Ruirui Li

Tao Chen, Ruirui Li, Jiafeng Fu et al. · deepmind

Object detection on VHR remote sensing images plays a vital role in applications such as urban planning, land resource management, and rescue missions. The large-scale variation of the remote-sensing targets is one of the main challenges in VHR remote-sensing object detection. Existing methods improve the detection accuracy of high-resolution remote sensing objects by improving the structure of feature pyramids and adopting different attention modules. However, for small targets, there still be seriously missed detections due to the loss of key detail features. There is still room for improvement in the way of multiscale feature fusion and balance. To address this issue, this paper proposes two novel modules: Guided Attention and Tucker Bilinear Attention, which are applied to the stages of early fusion and late fusion respectively. The former can effectively retain clean key detail features, and the latter can better balance features through semantic-level correlation mining. Based on two modules, we build a new multi-scale remote sensing object detection framework. No bells and whistles. The proposed method largely improves the average precisions of small objects and achieves the highest mean average precisions compared with 9 state-of-the-art methods on DOTA, DIOR, and NWPU VHR-10.Code and models are available at https://github.com/Shinichict/GTNet.

Bowen Jin, Hansi Zeng, Guoyin Wang et al.

Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs. Previous studies typically adopt a two-stage pipeline to learn semantic IDs by first procuring embeddings using off-the-shelf text encoders and then deriving IDs based on the embeddings. However, each step introduces potential information loss, and there is usually an inherent mismatch between the distribution of embeddings within the latent space produced by text encoders and the anticipated distribution required for semantic indexing. It is non-trivial to design a method that can learn the document's semantic representations and its hierarchical structure simultaneously, given that semantic IDs are discrete and sequentially structured, and the semantic supervision is deficient. In this paper, we introduce LMIndexer, a self-supervised framework to learn semantic IDs with a generative language model. We tackle the challenge of sequential discrete ID by introducing a semantic indexer capable of generating neural sequential discrete representations with progressive training and contrastive learning. In response to the semantic supervision deficiency, we propose to train the model with a self-supervised document reconstruction objective. We show the high quality of the learned IDs and demonstrate their effectiveness on three tasks including recommendation, product search, and document retrieval on five datasets from various domains. Code is available at https://github.com/PeterGriffinJin/LMIndexer.

Wei Jin, Haitao Mao, Zheng Li et al.

Modeling customer shopping intentions is a crucial task for e-commerce, as it directly impacts user experience and engagement. Thus, accurately understanding customer preferences is essential for providing personalized recommendations. Session-based recommendation, which utilizes customer session data to predict their next interaction, has become increasingly popular. However, existing session datasets have limitations in terms of item attributes, user diversity, and dataset scale. As a result, they cannot comprehensively capture the spectrum of user behaviors and preferences. To bridge this gap, we present the Amazon Multilingual Multi-locale Shopping Session Dataset, namely Amazon-M2. It is the first multilingual dataset consisting of millions of user sessions from six different locales, where the major languages of products are English, German, Japanese, French, Italian, and Spanish. Remarkably, the dataset can help us enhance personalization and understanding of user preferences, which can benefit various existing tasks as well as enable new tasks. To test the potential of the dataset, we introduce three tasks in this work: (1) next-product recommendation, (2) next-product recommendation with domain shifts, and (3) next-product title generation. With the above tasks, we benchmark a range of algorithms on our proposed dataset, drawing new insights for further research and practice. In addition, based on the proposed dataset and tasks, we hosted a competition in the KDD CUP 2023 and have attracted thousands of users and submissions. The winning solutions and the associated workshop can be accessed at our website https://kddcup23.github.io/.

Jiarun Liu, Daguang Jiang, Yukun Yang et al.

Deep learning has made many remarkable achievements in many fields but suffers from noisy labels in datasets. The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label by mutual-information between dual-network. However, the dual network always tends to convergent which would weaken the dual-network mechanism to resist the noisy labels. In this paper, we proposed a noise-tolerant framework named MLC in an end-to-end manner. It adjusts the dual-network with divergent regularization to ensure the effectiveness of the mechanism. In addition, we correct the label distribution according to the agreement between dual-networks. The proposed method can utilize the noisy data to improve the accuracy, generalization, and robustness of the network. We test the proposed method on the simulate noisy dataset MNIST, CIFAR-10, and the real-world noisy dataset Clothing1M. The experimental result shows that our method outperforms the previous state-of-the-art method. Besides, our method is network-free thus it is applicable to many tasks. Our code can be found at https://github.com/JiarunLiu/MLC.

Kewei Cheng, Jingfeng Yang, Haoming Jiang et al.

Reasoning encompasses two typical types: deductive reasoning and inductive reasoning. Despite extensive research into the reasoning capabilities of Large Language Models (LLMs), most studies have failed to rigorously differentiate between inductive and deductive reasoning, leading to a blending of the two. This raises an essential question: In LLM reasoning, which poses a greater challenge - deductive or inductive reasoning? While the deductive reasoning capabilities of LLMs, (i.e. their capacity to follow instructions in reasoning tasks), have received considerable attention, their abilities in true inductive reasoning remain largely unexplored. To investigate into the true inductive reasoning capabilities of LLMs, we propose a novel framework, SolverLearner. This framework enables LLMs to learn the underlying function (i.e., $y = f_w(x)$), that maps input data points $(x)$ to their corresponding output values $(y)$, using only in-context examples. By focusing on inductive reasoning and separating it from LLM-based deductive reasoning, we can isolate and investigate inductive reasoning of LLMs in its pure form via SolverLearner. Our observations reveal that LLMs demonstrate remarkable inductive reasoning capabilities through SolverLearner, achieving near-perfect performance with ACC of 1 in most cases. Surprisingly, despite their strong inductive reasoning abilities, LLMs tend to relatively lack deductive reasoning capabilities, particularly in tasks involving ``counterfactual'' reasoning.

Bowen Jin, Chulin Xie, Jiawei Zhang et al.

Large language models (LLMs), while exhibiting exceptional performance, suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora to alleviate the issue. However, in many domains, texts are interconnected (e.g., academic papers in a bibliographic graph are linked by citations and co-authorships) which form a (text-attributed) graph. The knowledge in such graphs is encoded not only in single texts/nodes but also in their associated connections. To facilitate the research of augmenting LLMs with graphs, we manually construct a Graph Reasoning Benchmark dataset called GRBench, containing 1,740 questions that can be answered with the knowledge from 10 domain graphs. Then, we propose a simple and effective framework called Graph Chain-of-thought (Graph-CoT) to augment LLMs with graphs by encouraging LLMs to reason on the graph iteratively. Each Graph-CoT iteration consists of three sub-steps: LLM reasoning, LLM-graph interaction, and graph execution. We conduct systematic experiments with three LLM backbones on GRBench, where Graph-CoT outperforms the baselines consistently. The code is available at https://github.com/PeterGriffinJin/Graph-CoT.

Zijun Xue, Ruirui Li, Mingda Li

Conversational artificial intelligence (AI) is becoming an increasingly popular topic among industry and academia. With the fast development of neural network-based models, a lot of neural-based conversational AI system are developed. We will provide a brief review of the recent progress in the Conversational AI, including the commonly adopted techniques, notable works, famous competitions from academia and industry and widely used datasets.

Jiarun Liu, Ruirui Li, Chuan Sun

With the development of deep learning, medical image classification has been significantly improved. However, deep learning requires massive data with labels. While labeling the samples by human experts is expensive and time-consuming, collecting labels from crowd-sourcing suffers from the noises which may degenerate the accuracy of classifiers. Therefore, approaches that can effectively handle label noises are highly desired. Unfortunately, recent progress on handling label noise in deep learning has gone largely unnoticed by the medical image. To fill the gap, this paper proposes a noise-tolerant medical image classification framework named Co-Correcting, which significantly improves classification accuracy and obtains more accurate labels through dual-network mutual learning, label probability estimation, and curriculum label correcting. On two representative medical image datasets and the MNIST dataset, we test six latest Learning-with-Noisy-Labels methods and conduct comparative studies. The experiments show that Co-Correcting achieves the best accuracy and generalization under different noise ratios in various tasks. Our project can be found at: https://github.com/JiarunLiu/Co-Correcting.

Wei Hu, Yangyu Huang, Fan Zhang et al.

Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR). However, tremendous scale of datasets inevitably lead to noisy data, which obviously reduce the performance of the trained CNN models. Kicking out wrong labels from large-scale FR datasets is still very expensive, although some cleaning approaches are proposed. According to the analysis of the whole process of training CNN models supervised by angular margin based loss(AM-Loss) functions, we find that the $θ$ distribution of training samples implicitly reflects their probability of being clean. Thus, we propose a novel training paradigm that employs the idea of weighting samples based on the above probability. Without any prior knowledge of noise, we can train high performance CNN models with large-scale FR datasets. Experiments demonstrate the effectiveness of our training paradigm. The codes are available at https://github.com/huangyangyu/NoiseFace.

Wei Hu, Yangyu Huang, Fan Zhang et al.

Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years. Almost all CNNs in FR are trained on the carefully labeled datasets containing plenty of identities. However, such high-quality datasets are very expensive to collect, which restricts many researchers to achieve state-of-the-art performance. In this paper, we propose a framework, called SeqFace, for learning discriminative face features. Besides a traditional identity training dataset, the designed SeqFace can train CNNs by using an additional dataset which includes a large number of face sequences collected from videos. Moreover, the label smoothing regularization (LSR) and a new proposed discriminative sequence agent (DSA) loss are employed to enhance discrimination power of deep face features via making full use of the sequence data. Our method achieves excellent performance on Labeled Faces in the Wild (LFW), YouTube Faces (YTF), only with a single ResNet. The code and models are publicly available on-line (https://github.com/huangyangyu/SeqFace).

Tianxin Wei, Bowen Jin, Ruirui Li et al.

Developing a universal model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration. Our daily choices, especially in domains like fashion and retail, are substantially shaped by multi-modal data, such as pictures and textual descriptions. These modalities not only offer intuitive guidance but also cater to personalized user preferences. However, the predominant personalization approaches mainly focus on the ID or text-based recommendation problem, failing to comprehend the information spanning various tasks or modalities. In this paper, our goal is to establish a Unified paradigm for Multi-modal Personalization systems (UniMP), which effectively leverages multi-modal data while eliminating the complexities associated with task- and modality-specific customization. We argue that the advancements in foundational generative modeling have provided the flexibility and effectiveness necessary to achieve the objective. In light of this, we develop a generic and extensible personalization generative framework, that can handle a wide range of personalized needs including item recommendation, product search, preference prediction, explanation generation, and further user-guided image generation. Our methodology enhances the capabilities of foundational language models for personalized tasks by seamlessly ingesting interleaved cross-modal user history information, ensuring a more precise and customized experience for users. To train and evaluate the proposed multi-modal personalized tasks, we also introduce a novel and comprehensive benchmark covering a variety of user requirements. Our experiments on the real-world benchmark showcase the model's potential, outperforming competitive methods specialized for each task.

Haoyu Wang, Ruirui Li, Haoming Jiang et al.

Retrieval-augmented Large Language Models (LLMs) offer substantial benefits in enhancing performance across knowledge-intensive scenarios. However, these methods often face challenges with complex inputs and encounter difficulties due to noisy knowledge retrieval, notably hindering model effectiveness. To address this issue, we introduce BlendFilter, a novel approach that elevates retrieval-augmented LLMs by integrating query generation blending with knowledge filtering. BlendFilter proposes the blending process through its query generation method, which integrates both external and internal knowledge augmentation with the original query, ensuring comprehensive information gathering. Additionally, our distinctive knowledge filtering module capitalizes on the intrinsic capabilities of the LLM, effectively eliminating extraneous data. We conduct extensive experiments on three open-domain question answering benchmarks, and the findings clearly indicate that our innovative BlendFilter surpasses state-of-the-art baselines significantly.

Tianci Liu, Ruirui Li, Yunzhe Qi et al.

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing methods designed to update certain knowledge in LLMs without changing unrelated others. To make selective edits, previous efforts often sought to update a small amount of parameters in some specific layer(s) of a LLM. Nonetheless, in challenging scenarios, they still fall short in making successful edits while preserving knowledge irrelevant to the updates simultaneously, resulting in a notable editing-locality trade-off. In this work, we question if the trade-offs are caused by the fact that parameter-based updates have a global effect, i.e., edited parameters affect all inputs indiscriminately. In light of this, we explore the feasibility of representation fine-tuning, which applied some linear update to a few representations in a learned subspace, for knowledge editing. While being effective to enhance an LLM's general ability as demonstrated in the previous work, we theoretically show that this linear update imposes a tension in editing-locality trade-off. Subsequently, BaFT is proposed to break the linearity. BaFT computes a weight for each basis that spans a dimension of the subspace based on the input representation. This input-dependent weighting mechanism allows BaFT to manage different types of knowledge in an adaptive way, thereby achieving a better editing-locality trade-off. Experiments on three LLMs with five editing benchmarks in diverse scenarios show the superiority of our method.

Xiusi Chen, Hongzhi Wen, Sreyashi Nag et al.

With the rapid development of large language models (LLMs), aligning LLMs with human values and societal norms to ensure their reliability and safety has become crucial. Reinforcement learning with human feedback (RLHF) and Constitutional AI (CAI) have been proposed for LLM alignment. However, these methods require either heavy human annotations or explicitly pre-defined constitutions, which are labor-intensive and resource-consuming. To overcome these drawbacks, we study constitution-based LLM alignment and propose a data-driven constitution discovery and self-alignment framework called IterAlign. IterAlign leverages red teaming to unveil the weaknesses of an LLM and automatically discovers new constitutions using a stronger LLM. These constitutions are then used to guide self-correction of the base LLM. Such a constitution discovery pipeline can be run iteratively and automatically to discover new constitutions that specifically target the alignment gaps in the current LLM. Empirical results on several safety benchmark datasets and multiple base LLMs show that IterAlign successfully improves truthfulness, helpfulness, harmlessness and honesty, improving the LLM alignment by up to $13.5\%$ in harmlessness.

Tianci Liu, Ruirui Li, Zihan Dong et al.

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing (KE) to update specific knowledge in LLMs without changing unrelated others or compromising their pre-trained capabilities. Previous efforts sought to update a small amount of parameters of a LLM and proved effective for making selective updates. Nonetheless, the edited LLM often exhibits degraded ability to reason about the new knowledge. In this work, we identify a key issue: heterogeneous token overfitting (HTO), where the LLM overfits different tokens in the provided knowledge at varying rates. To tackle this, we propose OVERTONE, a token-level smoothing method that mitigates HTO by adaptively refining the target distribution. Theoretically, OVERTONE offers better parameter updates with negligible computation overhead. It also induces an implicit DPO but does not require preference data pairs. Extensive experiments across four editing methods, two LLMs, and diverse scenarios demonstrate the effectiveness and versatility of our method.

Haotian Zhai, Xinyu Chen, Can Zhang et al.

Test-time adaptation (TTA) of visual language models has recently attracted significant attention as a solution to the performance degradation caused by distribution shifts in downstream tasks. However, existing cache-based TTA methods have certain limitations. They mainly rely on the accuracy of cached feature labels, and the presence of noisy pseudo-labels can cause these features to deviate from their true distribution. This makes cache retrieval methods based on similarity matching highly sensitive to outliers or extreme samples. Moreover, current methods lack effective mechanisms to model class distributions, which limits their ability to fully exploit the potential of cached information. To address these challenges, we introduce a comprehensive and reliable caching mechanism and propose a novel zero-shot TTA method called "Cache, Residual, Gaussian" (CRG). This method not only employs learnable residual parameters to better align positive and negative visual prototypes with text prototypes, thereby optimizing the quality of cached features, but also incorporates Gaussian Discriminant Analysis (GDA) to dynamically model intra-class feature distributions, further mitigating the impact of noisy features. Experimental results on 13 benchmarks demonstrate that CRG outperforms state-of-the-art TTA methods, showcasing exceptional robustness and adaptability.

Xinyu Chen, Haotian Zhai, Can Zhang et al.

In zero-shot setting, test-time adaptation adjusts pre-trained models using unlabeled data from the test phase to enhance performance on unknown test distributions. Existing cache-enhanced TTA methods rely on a low-entropy criterion to select samples for prototype construction, assuming intra-class compactness. However, low-entropy samples may be unreliable under distribution shifts, and the resulting prototypes may not ensure compact intra-class distributions. This study identifies a positive correlation between cache-enhanced performance and intra-class compactness. Based on this observation, we propose a Multi-Cache enhanced Prototype-based Test-Time Adaptation (MCP) featuring three caches: an entropy cache for initializing prototype representations with low-entropy samples, an align cache for integrating visual and textual information to achieve compact intra-class distributions, and a negative cache for prediction calibration using high-entropy samples. We further developed MCP++, a framework incorporating cross-modal prototype alignment and residual learning, introducing prototype residual fine-tuning. Comparative and ablation experiments across 15 downstream tasks demonstrate that the proposed method and framework achieve state-of-the-art generalization performance. Project Page available at: https://zhaihaotian.github.io/MCP-ICCV25/

Nikhil Kumar Koditala, Chelsea Jui-Ting Ju, Ruirui Li et al.

A speaker verification (SV) system offers an authentication service designed to confirm whether a given speech sample originates from a specific speaker. This technology has paved the way for various personalized applications that cater to individual preferences. A noteworthy challenge faced by SV systems is their ability to perform consistently across a range of emotional spectra. Most existing models exhibit high error rates when dealing with emotional utterances compared to neutral ones. Consequently, this phenomenon often leads to missing out on speech of interest. This issue primarily stems from the limited availability of labeled emotional speech data, impeding the development of robust speaker representations that encompass diverse emotional states. To address this concern, we propose a novel approach employing the CycleGAN framework to serve as a data augmentation method. This technique synthesizes emotional speech segments for each specific speaker while preserving the unique vocal identity. Our experimental findings underscore the effectiveness of incorporating synthetic emotional data into the training process. The models trained using this augmented dataset consistently outperform the baseline models on the task of verifying speakers in emotional speech scenarios, reducing equal error rate by as much as 3.64% relative.

Haoyu Wang, Tianci Liu, Ruirui Li et al.

Pre-trained language models, trained on large-scale corpora, demonstrate strong generalizability across various NLP tasks. Fine-tuning these models for specific tasks typically involves updating all parameters, which is resource-intensive. Parameter-efficient fine-tuning (PEFT) methods, such as the popular LoRA family, introduce low-rank matrices to learn only a few parameters efficiently. However, during inference, the product of these matrices updates all pre-trained parameters, complicating tasks like knowledge editing that require selective updates. We propose a novel PEFT method, which conducts \textbf{r}ow and c\textbf{o}lumn-wise spar\textbf{se} \textbf{lo}w-\textbf{r}ank \textbf{a}daptation (RoseLoRA), to address this challenge. RoseLoRA identifies and updates only the most important parameters for a specific task, maintaining efficiency while preserving other model knowledge. By adding a sparsity constraint on the product of low-rank matrices and converting it to row and column-wise sparsity, we ensure efficient and precise model updates. Our theoretical analysis guarantees the lower bound of the sparsity with respective to the matrix product. Extensive experiments on five benchmarks across twenty datasets demonstrate that RoseLoRA outperforms baselines in both general fine-tuning and knowledge editing tasks.

Kexin Meng, Ruirui Li, Daguang Jiang

Human pose estimation is a fundamental and challenging task in computer vision. Larger-scale and more accurate keypoint annotations, while helpful for improving the accuracy of supervised pose estimation, are often expensive and difficult to obtain. Semi-supervised pose estimation tries to leverage a large amount of unlabeled data to improve model performance, which can alleviate the problem of insufficient labeled samples. The latest semi-supervised learning usually adopts a strong and weak data augmented teacher-student learning framework to deal with the challenge of "Human postural diversity and its long-tailed distribution". Appropriate data augmentation method is one of the key factors affecting the accuracy and generalization of semi-supervised models. Aiming at the problem that the difference of sample learning is not considered in the fixed keypoint masking augmentation method, this paper proposes an adaptive keypoint masking method, which can fully mine the information in the samples and obtain better estimation performance. In order to further improve the generalization and robustness of the model, this paper proposes a dual-branch data augmentation scheme, which can perform Mixup on samples and features on the basis of adaptive keypoint masking. The effectiveness of the proposed method is verified on COCO and MPII, outperforming the state-of-the-art semi-supervised pose estimation by 5.2% and 0.3%, respectively.

Yukun Yang, Naihao Wang, Haixin Yang et al.

Label noise is a common issue in real-world datasets that inevitably impacts the generalization of models. This study focuses on robust classification tasks where the label noise is instance-dependent. Estimating the transition matrix accurately in this task is challenging, and methods based on sample selection often exhibit confirmation bias to varying degrees. Sparse over-parameterized training (SOP) has been theoretically effective in estimating and recovering label noise, offering a novel solution for noise-label learning. However, this study empirically observes and verifies a technical flaw of SOP: the lack of coordination between model predictions and noise recovery leads to increased generalization error. To address this, we propose a method called Coordinated Sparse Recovery (CSR). CSR introduces a collaboration matrix and confidence weights to coordinate model predictions and noise recovery, reducing error leakage. Based on CSR, this study designs a joint sample selection strategy and constructs a comprehensive and powerful learning framework called CSR+. CSR+ significantly reduces confirmation bias, especially for datasets with more classes and a high proportion of instance-specific noise. Experimental results on simulated and real-world noisy datasets demonstrate that both CSR and CSR+ achieve outstanding performance compared to methods at the same level.

Yinglun Xu, Tarun Suresh, Rohan Gumaste et al.

Preference-based reinforcement learning (PBRL) in the offline setting has succeeded greatly in industrial applications such as chatbots. A two-step learning framework where one applies a reinforcement learning step after a reward modeling step has been widely adopted for the problem. However, such a method faces challenges from the risk of reward hacking and the complexity of reinforcement learning. To overcome the challenge, our insight is that both challenges come from the state-actions not supported in the dataset. Such state-actions are unreliable and increase the complexity of the reinforcement learning problem at the second step. Based on the insight, we develop a novel two-step learning method called PRC: preference-based reinforcement learning with constrained actions. The high-level idea is to limit the reinforcement learning agent to optimize over a constrained action space that excludes the out-of-distribution state-actions. We empirically verify that our method has high learning efficiency on various datasets in robotic control environments.

Xin Zhang, Minho Jin, Roger Cheng et al.

This paper proposes a novel formulation of prototypical loss with mixup for speaker verification. Mixup is a simple yet efficient data augmentation technique that fabricates a weighted combination of random data point and label pairs for deep neural network training. Mixup has attracted increasing attention due to its ability to improve robustness and generalization of deep neural networks. Although mixup has shown success in diverse domains, most applications have centered around closed-set classification tasks. In this work, we propose contrastive-mixup, a novel augmentation strategy that learns distinguishing representations based on a distance metric. During training, mixup operations generate convex interpolations of both inputs and virtual labels. Moreover, we have reformulated the prototypical loss function such that mixup is enabled on metric learning objectives. To demonstrate its generalization given limited training data, we conduct experiments by varying the number of available utterances from each speaker in the VoxCeleb database. Experimental results show that applying contrastive-mixup outperforms the existing baseline, reducing error rate by 16% relatively, especially when the number of training utterances per speaker is limited.

Metehan Cekic, Ruirui Li, Zeya Chen et al.

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning, heavily depends on both clean and sufficient labeled data, which is always difficult to acquire. Noisy unlabeled data, on the other hand, also provides valuable information that can be exploited using self-supervised training methods. In this work, we investigate how to pretrain speaker recognition models by leveraging dialogues between customers and smart-speaker devices. However, the supervisory information in such dialogues is inherently noisy, as multiple speakers may speak to a device in the course of the same dialogue. To address this issue, we propose an effective rejection mechanism that selectively learns from dialogues based on their acoustic homogeneity. Both reconstruction-based and contrastive-learning-based self-supervised methods are compared. Experiments demonstrate that the proposed method provides significant performance improvements, superior to earlier work. Dialogue pretraining when combined with the rejection mechanism yields 27.10% equal error rate (EER) reduction in speaker recognition, compared to a model without self-supervised pretraining.

Tao Chen, Yiran Liu, Haoyu Jiang et al.

Accurately segmenting roads is challenging due to substantial intra-class variations, indistinct inter-class distinctions, and occlusions caused by shadows, trees, and buildings. To address these challenges, attention to important texture details and perception of global geometric contextual information are essential. Recent research has shown that CNN-Transformer hybrid structures outperform using CNN or Transformer alone. While CNN excels at extracting local detail features, the Transformer naturally perceives global contextual information. In this paper, we propose a dual-branch network block named ConSwin that combines ResNet and SwinTransformers for road extraction tasks. This ConSwin block harnesses the strengths of both approaches to better extract detailed and global features. Based on ConSwin, we construct an hourglass-shaped road extraction network and introduce two novel connection structures to better transmit texture and structural detail information to the decoder. Our proposed method outperforms state-of-the-art methods on both the Massachusetts and CHN6-CUG datasets in terms of overall accuracy, IOU, and F1 indicators. Additional experiments validate the effectiveness of our proposed module, while visualization results demonstrate its ability to obtain better road representations.

Ruirui Li, Chelsea J. -T. Ju, Zeya Chen et al.

By implicitly recognizing a user based on his/her speech input, speaker identification enables many downstream applications, such as personalized system behavior and expedited shopping checkouts. Based on whether the speech content is constrained or not, both text-dependent (TD) and text-independent (TI) speaker recognition models may be used. We wish to combine the advantages of both types of models through an ensemble system to make more reliable predictions. However, any such combined approach has to be robust to incomplete inputs, i.e., when either TD or TI input is missing. As a solution we propose a fusion of embeddings network foenet architecture, combining joint learning with neural attention. We compare foenet with four competitive baseline methods on a dataset of voice assistant inputs, and show that it achieves higher accuracy than the baseline and score fusion methods, especially in the presence of incomplete inputs.

Haici Yang, Hongda Mao, Ruirui Li et al.

Speaker recognition is the process of identifying a speaker based on the voice. The technology has attracted more attention with the recent increase in popularity of smart voice assistants, such as Amazon Alexa. In the past few years, various convolutional neural network (CNN) based speaker recognition algorithms have been proposed and achieved satisfactory performance. However, convolutional operations are building blocks that typically perform on a local neighborhood at a time and thus miss to capture global, long-range interactions at the feature level which are critical for understanding the pattern in a speaker's voice. In this work, we propose to apply Non-local Convolutional Neural Networks (NLCNN) to improve the capability of capturing long-range dependencies at the feature level, therefore improving speaker recognition performance. Specifically, we introduce non-local blocks where the output response of a position is computed as a weighted sum of the input features at all positions. Combining non-local blocks with pre-defined CNN networks, we investigate the effectiveness of NLCNN models. Without extensive tuning, the proposed NLCNN models outperform state-of-the-art speaker recognition algorithms on the public Voxceleb dataset. What's more, we investigate different types of non-local operations applied to the frequency-time domain, time domain, frequency domain and frame-level respectively. Among them, time domain is the most effective one for speaker recognition applications.

Zhenhang Huang, Shihao Sun, Ruirui Li

Object detection and instance segmentation in remote sensing images is a fundamental and challenging task, due to the complexity of scenes and targets. The latest methods tried to take into account both the efficiency and the accuracy of instance segmentation. In order to improve both of them, in this paper, we propose a single-shot convolutional neural network structure, which is conceptually simple and straightforward, and meanwhile makes up for the problem of low accuracy of single-shot networks. Our method, termed with SSS-Net, detects targets based on the location of the object's center and the distances between the center and the points on the silhouette sampling with non-uniform angle intervals, thereby achieving abalanced sampling of lines in mask generation. In addition, we propose a non-uniform polar template IoU based on the contour template in polar coordinates. Experiments on both the Airbus Ship Detection Challenge dataset and the ISAIDships dataset show that SSS-Net has strong competitiveness in precision and speed for ship instance segmentation.

Huaxiu Yao, Xian Wu, Zhiqiang Tao et al.

In order to efficiently learn with small amount of data on new tasks, meta-learning transfers knowledge learned from previous tasks to the new ones. However, a critical challenge in meta-learning is the task heterogeneity which cannot be well handled by traditional globally shared meta-learning methods. In addition, current task-specific meta-learning methods may either suffer from hand-crafted structure design or lack the capability to capture complex relations between tasks. In this paper, motivated by the way of knowledge organization in knowledge bases, we propose an automated relational meta-learning (ARML) framework that automatically extracts the cross-task relations and constructs the meta-knowledge graph. When a new task arrives, it can quickly find the most relevant structure and tailor the learned structure knowledge to the meta-learner. As a result, the proposed framework not only addresses the challenge of task heterogeneity by a learned meta-knowledge graph, but also increases the model interpretability. We conduct extensive experiments on 2D toy regression and few-shot image classification and the results demonstrate the superiority of ARML over state-of-the-art baselines.

Ruirui Li, Mingming Li, Jiacheng Li et al.

We develop a connection sensitive attention U-Net(CSAU) for accurate retinal vessel segmentation. This method improves the recent attention U-Net for semantic segmentation with four key improvements: (1) connection sensitive loss that models the structure properties to improve the accuracy of pixel-wise segmentation; (2) attention gate with novel neural network structure and concatenating DOWN-Link to effectively learn better attention weights on fine vessels; (3) integration of connection sensitive loss and attention gate to further improve the accuracy on detailed vessels by additionally concatenating attention weights to features before output; (4) metrics of connection sensitive accuracy to reflect the segmentation performance on boundaries and thin vessels. Our method can effectively improve state-of-the-art vessel segmentation methods that suffer from difficulties in presence of abnormalities, bifurcation and microvascular. This connection sensitive loss tightly integrates with the proposed attention U-Net to accurately (i) segment retinal vessels, and (ii) reserve the connectivity of thin vessels by modeling the structural properties. Our method achieves the leading position on DRIVE, STARE and HRF datasets among the state-of-the-art methods.

Yi Peng, Shihao Sun, Zheng Wang et al.

Robust semantic segmentation of VHR remote sensing images from UAV sensors is critical for earth observation, land use, land cover or mapping applications. Several factors such as shadows, weather disruption and camera shakes making this problem highly challenging, especially only using RGB images. In this paper, we propose the use of multi-modality data including NIR, RGB and DSM to increase robustness of segmentation in blurred or partially damaged VHR remote sensing images. By proposing a cascaded dense encoder-decoder network and the SELayer based fusion and assembling techniques, the proposed RobustDenseNet achieves steady performance when the image quality is decreasing, compared with the state-of-the-art semantic segmentation model.

Shihao Sun, Lei Yang, Wenjie Liu et al.

In recent years, Fully Convolutional Networks (FCN) has been widely used in various semantic segmentation tasks, including multi-modal remote sensing imagery. How to fuse multi-modal data to improve the segmentation performance has always been a research hotspot. In this paper, a novel end-toend fully convolutional neural network is proposed for semantic segmentation of natural color, infrared imagery and Digital Surface Models (DSM). It is based on a modified DeepUNet and perform the segmentation in a multi-task way. The channels are clustered into groups and processed on different task pipelines. After a series of segmentation and fusion, their shared features and private features are successfully merged together. Experiment results show that the feature fusion network is efficient. And our approach achieves good performance in ISPRS Semantic Labeling Contest (2D).

Kai Yue, Lei Yang, Ruirui Li et al.

For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions. Recently, convolutional neural networks (CNNs) have shown outstanding performance on this task. Although many deep neural network structures and techniques have been applied to improve the accuracy, few have paid attention to better differentiating the easily confused classes. In this paper, we propose TreeSegNet which adopts an adaptive network to increase the classification rate at the pixelwise level. Specifically, based on the infrastructure of DeepUNet, a Tree-CNN block in which each node represents a ResNeXt unit is constructed adaptively according to the confusion matrix and the proposed TreeCutting algorithm. By transporting feature maps through concatenating connections, the Tree-CNN block fuses multiscale features and learns best weights for the model. In experiments on the ISPRS 2D semantic labeling Potsdam dataset, the results obtained by TreeSegNet are better than those of other published state-of-the-art methods. Detailed comparison and analysis show that the improvement brought by the adaptive Tree-CNN block is significant.

Ruirui Li, Wenjie Liu, Lei Yang et al.

Semantic segmentation is a fundamental research in remote sensing image processing. Because of the complex maritime environment, the sea-land segmentation is a challenging task. Although the neural network has achieved excellent performance in semantic segmentation in the last years, there are a few of works using CNN for sea-land segmentation and the results could be further improved. This paper proposes a novel deep convolution neural network named DeepUNet. Like the U-Net, its structure has a contracting path and an expansive path to get high resolution output. But differently, the DeepUNet uses DownBlocks instead of convolution layers in the contracting path and uses UpBlock in the expansive path. The two novel blocks bring two new connections that are U-connection and Plus connection. They are promoted to get more precise segmentation results. To verify our network architecture, we made a new challenging sea-land dataset and compare the DeepUNet on it with the SegNet and the U-Net. Experimental results show that DeepUNet achieved good performance compared with other architectures, especially in high-resolution remote sensing imagery.