Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

Most existing human matting algorithms tried to separate pure human-only foreground from the background. In this paper, we propose a Virtual Multi-modality Foreground Matting (VMFM) method to learn human-object interactive foreground (human and objects interacted with him or her) from a raw RGB image. The VMFM method requires no additional inputs, e.g. trimap or known background. We reformulate foreground matting as a self-supervised multi-modality problem: factor each input image into estimated depth map, segmentation mask, and interaction heatmap using three auto-encoders. In order to fully utilize the characteristics of each modality, we first train a dual encoder-to-decoder network to estimate the same alpha matte. Then we introduce a self-supervised method: Complementary Learning(CL) to predict deviation probability map and exchange reliable gradients across modalities without label. We conducted extensive experiments to analyze the effectiveness of each modality and the significance of different components in complementary learning. We demonstrate that our model outperforms the state-of-the-art methods.

Tao: A Learning Framework for Adaptive Nearest Neighbor Search using Static Features Only

Approximate nearest neighbor (ANN) search is a fundamental problem in areas such as data management,information retrieval and machine learning. Recently, Li et al. proposed a learned approach named AdaptNN to support adaptive ANN query processing. In the middle of query execution, AdaptNN collects a number of runtime features and predicts termination condition for each individual query, by which better end-to-end latency is attained. Despite its efficiency, using runtime features complicates the learning process and leads to performance degradation. Radically different from AdaptNN, we argue that it is promising to predict termination condition before query exetution. Particularly, we developed Tao, a general learning framework for Terminating ANN queries Adaptively using Only static features. Upon the arrival of a query, Tao first maps the query to a local intrinsic dimension (LID) number, and then predicts the termination condition using LID instead of runtime features. By decoupling prediction procedure from query execution, Tao eliminates the laborious feature selection process involved in AdaptNN. Besides, two design principles are formulated to guide the application of Tao and improve the explainability of the prediction model. We integrate two state-of-the-art indexing approaches, i.e., IMI and HNSW, into Tao, and evaluate the performance over several million to billion-scale datasets. Experimental results show that, in addition to its simplicity and generality , Tao achieves up to 2.69x speedup even compared to its counterpart, at the same high accuracy targets.

A Simple Unified Framework for Anomaly Detection in Deep Reinforcement Learning

Abnormal states in deep reinforcement learning~(RL) are states that are beyond the scope of an RL policy. Such states may make the RL system unsafe and impede its deployment in real scenarios. In this paper, we propose a simple yet effective anomaly detection framework for deep RL algorithms that simultaneously considers random, adversarial and out-of-distribution~(OOD) state outliers. In particular, we attain the class-conditional distributions for each action class under the Gaussian assumption, and rely on these distributions to discriminate between inliers and outliers based on Mahalanobis Distance~(MD) and Robust Mahalanobis Distance. We conduct extensive experiments on Atari games that verify the effectiveness of our detection strategies. To the best of our knowledge, we present the first in-detail study of statistical and adversarial anomaly detection in deep RL algorithms. This simple unified anomaly detection paves the way towards deploying safe RL systems in real-world applications.

MACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verification

Most of the recent state-of-the-art results for speaker verification are achieved by X-vector and its subsequent variants. In this paper, we propose a new network architecture which aggregates the channel and context interdependence features from multi aspect based on Time Delay Neural Network (TDNN). Firstly, we use the SE-Res2Blocks as in ECAPA-TDNN to explicitly model the channel interdependence to realize adaptive calibration of channel features, and process local context features in a multi-scale way at a more granular level compared with conventional TDNN-based methods. Secondly, we explore to use the encoder structure of Transformer to model the global context interdependence features at an utterance level which can capture better long term temporal characteristics. Before the pooling layer, we aggregate the outputs of SE-Res2Blocks and Transformer encoder to leverage the complementary channel and context interdependence features learned by themself respectively. Finally, instead of performing a single attentive statistics pooling, we also find it beneficial to extend the pooling method in a multi-head way which can discriminate features from multiple aspect. The proposed MACCIF-TDNN architecture can outperform most of the state-of-the-art TDNN-based systems on VoxCeleb1 test sets.

Population-coding and Dynamic-neurons improved Spiking Actor Network for Reinforcement Learning

With the Deep Neural Networks (DNNs) as a powerful function approximator, Deep Reinforcement Learning (DRL) has been excellently demonstrated on robotic control tasks. Compared to DNNs with vanilla artificial neurons, the biologically plausible Spiking Neural Network (SNN) contains a diverse population of spiking neurons, making it naturally powerful on state representation with spatial and temporal information. Based on a hybrid learning framework, where a spike actor-network infers actions from states and a deep critic network evaluates the actor, we propose a Population-coding and Dynamic-neurons improved Spiking Actor Network (PDSAN) for efficient state representation from two different scales: input coding and neuronal coding. For input coding, we apply population coding with dynamically receptive fields to directly encode each input state component. For neuronal coding, we propose different types of dynamic-neurons (containing 1st-order and 2nd-order neuronal dynamics) to describe much more complex neuronal dynamics. Finally, the PDSAN is trained in conjunction with deep critic networks using the Twin Delayed Deep Deterministic policy gradient algorithm (TD3-PDSAN). Extensive experimental results show that our TD3-PDSAN model achieves better performance than state-of-the-art models on four OpenAI gym benchmark tasks. It is an important attempt to improve RL with SNN towards the effective computation satisfying biological plausibility.

WASE: Learning When to Attend for Speaker Extraction in Cocktail Party Environments

In the speaker extraction problem, it is found that additional information from the target speaker contributes to the tracking and extraction of the target speaker, which includes voiceprint, lip movement, facial expression, and spatial information. However, no one cares for the cue of sound onset, which has been emphasized in the auditory scene analysis and psychology. Inspired by it, we explicitly modeled the onset cue and verified the effectiveness in the speaker extraction task. We further extended to the onset/offset cues and got performance improvement. From the perspective of tasks, our onset/offset-based model completes the composite task, a complementary combination of speaker extraction and speaker-dependent voice activity detection. We also combined voiceprint with onset/offset cues. Voiceprint models voice characteristics of the target while onset/offset models the start/end information of the speech. From the perspective of auditory scene analysis, the combination of two perception cues can promote the integrity of the auditory object. The experiment results are also close to state-of-the-art performance, using nearly half of the parameters. We hope that this work will inspire communities of speech processing and psychology, and contribute to communication between them. Our code will be available in https://github.com/aispeech-lab/wase/.

Leveraging Structural Information to Improve Point Line Visual-Inertial Odometry

Leveraging line features can help to improve the localization accuracy of point-based monocular Visual-Inertial Odometry (VIO) system, as lines provide additional constraints. Moreover, in an artificial environment, some straight lines are parallel to each other. In this paper, we designed a VIO system based on points and straight lines, which divides straight lines into structural straight lines (that is, straight lines parallel to each other) and non-structural straight lines. In addition, unlike the orthogonal representation using four parameters to represent the 3D straight line, we only used two parameters to minimize the representation of the structural straight line and the non-structural straight line. Furthermore, we designed a straight line matching strategy based on sampling points to improve the efficiency and success rate of straight line matching. The effectiveness of our method is verified on both public datasets of EuRoc and TUM VI benchmark and compared with other state-of-the-art algorithms.

MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separation

Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance over the conventional MVDR by replacing the matrix inversion and eigenvalue decomposition with two recurrent neural networks. In this work, we present a self-attentive RNN beamformer to further improve our previous RNN-based beamformer by leveraging on the powerful modeling capability of self-attention. Temporal-spatial self-attention module is proposed to better learn the beamforming weights from the speech and noise spatial covariance matrices. The temporal self-attention module could help RNN to learn global statistics of covariance matrices. The spatial self-attention module is designed to attend on the cross-channel correlation in the covariance matrices. Furthermore, a multi-channel input with multi-speaker directional features and multi-speaker speech separation outputs (MIMO) model is developed to improve the inference efficiency. The evaluations demonstrate that our proposed MIMO self-attentive RNN beamformer improves both the automatic speech recognition (ASR) accuracy and the perceptual estimation of speech quality (PESQ) against prior arts.