Li Zhang

Hao Zhu, Wayne Wu, Wentao Zhu et al.

Large-scale datasets have played indispensable roles in the recent success of face generation/editing and significantly facilitated the advances of emerging research fields. However, the academic community still lacks a video dataset with diverse facial attribute annotations, which is crucial for the research on face-related videos. In this work, we propose a large-scale, high-quality, and diverse video dataset with rich facial attribute annotations, named the High-Quality Celebrity Video Dataset (CelebV-HQ). CelebV-HQ contains 35,666 video clips with the resolution of 512x512 at least, involving 15,653 identities. All clips are labeled manually with 83 facial attributes, covering appearance, action, and emotion. We conduct a comprehensive analysis in terms of age, ethnicity, brightness stability, motion smoothness, head pose diversity, and data quality to demonstrate the diversity and temporal coherence of CelebV-HQ. Besides, its versatility and potential are validated on two representative tasks, i.e., unconditional video generation and video facial attribute editing. Furthermore, we envision the future potential of CelebV-HQ, as well as the new opportunities and challenges it would bring to related research directions. Data, code, and models are publicly available. Project page: https://celebv-hq.github.io.

Li Zhang, Mohan Chen, Anurag Arnab et al.

Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they are still limited in capturing long-range structured relationships as they typically consist of layers of local kernels. A fully-connected graph, such as the self-attention operation in Transformers, is beneficial for such modelling, however, its computational overhead is prohibitive. In this paper, we propose a dynamic graph message passing network, that significantly reduces the computational complexity compared to related works modelling a fully-connected graph. This is achieved by adaptively sampling nodes in the graph, conditioned on the input, for message passing. Based on the sampled nodes, we dynamically predict node-dependent filter weights and the affinity matrix for propagating information between them. This formulation allows us to design a self-attention module, and more importantly a new Transformer-based backbone network, that we use for both image classification pretraining, and for addressing various downstream tasks (object detection, instance and semantic segmentation). Using this model, we show significant improvements with respect to strong, state-of-the-art baselines on four different tasks. Our approach also outperforms fully-connected graphs while using substantially fewer floating-point operations and parameters. Code and models will be made publicly available at https://github.com/fudan-zvg/DGMN2

Xiao Han, Sen He, Li Zhang et al.

Interactive garment retrieval (IGR) aims to retrieve a target garment image based on a reference garment image along with user feedback on what to change on the reference garment. Two IGR tasks have been studied extensively: text-guided garment retrieval (TGR) and visually compatible garment retrieval (VCR). The user feedback for the former indicates what semantic attributes to change with the garment category preserved, while the category is the only thing to be changed explicitly for the latter, with an implicit requirement on style preservation. Despite the similarity between these two tasks and the practical need for an efficient system tackling both, they have never been unified and modeled jointly. In this paper, we propose a Unified Interactive Garment Retrieval (UIGR) framework to unify TGR and VCR. To this end, we first contribute a large-scale benchmark suited for both problems. We further propose a strong baseline architecture to integrate TGR and VCR in one model. Extensive experiments suggest that unifying two tasks in one framework is not only more efficient by requiring a single model only, it also leads to better performance. Code and datasets are available at https://github.com/BrandonHanx/CompFashion.

Junge Zhang, Feihu Zhang, Shaochen Kuang et al.

Labeling LiDAR point clouds for training autonomous driving is extremely expensive and difficult. LiDAR simulation aims at generating realistic LiDAR data with labels for training and verifying self-driving algorithms more efficiently. Recently, Neural Radiance Fields (NeRF) have been proposed for novel view synthesis using implicit reconstruction of 3D scenes. Inspired by this, we present NeRF-LIDAR, a novel LiDAR simulation method that leverages real-world information to generate realistic LIDAR point clouds. Different from existing LiDAR simulators, we use real images and point cloud data collected by self-driving cars to learn the 3D scene representation, point cloud generation and label rendering. We verify the effectiveness of our NeRF-LiDAR by training different 3D segmentation models on the generated LiDAR point clouds. It reveals that the trained models are able to achieve similar accuracy when compared with the same model trained on the real LiDAR data. Besides, the generated data is capable of boosting the accuracy through pre-training which helps reduce the requirements of the real labeled data.

Yulei Lu, Yawei Luo, Li Zhang et al.

A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them. Under this self-training paradigm, some competitive methods have sought to the latent-space information, which establishes the feature centroids (a.k.a prototypes) of the semantic classes and determines the pseudo label candidates by their distances from these centroids. In this paper, we argue that the latent space contains more information to be exploited thus taking one step further to capitalize on it. Firstly, instead of merely using the source-domain prototypes to determine the target pseudo labels as most of the traditional methods do, we bidirectionally produce the target-domain prototypes to degrade those source features which might be too hard or disturbed for the adaptation. Secondly, existing attempts simply model each category as a single and isotropic prototype while ignoring the variance of the feature distribution, which could lead to the confusion of similar categories. To cope with this issue, we propose to represent each category with multiple and anisotropic prototypes via Gaussian Mixture Model, in order to fit the de facto distribution of source domain and estimate the likelihood of target samples based on the probability density. We apply our method on GTA5->Cityscapes and Synthia->Cityscapes tasks and achieve 61.2 and 62.8 respectively in terms of mean IoU, substantially outperforming other competitive self-training methods. Noticeably, in some categories which severely suffer from the categorical confusion such as "truck" and "bus", our method achieves 56.4 and 68.8 respectively, which further demonstrates the effectiveness of our design.

Xiaopeng Sun, Weiqi Li, Zhenyu Zhang et al.

360° omnidirectional images have gained research attention due to their immersive and interactive experience, particularly in AR/VR applications. However, they suffer from lower angular resolution due to being captured by fisheye lenses with the same sensor size for capturing planar images. To solve the above issues, we propose a two-stage framework for 360° omnidirectional image superresolution. The first stage employs two branches: model A, which incorporates omnidirectional position-aware deformable blocks (OPDB) and Fourier upsampling, and model B, which adds a spatial frequency fusion module (SFF) to model A. Model A aims to enhance the feature extraction ability of 360° image positional information, while Model B further focuses on the high-frequency information of 360° images. The second stage performs same-resolution enhancement based on the structure of model A with a pixel unshuffle operation. In addition, we collected data from YouTube to improve the fitting ability of the transformer, and created pseudo low-resolution images using a degradation network. Our proposed method achieves superior performance and wins the NTIRE 2023 challenge of 360° omnidirectional image super-resolution.

Zhongli Fan, Li Zhang, Yuxuan Liu

We present an effective method for the matching of multimodal images. Accurate image matching is the basis of various applications, such as image registration and structure from motion. Conventional matching methods fail when handling noisy multimodal image pairs with severe scale change, rotation, and nonlinear intensity distortion (NID). Toward this need, we introduce an image pyramid strategy to tackle scale change. We put forward an accurate primary orientation estimation approach to reduce the effect of image rotation at any angle. We utilize multi-scale and multi-orientation image filtering results and a feature-to-template matching scheme to ensure effective and accurate matching under large NID. Integrating these improvements significantly increases noise, scale, rotation, and NID invariant capability. Our experimental results confirm the excellent ability to achieve high-quality matches across various multimodal images. The proposed method outperforms the mainstream multimodal image matching methods in qualitative and quantitative evaluations. Our implementation is available at https://github.com/Zhongli-Fan/NISR.

Jinhai Yang, Mengxi Guo, Shijie Zhao et al.

High-resolution (HR) images are usually downscaled to low-resolution (LR) ones for better display and afterward upscaled back to the original size to recover details. Recent work in image rescaling formulates downscaling and upscaling as a unified task and learns a bijective mapping between HR and LR via invertible networks. However, in real-world applications (e.g., social media), most images are compressed for transmission. Lossy compression will lead to irreversible information loss on LR images, hence damaging the inverse upscaling procedure and degrading the reconstruction accuracy. In this paper, we propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling. To tackle the distribution shift, we first develop an end-to-end asymmetric framework with two separate bijective mappings for high-quality and compressed LR images, respectively. Then, based on empirical analysis of this framework, we model the distribution of the lost information (including downscaling and compression) using isotropic Gaussian mixtures and propose the Enhanced Invertible Block to derive high-quality/compressed LR images in one forward pass. Besides, we design a set of losses to regularize the learned LR images and enhance the invertibility. Extensive experiments demonstrate the consistent improvements of SAIN across various image rescaling datasets in terms of both quantitative and qualitative evaluation under standard image compression formats (i.e., JPEG and WebP).

Shib Dasgupta, Andrew McCallum, Steffen Rendle et al.

The need to compactly and robustly represent item-attribute relations arises in many important tasks, such as faceted browsing and recommendation systems. A popular machine learning approach for this task denotes that an item has an attribute by a high dot-product between vectors for the item and attribute -- a representation that is not only dense, but also tends to correct noisy and incomplete data. While this method works well for queries retrieving items by a single attribute (such as \emph{movies that are comedies}), we find that vector embeddings do not so accurately support compositional queries (such as movies that are comedies and British but not romances). To address these set-theoretic compositions, this paper proposes to replace vectors with box embeddings, a region-based representation that can be thought of as learnable Venn diagrams. We introduce a new benchmark dataset for compositional queries, and present experiments and analysis providing insights into the behavior of both. We find that, while vector and box embeddings are equally suited to single attribute queries, for compositional queries box embeddings provide substantial advantages over vectors, particularly at the moderate and larger retrieval set sizes that are most useful for users' search and browsing.

Jiaqi Chen, Jiachen Lu, Xiatian Zhu et al.

We present Generative Semantic Segmentation (GSS), a generative learning approach for semantic segmentation. Uniquely, we cast semantic segmentation as an image-conditioned mask generation problem. This is achieved by replacing the conventional per-pixel discriminative learning with a latent prior learning process. Specifically, we model the variational posterior distribution of latent variables given the segmentation mask. To that end, the segmentation mask is expressed with a special type of image (dubbed as maskige). This posterior distribution allows to generate segmentation masks unconditionally. To achieve semantic segmentation on a given image, we further introduce a conditioning network. It is optimized by minimizing the divergence between the posterior distribution of maskige (i.e., segmentation masks) and the latent prior distribution of input training images. Extensive experiments on standard benchmarks show that our GSS can perform competitively to prior art alternatives in the standard semantic segmentation setting, whilst achieving a new state of the art in the more challenging cross-domain setting.

Jian Gao, Chun Gu, Youtian Lin et al.

In this paper, we present a novel differentiable point-based rendering framework to achieve photo-realistic relighting. To make the reconstructed scene relightable, we enhance vanilla 3D Gaussians by associating extra properties, including normal vectors, BRDF parameters, and incident lighting from various directions. From a collection of multi-view images, the 3D scene is optimized through 3D Gaussian Splatting while BRDF and lighting are decomposed by physically based differentiable rendering. To produce plausible shadow effects in photo-realistic relighting, we introduce an innovative point-based ray tracing with the bounding volume hierarchies for efficient visibility pre-computation. Extensive experiments demonstrate our improved BRDF estimation, novel view synthesis and relighting results compared to state-of-the-art approaches. The proposed framework showcases the potential to revolutionize the mesh-based graphics pipeline with a point-based pipeline enabling editing, tracing, and relighting.

Yao Sui, Guanghui Wang, Li Zhang

The paper focuses on a classical tracking model, subspace learning, grounded on the fact that the targets in successive frames are considered to reside in a low-dimensional subspace or manifold due to the similarity in their appearances. In recent years, a number of subspace trackers have been proposed and obtained impressive results. Inspired by the most recent results that the tracking performance is boosted by the subspace with discrimination capability learned over the recently localized targets and their immediately surrounding background, this work aims at solving such a problem: how to learn a robust low-dimensional subspace to accurately and discriminatively represent these target and background samples. To this end, a discriminative approach, which reliably separates the target from its surrounding background, is injected into the subspace learning by means of joint learning, achieving a dimension-adaptive subspace with superior discrimination capability. The proposed approach is extensively evaluated and compared with the state-of-the-art trackers on four popular tracking benchmarks. The experimental results demonstrate that the proposed tracker performs competitively against its counterparts. In particular, it achieves more than 9% performance increase compared with the state-of-the-art subspace trackers.

Li Zhang, Yan Ge, Jun Ma et al.

Cross-domain recommendation (CDR) can help customers find more satisfying items in different domains. Existing CDR models mainly use common users or mapping functions as bridges between domains but have very limited exploration in fully utilizing extra knowledge across domains. In this paper, we propose to incorporate the knowledge graph (KG) for CDR, which enables items in different domains to share knowledge. To this end, we first construct a new dataset AmazonKG4CDR from the Freebase KG and a subset (two domain pairs: movies-music, movie-book) of Amazon Review Data. This new dataset facilitates linking knowledge to bridge within- and cross-domain items for CDR. Then we propose a new framework, KG-aware Neural Collective Matrix Factorization (KG-NeuCMF), leveraging KG to enrich item representations. It first learns item embeddings by graph convolutional autoencoder to capture both domain-specific and domain-general knowledge from adjacent and higher-order neighbours in the KG. Then, we maximize the mutual information between item embeddings learned from the KG and user-item matrix to establish cross-domain relationships for better CDR. Finally, we conduct extensive experiments on the newly constructed dataset and demonstrate that our model significantly outperforms the best-performing baselines.

Li Zhang

This tutorial provides a comprehensive and in-depth view of the research on procedures, primarily in Natural Language Processing. A procedure is a sequence of steps intended to achieve some goal. Understanding procedures in natural language has a long history, with recent breakthroughs made possible by advances in technology. First, we discuss established approaches to collect procedures, by human annotation or extraction from web resources. Then, we examine different angles from which procedures can be reasoned about, as well as ways to represent them. Finally, we enumerate scenarios where procedural knowledge can be applied to the real world.

Ramtin Hosseini, Li Zhang, Bhanu Garg et al.

The integration of machine learning models in various real-world applications is becoming more prevalent to assist humans in their daily decision-making tasks as a result of recent advancements in this field. However, it has been discovered that there is a tradeoff between the accuracy and fairness of these decision-making tasks. In some cases, these AI systems can be unfair by exhibiting bias or discrimination against certain social groups, which can have severe consequences in real life. Inspired by one of the most well-known human learning skills called grouping, we address this issue by proposing a novel machine learning framework where the ML model learns to group a diverse set of problems into distinct subgroups to solve each subgroup using its specific sub-model. Our proposed framework involves three stages of learning, which are formulated as a three-level optimization problem: (i) learning to group problems into different subgroups; (ii) learning group-specific sub-models for problem-solving; and (iii) updating group assignments of training examples by minimizing the validation loss. These three learning stages are performed end-to-end in a joint manner using gradient descent. To improve fairness and accuracy, we develop an efficient optimization algorithm to solve this three-level optimization problem. To further reduce the risk of overfitting in small datasets, we incorporate domain adaptation techniques in the second stage of training. We further apply our method to neural architecture search. Extensive experiments on various datasets demonstrate our method's effectiveness and performance improvements in both fairness and accuracy. Our proposed Learning by Grouping can reduce overfitting and achieve state-of-the-art performances with fixed human-designed network architectures and searchable network architectures on various datasets.

He Yao, Yongjun Zhang, Huachun Jian et al.

The significance of background information is frequently overlooked in contemporary research concerning channel attention mechanisms. This study addresses the issue of suboptimal single-spectral nighttime pedestrian detection performance under low-light conditions by incorporating background information into the channel attention mechanism. Despite numerous studies focusing on the development of efficient channel attention mechanisms, the relevance of background information has been largely disregarded. By adopting a contrast learning approach, we reexamine channel attention with regard to pedestrian objects and background information for nighttime pedestrian detection, resulting in the proposed Fore-Background Contrast Attention (FBCA). FBCA possesses two primary attributes: (1) channel descriptors form remote dependencies with global spatial feature information; (2) the integration of background information enhances the distinction between channels concentrating on low-light pedestrian features and those focusing on background information. Consequently, the acquired channel descriptors exhibit a higher semantic level and spatial accuracy. Experimental outcomes demonstrate that FBCA significantly outperforms existing methods in single-spectral nighttime pedestrian detection, achieving state-of-the-art results on the NightOwls and TJU-DHD-pedestrian datasets. Furthermore, this methodology also yields performance improvements for the multispectral LLVIP dataset. These findings indicate that integrating background information into the channel attention mechanism effectively mitigates detector performance degradation caused by illumination factors in nighttime scenarios.

Zheyuan Zhou, Jiachen Lu, Yihan Zeng et al.

3D object detection from LiDAR point cloud is of critical importance for autonomous driving and robotics. While sequential point cloud has the potential to enhance 3D perception through temporal information, utilizing these temporal features effectively and efficiently remains a challenging problem. Based on the observation that the foreground information is sparsely distributed in LiDAR scenes, we believe sufficient knowledge can be provided by sparse format rather than dense maps. To this end, we propose to learn Significance-gUided Information for 3D Temporal detection (SUIT), which simplifies temporal information as sparse features for information fusion across frames. Specifically, we first introduce a significant sampling mechanism that extracts information-rich yet sparse features based on predicted object centroids. On top of that, we present an explicit geometric transformation learning technique, which learns the object-centric transformations among sparse features across frames. We evaluate our method on large-scale nuScenes and Waymo dataset, where our SUIT not only significantly reduces the memory and computation cost of temporal fusion, but also performs well over the state-of-the-art baselines.

Peirong Wang, Pengfei Li, Farzana Chowdhury et al.

In this paper, we first present a centralized traffic control model based on the emerging dynamic path flows. This new model in essence views the whole target network as one integral piece in which traffic propagates based on traffic flow dynamics, vehicle paths, and traffic control. In light of this centralized traffic control concept, most requirements for the existing traffic control coordination will be dropped in the optimal traffic control operations, such as the common cycle length or offsets. Instead, the optimal traffic control strategy across intersections will be highly adaptive over time to minimize the total travel time and it can also prevent any short-term traffic congestions according to the space-time characteristics of vehicle path flows. A mixed integer linear programming (MILP) formulation is then presented to model the propagations of path flows given a centralized traffic control strategy. Secondly, a new approximated Lagrangian decomposition framework is presented. Solving the proposed MILP model with the traditional Lagrangian decomposition approach faces the leveraging challenge between the problem tractability after decomposition and computing complexity. To address this issue, we propose an approximate Lagrangian decomposition framework in which the target problem is reformulated into an approximated problem by constructing its complicating attributes into the objective function instead of in constraints to reduce the computing complexity. The computing efficiency loss of the objective function can be mitigated via multiple advanced computing techniques. With the proposed approximated approach, the upper bound and tight lower bound can be obtained via two customized dynamic network loading models. In the end, one demonstrative and one real-world example are illustrated to show the validness, robustness, and scalability of the new approach.

Harsh Mehta, Steffen Rendle, Walid Krichene et al.

We present ALX, an open-source library for distributed matrix factorization using Alternating Least Squares, written in JAX. Our design allows for efficient use of the TPU architecture and scales well to matrix factorization problems of O(B) rows/columns by scaling the number of available TPU cores. In order to spur future research on large scale matrix factorization methods and to illustrate the scalability properties of our own implementation, we also built a real world web link prediction dataset called WebGraph. This dataset can be easily modeled as a matrix factorization problem. We created several variants of this dataset based on locality and sparsity properties of sub-graphs. The largest variant of WebGraph has around 365M nodes and training a single epoch finishes in about 20 minutes with 256 TPU cores. We include speed and performance numbers of ALX on all variants of WebGraph. Both the framework code and the dataset is open-sourced.

Zhihe Lu, Sen He, Xiatian Zhu et al.

A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier (separating foreground and background pixels). Most existing methods meta-learn all three model components for fast adaptation to a new class. However, given that as few as a single support set image is available, effective model adaption of all three components to the new class is extremely challenging. In this work we propose to simplify the meta-learning task by focusing solely on the simplest component, the classifier, whilst leaving the encoder and decoder to pre-training. We hypothesize that if we pre-train an off-the-shelf segmentation model over a set of diverse training classes with sufficient annotations, the encoder and decoder can capture rich discriminative features applicable for any unseen classes, rendering the subsequent meta-learning stage unnecessary. For the classifier meta-learning, we introduce a Classifier Weight Transformer (CWT) designed to dynamically adapt the supportset trained classifier's weights to each query image in an inductive way. Extensive experiments on two standard benchmarks show that despite its simplicity, our method outperforms the state-of-the-art alternatives, often by a large margin.Code is available on https://github.com/zhiheLu/CWT-for-FSS.

Xiangtai Li, Li Zhang, Guangliang Cheng et al.

Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherently limited to model such dependencies due to the naive structure in its building modules (\eg, local convolution kernel). While recent global aggregation methods are beneficial for long-range structure information modelling, they would oversmooth and bring noise to the regions containing fine details (\eg,~boundaries and small objects), which are very much cared for the semantic segmentation task. To alleviate this problem, we propose to explore the local context for making the aggregated long-range relationship being distributed more accurately in local regions. In particular, we design a novel local distribution module which models the affinity map between global and local relationship for each pixel adaptively. Integrating existing global aggregation modules, we show that our approach can be modularized as an end-to-end trainable block and easily plugged into existing semantic segmentation networks, giving rise to the \emph{GALD} networks. Despite its simplicity and versatility, our approach allows us to build new state of the art on major semantic segmentation benchmarks including Cityscapes, ADE20K, Pascal Context, Camvid and COCO-stuff. Code and trained models are released at \url{https://github.com/lxtGH/GALD-DGCNet} to foster further research.

Qing Lyu, Kumar Shridhar, Chaitanya Malaviya et al.

Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their proprietary nature and massive scale. In this work, we explore the potential of deriving confidence from the distribution of multiple randomly sampled model generations, via three measures of consistency. We perform an extensive evaluation across various open and closed-source models on nine reasoning datasets. Results show that consistency-based calibration methods outperform existing post-hoc approaches. Meanwhile, we find that factors such as intermediate explanations, model scaling, and larger sample sizes enhance calibration, while instruction-tuning makes calibration more difficult. Moreover, confidence scores obtained from consistency have the potential to enhance model performance. Finally, we offer practical guidance on choosing suitable consistency metrics for calibration, tailored to the characteristics of various LMs.

Xiaohan Yu, Li Zhang, Xin Zhao et al.

Large language models (LLM) have recently emerged as a powerful tool for a variety of natural language processing tasks, bringing a new surge of combining LLM with recommendation systems, termed as LLM-based RS. Current approaches generally fall into two main paradigms, the ID direct usage paradigm and the ID translation paradigm, noting their core weakness stems from lacking recommendation knowledge and uniqueness. To address this limitation, we propose a new paradigm, ID representation, which incorporates pre-trained ID embeddings into LLMs in a complementary manner. In this work, we present RA-Rec, an efficient ID representation alignment framework for LLM-based recommendation, which is compatible with multiple ID-based methods and LLM architectures. Specifically, we treat ID embeddings as soft prompts and design an innovative alignment module and an efficient tuning method with tailored data construction for alignment. Extensive experiments demonstrate RA-Rec substantially outperforms current state-of-the-art methods, achieving up to 3.0% absolute HitRate@100 improvements while utilizing less than 10x training data.

Zinuo You, Zijian Shi, Hongbo Bo et al.

Forecasting future stock trends remains challenging for academia and industry due to stochastic inter-stock dynamics and hierarchical intra-stock dynamics influencing stock prices. In recent years, graph neural networks have achieved remarkable performance in this problem by formulating multiple stocks as graph-structured data. However, most of these approaches rely on artificially defined factors to construct static stock graphs, which fail to capture the intrinsic interdependencies between stocks that rapidly evolve. In addition, these methods often ignore the hierarchical features of the stocks and lose distinctive information within. In this work, we propose a novel graph learning approach implemented without expert knowledge to address these issues. First, our approach automatically constructs dynamic stock graphs by entropy-driven edge generation from a signal processing perspective. Then, we further learn task-optimal dependencies between stocks via a generalized graph diffusion process on constructed stock graphs. Last, a decoupled representation learning scheme is adopted to capture distinctive hierarchical intra-stock features. Experimental results demonstrate substantial improvements over state-of-the-art baselines on real-world datasets. Moreover, the ablation study and sensitivity study further illustrate the effectiveness of the proposed method in modeling the time-evolving inter-stock and intra-stock dynamics.

Chunguang Zhao, Yilun Liu, Pufan Zeng et al.

Multilingual Instruction Fine-Tuning (IFT) is essential for enabling large language models (LLMs) to generalize effectively across diverse linguistic and cultural contexts. However, the scarcity of high-quality multilingual training data and corresponding building method remains a critical bottleneck. While data selection has shown promise in English settings, existing methods often fail to generalize across languages due to reliance on simplistic heuristics or language-specific assumptions. In this work, we introduce Multilingual Data Quality and Diversity (M-DaQ), a novel method for improving LLMs multilinguality, by selecting high-quality and semantically diverse multilingual IFT samples. We further conduct the first systematic investigation of the Superficial Alignment Hypothesis (SAH) in multilingual setting. Empirical results across 18 languages demonstrate that models fine-tuned with M-DaQ method achieve significant performance gains over vanilla baselines over 60% win rate. Human evaluations further validate these gains, highlighting the increment of cultural points in the response. We release the M-DaQ code to support future research.

Yingxue Pang, Shijie Zhao, Mengxi Guo et al.

Sharpening is a widely adopted video enhancement technique. However, uniform sharpening intensity ignores texture variations, degrading video quality. Sharpening also increases bitrate, and there's a lack of techniques to optimally allocate these additional bits across diverse regions. Thus, this paper proposes RPO-AdaSharp, an end-to-end region-adaptive video sharpening model for both perceptual enhancement and bitrate savings. We use the coding tree unit (CTU) partition mask as prior information to guide and constrain the allocation of increased bits. Experiments on benchmarks demonstrate the effectiveness of the proposed model qualitatively and quantitatively.

Yilun Liu, Chunguang Zhao, Xinhua Yang et al.

Despite doubts on data quality, instruction synthesis has been widely applied into instruction tuning (IT) of LLMs as an economic and rapid alternative. Recent endeavors focus on improving data quality for synthesized instruction pairs in English and have facilitated IT of English-centric LLMs. However, data quality issues in multilingual synthesized instruction pairs are even more severe, since the common synthesizing practice is to translate English synthesized data into other languages using machine translation (MT). Besides the known content errors in these English synthesized data, multilingual synthesized instruction data are further exposed to defects introduced by MT and face insufficient localization of the target languages, leading to cultural inequality in trained LLMs. In this paper, we propose MIDB, a Multilingual Instruction Data Booster to automatically address the quality issues in multilingual synthesized data. MIDB is trained on around 36.8k revision examples across 16 languages by human linguistic experts, thereby can boost the low-quality data by addressing content errors and MT defects, and improving localization in these synthesized data. Both automatic and human evaluation indicate that not only MIDB steadily improved instruction data quality in 16 languages, but also the instruction-following and cultural-understanding abilities of multilingual LLMs fine-tuned on MIDB-boosted data were significantly enhanced, suggesting an improved linguistic and cultural equality.

Jianyu Zhang, Li Zhang, Shijian Li

The visual understanding are often approached from 3 granular levels: image, patch and pixel. Visual Tokenization, trained by self-supervised reconstructive learning, compresses visual data by codebook in patch-level with marginal information loss, but the visual tokens does not have semantic meaning. Open Vocabulary semantic segmentation benefits from the evolving Vision-Language models (VLMs) with strong image zero-shot capability, but transferring image-level to pixel-level understanding remains an imminent challenge. In this paper, we treat segmentation as tokenizing pixels and study a united perceptual and semantic token compression for all granular understanding and consequently facilitate open vocabulary semantic segmentation. Referring to the cognitive process of pretrained VLM where the low-level features are progressively composed to high-level semantics, we propose Feature Pyramid Tokenization (PAT) to cluster and represent multi-resolution feature by learnable codebooks and then decode them by joint learning pixel reconstruction and semantic segmentation. We design loosely coupled pixel and semantic learning branches. The pixel branch simulates bottom-up composition and top-down visualization of codebook tokens, while the semantic branch collectively fuse hierarchical codebooks as auxiliary segmentation guidance. Our experiments show that PAT enhances the semantic intuition of VLM feature pyramid, improves performance over the baseline segmentation model and achieves competitive performance on open vocabulary semantic segmentation benchmark. Our model is parameter-efficient for VLM integration and flexible for the independent tokenization. We hope to give inspiration not only on improving segmentation but also on semantic visual token utilization.

Hengyuan Ma, Yang Qi, Li Zhang et al.

Building robust, interpretable, and secure AI system requires quantifying and representing uncertainty under a probabilistic perspective to mimic human cognitive abilities. However, probabilistic computation presents significant challenges for most conventional artificial neural network, as they are essentially implemented in a deterministic manner. In this paper, we develop an efficient probabilistic computation framework by truncating the probabilistic representation of neural activation up to its mean and covariance and construct a moment neural network that encapsulates the nonlinear coupling between the mean and covariance of the underlying stochastic network. We reveal that when only the mean but not the covariance is supervised during gradient-based learning, the unsupervised covariance spontaneously emerges from its nonlinear coupling with the mean and faithfully captures the uncertainty associated with model predictions. Our findings highlight the inherent simplicity of probabilistic computation by seamlessly incorporating uncertainty into model prediction, paving the way for integrating it into large-scale AI systems.

Ming Cheng, Haoyu Ma, Qiufang Ma et al.

Multi-stage strategies are frequently employed in image restoration tasks. While transformer-based methods have exhibited high efficiency in single-image super-resolution tasks, they have not yet shown significant advantages over CNN-based methods in stereo super-resolution tasks. This can be attributed to two key factors: first, current single-image super-resolution transformers are unable to leverage the complementary stereo information during the process; second, the performance of transformers is typically reliant on sufficient data, which is absent in common stereo-image super-resolution algorithms. To address these issues, we propose a Hybrid Transformer and CNN Attention Network (HTCAN), which utilizes a transformer-based network for single-image enhancement and a CNN-based network for stereo information fusion. Furthermore, we employ a multi-patch training strategy and larger window sizes to activate more input pixels for super-resolution. We also revisit other advanced techniques, such as data augmentation, data ensemble, and model ensemble to reduce overfitting and data bias. Finally, our approach achieved a score of 23.90dB and emerged as the winner in Track 1 of the NTIRE 2023 Stereo Image Super-Resolution Challenge.

Xiaoliang Zhou, Dongyang Wu, Zitong You et al.

Naive Bayes(NB) is one of the essential algorithms in data mining. However, it is rarely used in reality because of the attribute independent assumption. Researchers have proposed many improved NB methods to alleviate this assumption. Among these methods, due to high efficiency and easy implementation, the filter attribute weighted NB methods receive great attentions. However, there still exists several challenges, such as the poor representation ability for single index and the fusion problem of two indexes. To overcome above challenges, we propose a general framework for Adaptive Two-index Fusion attribute weighted NB(ATFNB). Two types of data description category are used to represent the correlation between classes and attributes, intercorrelation between attributes and attributes, respectively. ATFNB can select any one index from each category. Then, we introduce a switching factor \{beta} to fuse two indexes, which can adaptively adjust the optimal ratio of the two index on various datasets. And a quick algorithm is proposed to infer the optimal interval of switching factor \{beta}. Finally, the weight of each attribute is calculated using the optimal value \{beta} and is integrated into NB classifier to improve the accuracy. The experimental results on 50 benchmark datasets and a Flavia dataset show that ATFNB outperforms the basic NB and state-of-the-art filter weighted NB models. In addition, the ATFNB framework can improve the existing two-index NB model by introducing the adaptive switching factor \{beta}. Auxiliary experimental results demonstrate the improved model significantly increases the accuracy compared to the original model without the adaptive switching factor \{beta}.

Bhanu Garg, Li Zhang, Pradyumna Sridhara et al.

Learning from one's mistakes is an effective human learning technique where the learners focus more on the topics where mistakes were made, so as to deepen their understanding. In this paper, we investigate if this human learning strategy can be applied in machine learning. We propose a novel machine learning method called Learning From Mistakes (LFM), wherein the learner improves its ability to learn by focusing more on the mistakes during revision. We formulate LFM as a three-stage optimization problem: 1) learner learns; 2) learner re-learns focusing on the mistakes, and; 3) learner validates its learning. We develop an efficient algorithm to solve the LFM problem. We apply the LFM framework to neural architecture search on CIFAR-10, CIFAR-100, and Imagenet. Experimental results strongly demonstrate the effectiveness of our model.

Steffen Rendle, Walid Krichene, Li Zhang et al.

iALS is a popular algorithm for learning matrix factorization models from implicit feedback with alternating least squares. This algorithm was invented over a decade ago but still shows competitive quality compared to recent approaches like VAE, EASE, SLIM, or NCF. Due to a computational trick that avoids negative sampling, iALS is very efficient especially for large item catalogues. However, iALS does not scale well with large embedding dimensions, d, due to its cubic runtime dependency on d. Coordinate descent variations, iCD, have been proposed to lower the complexity to quadratic in d. In this work, we show that iCD approaches are not well suited for modern processors and can be an order of magnitude slower than a careful iALS implementation for small to mid scale embedding sizes (d ~ 100) and only perform better than iALS on large embeddings d ~ 1000. We propose a new solver iALS++ that combines the advantages of iALS in terms of vector processing with a low computational complexity as in iCD. iALS++ is an order of magnitude faster than iCD both for small and large embedding dimensions. It can solve benchmark problems like Movielens 20M or Million Song Dataset even for 1000 dimensional embedding vectors in a few minutes.

Steffen Rendle, Walid Krichene, Li Zhang et al.

Matrix factorization learned by implicit alternating least squares (iALS) is a popular baseline in recommender system research publications. iALS is known to be one of the most computationally efficient and scalable collaborative filtering methods. However, recent studies suggest that its prediction quality is not competitive with the current state of the art, in particular autoencoders and other item-based collaborative filtering methods. In this work, we revisit the iALS algorithm and present a bag of tricks that we found useful when applying iALS. We revisit four well-studied benchmarks where iALS was reported to perform poorly and show that with proper tuning, iALS is highly competitive and outperforms any method on at least half of the comparisons. We hope that these high quality results together with iALS's known scalability spark new interest in applying and further improving this decade old technique.

Li Zhang, Qing Wang, Lei Xie

The use of channel-wise attention in CNN based speaker representation networks has achieved remarkable performance in speaker verification (SV). But these approaches do simple averaging on time and frequency feature maps before channel-wise attention learning and ignore the essential mutual interaction among temporal, channel as well as frequency scales. To address this problem, we propose the Duality Temporal-Channel-Frequency (DTCF) attention to re-calibrate the channel-wise features with aggregation of global context on temporal and frequency dimensions. Specifically, the duality attention - time-channel (T-C) attention as well as frequency-channel (F-C) attention - aims to focus on salient regions along the T-C and F-C feature maps that may have more considerable impact on the global context, leading to more discriminative speaker representations. We evaluate the effectiveness of the proposed DTCF attention on the CN-Celeb and VoxCeleb datasets. On the CN-Celeb evaluation set, the EER/minDCF of ResNet34-DTCF are reduced by 0.63%/0.0718 compared with those of ResNet34-SE. On VoxCeleb1-O, VoxCeleb1-E and VoxCeleb1-H evaluation sets, the EER/minDCF of ResNet34-DTCF achieve 0.36%/0.0263, 0.39%/0.0382 and 0.74%/0.0753 reductions compared with those of ResNet34-SE.

Hexin Dong, Fei Yu, Jie Zhao et al.

This paper proposes an unsupervised cross-modality domain adaptation approach based on pixel alignment and self-training. Pixel alignment transfers ceT1 scans to hrT2 modality, helping to reduce domain shift in the training segmentation model. Self-training adapts the decision boundary of the segmentation network to fit the distribution of hrT2 scans. Experiment results show that PAST has outperformed the non-UDA baseline significantly, and it received rank-2 on CrossMoDA validation phase Leaderboard with a mean Dice score of 0.8395.

Qing Lyu, Li Zhang, Chris Callison-Burch

The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a sequence of steps to accomplish a given goal. We pilot our task on the first multilingual script learning dataset supporting 18 languages collected from wikiHow, a website containing half a million how-to articles. For baselines, we consider both a generation-based approach using a language model and a retrieval-based approach by first retrieving the relevant steps from a large candidate pool and then ordering them. We show that our task is practical, feasible but challenging for state-of-the-art Transformer models, and that our methods can be readily deployed for various other datasets and domains with decent zero-shot performance.

Li Zhang, Qing Wang, Kong Aik Lee et al.

In far-field speaker verification, the performance of speaker embeddings is susceptible to degradation when there is a mismatch between the conditions of enrollment and test speech. To solve this problem, we propose the feature-level and instance-level transfer learning in the teacher-student framework to learn a domain-invariant embedding space. For the feature-level knowledge transfer, we develop the contrastive loss to transfer knowledge from teacher model to student model, which can not only decrease the intra-class distance, but also enlarge the inter-class distance. Moreover, we propose the instance-level pairwise distance transfer method to force the student model to preserve pairwise instances distance from the well optimized embedding space of the teacher model. On FFSVC 2020 evaluation set, our EER on Full-eval trials is relatively reduced by 13.9% compared with the fusion system result on Partial-eval trials of Task2. On Task1, compared with the winner's DenseNet result on Partial-eval trials, our minDCF on Full-eval trials is relatively reduced by 6.3%. On Task3, the EER and minDCF of our proposed method on Full-eval trials are very close to the result of the fusion system on Partial-eval trials. Our results also outperform other competitive domain adaptation methods.

ZiFan Chen, Xin Qin, Chao Yang et al.

The existing human pose estimation methods are confronted with inaccurate long-distance regression or high computational cost due to the complex learning objectives. This work proposes a novel deep learning framework for human pose estimation called composite localization to divide the complex learning objective into two simpler ones: a sparse heatmap to find the keypoint's approximate location and two short-distance offsetmaps to obtain its final precise coordinates. To realize the framework, we construct two types of composite localization networks: CLNet-ResNet and CLNet-Hourglass. We evaluate the networks on three benchmark datasets, including the Leeds Sports Pose dataset, the MPII Human Pose dataset, and the COCO keypoints detection dataset. The experimental results show that our CLNet-ResNet50 outperforms SimpleBaseline by 1.14% with about 1/2 GFLOPs. Our CLNet-Hourglass outperforms the original stacked-hourglass by 4.45% on COCO.

Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov et al.

In this work, we present BasisNet which combines recent advancements in efficient neural network architectures, conditional computation, and early termination in a simple new form. Our approach incorporates a lightweight model to preview the input and generate input-dependent combination coefficients, which later controls the synthesis of a more accurate specialist model to make final prediction. The two-stage model synthesis strategy can be applied to any network architectures and both stages are jointly trained. We also show that proper training recipes are critical for increasing generalizability for such high capacity neural networks. On ImageNet classification benchmark, our BasisNet with MobileNets as backbone demonstrated clear advantage on accuracy-efficiency trade-off over several strong baselines. Specifically, BasisNet-MobileNetV3 obtained 80.3% top-1 accuracy with only 290M Multiply-Add operations, halving the computational cost of previous state-of-the-art without sacrificing accuracy. With early termination, the average cost can be further reduced to 198M MAdds while maintaining accuracy of 80.0% on ImageNet.

Yuxuan Chen, Li Zhang, Shijian Li et al.

Optimization of deep learning algorithms to approach Nash Equilibrium remains a significant problem in imperfect information games, e.g. StarCraft and poker. Neural Fictitious Self-Play (NFSP) has provided an effective way to learn approximate Nash Equilibrium without prior domain knowledge in imperfect information games. However, optimality gap was left as an optimization problem of NFSP and by solving the problem, the performance of NFSP could be improved. In this study, focusing on the optimality gap of NFSP, we have proposed a new method replacing NFSP's best response computation with regret matching method. The new algorithm can make the optimality gap converge to zero as it iterates, thus converge faster than original NFSP. We have conduct experiments on three typical environments of perfect-information games and imperfect information games in OpenSpiel and all showed that our new algorithm performances better than original NFSP.

Feifei Shao, Yawei Luo, Li Zhang et al.

The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels. Previous works endeavor to perceive the interval objects from the small and sparse discriminative attention map, yet ignoring the co-occurrence confounder (e.g., bird and sky), which makes the model inspection (e.g., CAM) hard to distinguish between the object and context. In this paper, we make an early attempt to tackle this challenge via causal intervention (CI). Our proposed method, dubbed CI-CAM, explores the causalities among images, contexts, and categories to eliminate the biased co-occurrence in the class activation maps thus improving the accuracy of object localization. Extensive experiments on several benchmarks demonstrate the effectiveness of CI-CAM in learning the clear object boundaries from confounding contexts. Particularly, in CUB-200-2011 which severely suffers from the co-occurrence confounder, CI-CAM significantly outperforms the traditional CAM-based baseline (58.39% vs 52.4% in top-1 localization accuracy). While in more general scenarios such as ImageNet, CI-CAM can also perform on par with the state of the arts.

Jingyong Hou, Li Zhang, Yihui Fu et al.

This paper describes the system developed by the NPU team for the 2020 personalized voice trigger challenge. Our submitted system consists of two independently trained subsystems: a small footprint keyword spotting (KWS) system and a speaker verification (SV) system. For the KWS system, a multi-scale dilated temporal convolutional (MDTC) network is proposed to detect wake-up word (WuW). For SV system, Write something here. The KWS predicts posterior probabilities of whether an audio utterance contains WuW and estimates the location of WuW at the same time. When the posterior probability ofWuW reaches a predefined threshold, the identity information of triggered segment is determined by the SV system. On evaluation dataset, our submitted system obtains detection costs of 0.081and 0.091 in close talking and far-field tasks, respectively.

Xiatian Zhu, Antoine Toisoul, Juan-Manuel Perez-Rua et al.

Few-shot action recognition aims to recognize action classes with few training samples. Most existing methods adopt a meta-learning approach with episodic training. In each episode, the few samples in a meta-training task are split into support and query sets. The former is used to build a classifier, which is then evaluated on the latter using a query-centered loss for model updating. There are however two major limitations: lack of data efficiency due to the query-centered only loss design and inability to deal with the support set outlying samples and inter-class distribution overlapping problems. In this paper, we overcome both limitations by proposing a new Prototype-centered Attentive Learning (PAL) model composed of two novel components. First, a prototype-centered contrastive learning loss is introduced to complement the conventional query-centered learning objective, in order to make full use of the limited training samples in each episode. Second, PAL further integrates a hybrid attentive learning mechanism that can minimize the negative impacts of outliers and promote class separation. Extensive experiments on four standard few-shot action benchmarks show that our method clearly outperforms previous state-of-the-art methods, with the improvement particularly significant (10+\%) on the most challenging fine-grained action recognition benchmark.

Yan Ge, Jun Ma, Li Zhang et al.

Higher-order proximity (HOP) is fundamental for most network embedding methods due to its significant effects on the quality of node embedding and performance on downstream network analysis tasks. Most existing HOP definitions are based on either homophily to place close and highly interconnected nodes tightly in embedding space or heterophily to place distant but structurally similar nodes together after embedding. In real-world networks, both can co-exist, and thus considering only one could limit the prediction performance and interpretability. However, there is no general and universal solution that takes both into consideration. In this paper, we propose such a simple yet powerful framework called homophily and heterophliy preserving network transformation (H2NT) to capture HOP that flexibly unifies homophily and heterophily. Specifically, H2NT utilises motif representations to transform a network into a new network with a hybrid assumption via micro-level and macro-level walk paths. H2NT can be used as an enhancer to be integrated with any existing network embedding methods without requiring any changes to latter methods. Because H2NT can sparsify networks with motif structures, it can also improve the computational efficiency of existing network embedding methods when integrated. We conduct experiments on node classification, structural role classification and motif prediction to show the superior prediction performance and computational efficiency over state-of-the-art methods. In particular, DeepWalk-based H2 NT achieves 24% improvement in terms of precision on motif prediction, while reducing 46% computational time compared to the original DeepWalk.

Mengmeng Xu, Juan-Manuel Perez-Rua, Victor Escorcia et al.

Many video analysis tasks require temporal localization thus detection of content changes. However, most existing models developed for these tasks are pre-trained on general video action classification tasks. This is because large scale annotation of temporal boundaries in untrimmed videos is expensive. Therefore no suitable datasets exist for temporal boundary-sensitive pre-training. In this paper for the first time, we investigate model pre-training for temporal localization by introducing a novel boundary-sensitive pretext (BSP) task. Instead of relying on costly manual annotations of temporal boundaries, we propose to synthesize temporal boundaries in existing video action classification datasets. With the synthesized boundaries, BSP can be simply conducted via classifying the boundary types. This enables the learning of video representations that are much more transferable to downstream temporal localization tasks. Extensive experiments show that the proposed BSP is superior and complementary to the existing action classification based pre-training counterpart, and achieves new state-of-the-art performance on several temporal localization tasks.

Yuqian Fu, Li Zhang, Junke Wang et al.

Humans can easily recognize actions with only a few examples given, while the existing video recognition models still heavily rely on the large-scale labeled data inputs. This observation has motivated an increasing interest in few-shot video action recognition, which aims at learning new actions with only very few labeled samples. In this paper, we propose a depth guided Adaptive Meta-Fusion Network for few-shot video recognition which is termed as AMeFu-Net. Concretely, we tackle the few-shot recognition problem from three aspects: firstly, we alleviate this extremely data-scarce problem by introducing depth information as a carrier of the scene, which will bring extra visual information to our model; secondly, we fuse the representation of original RGB clips with multiple non-strictly corresponding depth clips sampled by our temporal asynchronization augmentation mechanism, which synthesizes new instances at feature-level; thirdly, a novel Depth Guided Adaptive Instance Normalization (DGAdaIN) fusion module is proposed to fuse the two-stream modalities efficiently. Additionally, to better mimic the few-shot recognition process, our model is trained in the meta-learning way. Extensive experiments on several action recognition benchmarks demonstrate the effectiveness of our model.

Yan Zhang, Zhao Zhang, Yang Wang et al.

Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces. In this paper, we technically propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net, for learning the hierarchical coupled representations. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Specifically, DS2CF-Net designs a deep coupled factorization architecture using multi-layers of linear transformations, which coupled updates the bases and new representations in each layer. To improve the discriminating ability of learned deep representations and deep coefficients, our network clearly considers enriching the supervised prior by the joint deep coefficients-regularized label prediction, and incorporates enriched prior information as additional label and structure constraints. The label constraint can enable the samples of the same label to have the same coordinate in the new feature space, while the structure constraint forces the coefficient matrices in each layer to be block-diagonal so that the enhanced prior using the self-expressive label propagation are more accurate. Our network also integrates the adaptive dual-graph learning to retain the local manifold structures of both the data manifold and feature manifold by minimizing the reconstruction errors in each layer. Extensive experiments on several real databases demonstrate that our DS2CF-Net can obtain state-of-the-art performance for representation learning and clustering.

Sayali Kulkarni, Shailee Jain, Mohammad Javad Hosseini et al.

We present a multi-level geocoding model (MLG) that learns to associate texts to geographic locations. The Earth's surface is represented using space-filling curves that decompose the sphere into a hierarchy of similarly sized, non-overlapping cells. MLG balances generalization and accuracy by combining losses across multiple levels and predicting cells at each level simultaneously. Without using any dataset-specific tuning, we show that MLG obtains state-of-the-art results for toponym resolution on three English datasets. Furthermore, it obtains large gains without any knowledge base metadata, demonstrating that it can effectively learn the connection between text spans and coordinates - and thus can be extended to toponymns not present in knowledge bases.

Li Zhang, Jian Wu, Lei Xie

This paper describes the NPU system submitted to Interspeech 2020 Far-Field Speaker Verification Challenge (FFSVC). We particularly focus on far-field text-dependent SV from single (task1) and multiple microphone arrays (task3). The major challenges in such scenarios are short utterance and cross-channel and distance mismatch for enrollment and test. With the belief that better speaker embedding can alleviate the effects from short utterance, we introduce a new speaker embedding architecture - ResNet-BAM, which integrates a bottleneck attention module with ResNet as a simple and efficient way to further improve the representation power of ResNet. This contribution brings up to 1% EER reduction. We further address the mismatch problem in three directions. First, domain adversarial training, which aims to learn domain-invariant features, can yield to 0.8% EER reduction. Second, front-end signal processing, including WPE and beamforming, has no obvious contribution, but together with data selection and domain adversarial training, can further contribute to 0.5% EER reduction. Finally, data augmentation, which works with a specifically-designed data selection strategy, can lead to 2% EER reduction. Together with the above contributions, in the middle challenge results, our single submission system (without multi-system fusion) achieves the first and second place on task 1 and task 3, respectively.