sharing of data among different institutions. Specifically, a pre-trained forecasting model is first learned based on the data of a source mode, which can capture and memorize the source travel patterns. Then, the demand data of the target dataset is encoded into an individual knowledge part and a sharing knowledge part which will extract travel patterns by individual extraction network and sharing extraction network, respectively. The unsupervised knowledge adaptation strategy is utilized to form the sharing features for further forecasting by making the pre-trained network and the sharing extraction network analogous. Our findings illustrate that unsupervised knowledge adaptation by sharing the pre-trained model to the target mode can improve the forecasting performance without the dependence on direct data sharing.

Egocentric Video-Language Pretraining

Video-Language Pretraining (VLP), aiming to learn transferable representation to advance a wide range of video-text downstream tasks, has recently received increasing attention. Dominant works that achieve strong performance rely on large-scale, 3rd-person video-text datasets, such as HowTo100M. In this work, we exploit the recently released Ego4D dataset to pioneer Egocentric VLP along three directions. (i) We create EgoClip, a 1st-person video-text pretraining dataset comprising 3.8M clip-text pairs well-chosen from Ego4D, covering a large variety of human daily activities. (ii) We propose a novel pretraining objective, dubbed as EgoNCE, which adapts video-text contrastive learning to egocentric domain by mining egocentric-aware positive and negative samples. (iii) We introduce EgoMCQ, a development benchmark that is close to EgoClip and hence can support effective validation and fast exploration of our design decisions regarding EgoClip and EgoNCE. Furthermore, we demonstrate strong performance on five egocentric downstream tasks across three datasets: video-text retrieval on EPIC-KITCHENS-100; action recognition on Charades-Ego; and natural language query, moment query, and object state change classification on Ego4D challenge benchmarks. The dataset and code will be available at https://github.com/showlab/EgoVLP.

Efficient-Adam: Communication-Efficient Distributed Adam with Complexity Analysis

Distributed adaptive stochastic gradient methods have been widely used for large-scale nonconvex optimization, such as training deep learning models. However, their communication complexity on finding $\varepsilon$-stationary points has rarely been analyzed in the nonconvex setting. In this work, we present a novel communication-efficient distributed Adam in the parameter-server model for stochastic nonconvex optimization, dubbed {\em Efficient-Adam}. Specifically, we incorporate a two-way quantization scheme into Efficient-Adam to reduce the communication cost between the workers and server. Simultaneously, we adopt a two-way error feedback strategy to reduce the biases caused by the two-way quantization on both the server and workers, respectively. In addition, we establish the iteration complexity for the proposed Efficient-Adam with a class of quantization operators, and further characterize its communication complexity between the server and workers when an $\varepsilon$-stationary point is achieved. Finally, we apply Efficient-Adam to solve a toy stochastic convex optimization problem and train deep learning models on real-world vision and language tasks. Extensive experiments together with a theoretical guarantee justify the merits of Efficient Adam.

An Investigation on Applying Acoustic Feature Conversion to ASR of Adult and Child Speech

The performance of child speech recognition is generally less satisfactory compared to adult speech due to limited amount of training data. Significant performance degradation is expected when applying an automatic speech recognition (ASR) system trained on adult speech to child speech directly, as a result of domain mismatch. The present study is focused on adult-to-child acoustic feature conversion to alleviate this mismatch. Different acoustic feature conversion approaches, including deep neural network based and signal processing based, are investigated and compared under a fair experimental setting, in which converted acoustic features from the same amount of labeled adult speech are used to train the ASR models from scratch. Experimental results reveal that not all of the conversion methods lead to ASR performance gain. Specifically, as a classic unsupervised domain adaptation method, the statistic matching does not show an effectiveness. A disentanglement-based auto-encoder (DAE) conversion framework is found to be useful and the approach of F0 normalization achieves the best performance. It is noted that the F0 distribution of converted features is an important attribute to reflect the conversion quality, while utilizing an adult-child deep classification model to make judgment is shown to be inappropriate.

Demand Response Method Considering Multiple Types of Flexible Loads in Industrial Parks

With the rapid development of the energy internet, the proportion of flexible loads in smart grid is getting much higher than before. It is highly important to model flexible loads based on demand response. Therefore, a new demand response method considering multiple flexible loads is proposed in this paper to character the integrated demand response (IDR) resources. Firstly, a physical process analytical deduction (PPAD) model is proposed to improve the classification of flexible loads in industrial parks. Scenario generation, data point augmentation, and smooth curves under various operating conditions are considered to enhance the applicability of the model. Secondly, in view of the strong volatility and poor modeling effect of Wasserstein-generative adversarial networks (WGAN), an improved WGAN-gradient penalty (IWGAN-GP) model is developed to get a faster convergence speed than traditional WGAN and generate a higher quality samples. Finally, the PPAD and IWGAN-GP models are jointly implemented to reveal the degree of correlation between flexible loads. Meanwhile, an intelligent offline database is built to deal with the impact of nonlinear factors in different response scenarios. Numerical examples have been performed with the results proving that the proposed method is significantly better than the existing technologies in reducing load modeling deviation and improving the responsiveness of park loads.