arXiv subjects

Long Ma

Publications and source records attributed to Long Ma.

At least 109 records · Page 6Linked to original sources

arXiv2023

ASF-Net: Robust Video Deraining via Temporal Alignment and Online Adaptive Learning

In recent times, learning-based methods for video deraining have demonstrated commendable results. However, there are two critical challenges that these methods are yet to address: exploiting temporal correlations among adjacent frames and ensuring adaptability to unknown real-world scenarios. To overcome these challenges, we explore video deraining from a paradigm design perspective to learning strategy construction. Specifically, we propose a new computational paradigm, Alignment-Shift-Fusion Network (ASF-Net), which incorporates a temporal shift module. This module is novel to this field and provides deeper exploration of temporal information by facilitating the exchange of channel-level information within the feature space. To fully discharge the model's characterization capability, we further construct a LArge-scale RAiny video dataset (LARA) which also supports the development of this community. On the basis of the newly-constructed dataset, we explore the parameters learning process by developing an innovative re-degraded learning strategy. This strategy bridges the gap between synthetic and real-world scenes, resulting in stronger scene adaptability. Our proposed approach exhibits superior performance in three benchmarks and compelling visual quality in real-world scenarios, underscoring its efficacy. The code is available at https://github.com/vis-opt-group/ASF-Net.

cs.CV↗

arXiv2023

Improving Misaligned Multi-modality Image Fusion with One-stage Progressive Dense Registration

Misalignments between multi-modality images pose challenges in image fusion, manifesting as structural distortions and edge ghosts. Existing efforts commonly resort to registering first and fusing later, typically employing two cascaded stages for registration,i.e., coarse registration and fine registration. Both stages directly estimate the respective target deformation fields. In this paper, we argue that the separated two-stage registration is not compact, and the direct estimation of the target deformation fields is not accurate enough. To address these challenges, we propose a Cross-modality Multi-scale Progressive Dense Registration (C-MPDR) scheme, which accomplishes the coarse-to-fine registration exclusively using a one-stage optimization, thus improving the fusion performance of misaligned multi-modality images. Specifically, two pivotal components are involved, a dense Deformation Field Fusion (DFF) module and a Progressive Feature Fine (PFF) module. The DFF aggregates the predicted multi-scale deformation sub-fields at the current scale, while the PFF progressively refines the remaining misaligned features. Both work together to accurately estimate the final deformation fields. In addition, we develop a Transformer-Conv-based Fusion (TCF) subnetwork that considers local and long-range feature dependencies, allowing us to capture more informative features from the registered infrared and visible images for the generation of high-quality fused images. Extensive experimental analysis demonstrates the superiority of the proposed method in the fusion of misaligned cross-modality images.

cs.CV↗

arXiv2023

PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation

Infrared and visible image fusion is a powerful technique that combines complementary information from different modalities for downstream semantic perception tasks. Existing learning-based methods show remarkable performance, but are suffering from the inherent vulnerability of adversarial attacks, causing a significant decrease in accuracy. In this work, a perception-aware fusion framework is proposed to promote segmentation robustness in adversarial scenes. We first conduct systematic analyses about the components of image fusion, investigating the correlation with segmentation robustness under adversarial perturbations. Based on these analyses, we propose a harmonized architecture search with a decomposition-based structure to balance standard accuracy and robustness. We also propose an adaptive learning strategy to improve the parameter robustness of image fusion, which can learn effective feature extraction under diverse adversarial perturbations. Thus, the goals of image fusion (\textit{i.e.,} extracting complementary features from source modalities and defending attack) can be realized from the perspectives of architectural and learning strategies. Extensive experimental results demonstrate that our scheme substantially enhances the robustness, with gains of 15.3% mIOU of segmentation in the adversarial scene, compared with advanced competitors. The source codes are available at https://github.com/LiuZhu-CV/PAIF.

cs.CV↗

arXiv2023

Bilevel Generative Learning for Low-Light Vision

Recently, there has been a growing interest in constructing deep learning schemes for Low-Light Vision (LLV). Existing techniques primarily focus on designing task-specific and data-dependent vision models on the standard RGB domain, which inherently contain latent data associations. In this study, we propose a generic low-light vision solution by introducing a generative block to convert data from the RAW to the RGB domain. This novel approach connects diverse vision problems by explicitly depicting data generation, which is the first in the field. To precisely characterize the latent correspondence between the generative procedure and the vision task, we establish a bilevel model with the parameters of the generative block defined as the upper level and the parameters of the vision task defined as the lower level. We further develop two types of learning strategies targeting different goals, namely low cost and high accuracy, to acquire a new bilevel generative learning paradigm. The generative blocks embrace a strong generalization ability in other low-light vision tasks through the bilevel optimization on enhancement tasks. Extensive experimental evaluations on three representative low-light vision tasks, namely enhancement, detection, and segmentation, fully demonstrate the superiority of our proposed approach. The code will be available at https://github.com/Yingchi1998/BGL.

cs.CV↗

arXiv2023

Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation

Multi-modality image fusion and segmentation play a vital role in autonomous driving and robotic operation. Early efforts focus on boosting the performance for only one task, \emph{e.g.,} fusion or segmentation, making it hard to reach~`Best of Both Worlds'. To overcome this issue, in this paper, we propose a \textbf{M}ulti-\textbf{i}nteractive \textbf{F}eature learning architecture for image fusion and \textbf{Seg}mentation, namely SegMiF, and exploit dual-task correlation to promote the performance of both tasks. The SegMiF is of a cascade structure, containing a fusion sub-network and a commonly used segmentation sub-network. By slickly bridging intermediate features between two components, the knowledge learned from the segmentation task can effectively assist the fusion task. Also, the benefited fusion network supports the segmentation one to perform more pretentiously. Besides, a hierarchical interactive attention block is established to ensure fine-grained mapping of all the vital information between two tasks, so that the modality/semantic features can be fully mutual-interactive. In addition, a dynamic weight factor is introduced to automatically adjust the corresponding weights of each task, which can balance the interactive feature correspondence and break through the limitation of laborious tuning. Furthermore, we construct a smart multi-wave binocular imaging system and collect a full-time multi-modality benchmark with 15 annotated pixel-level categories for image fusion and segmentation. Extensive experiments on several public datasets and our benchmark demonstrate that the proposed method outputs visually appealing fused images and perform averagely $7.66\%$ higher segmentation mIoU in the real-world scene than the state-of-the-art approaches. The source code and benchmark are available at \url{https://github.com/JinyuanLiu-CV/SegMiF}.

cs.CV↗

arXiv2023

High-field NMR study of the spin correlations in the spin-cluster mineral Na$_2$Cu$_3$O(SO$_4$)$_3$

We report NMR study on the spin correlations in the spin-cluster based mineral Na$_2$Cu$_3$O(SO$_4$)$_3$ with magnetic fields ranged from 1 T to 33 T. The long-range magnetic order is observed from both the sudden spectral broadening at $T_N$ and critical slowing down behavior in the temperature dependence of spin-lattice relaxation rates ($1/T_1(T)$). The hump behavior of $1/T_1(T)$ persists to $μ_0H=7.25$ T, above which a spin excitation gap is observed from the thermally activated temperature dependence of $1/T_1$. The gap size shows a linear field dependence, whose slope and intercept respectively yield an effective magnetic moment of 2.54 $μ_B$ and a 0.94 meV spin excitation gap under zero magnetic field. These results indicate the existence of short-range order and prominent easy-plane spin anisotropy, which are important for understanding the spin excitation spectrum in A$_2$Cu$_3$O(SO$_4$)$_3$.

cond-mat.str-el↗

arXiv2023

DCCRN-KWS: an audio bias based model for noise robust small-footprint keyword spotting

Real-world complex acoustic environments especially the ones with a low signal-to-noise ratio (SNR) will bring tremendous challenges to a keyword spotting (KWS) system. Inspired by the recent advances of neural speech enhancement and context bias in speech recognition, we propose a robust audio context bias based DCCRN-KWS model to address this challenge. We form the whole architecture as a multi-task learning framework for both denosing and keyword spotting, where the DCCRN encoder is connected with the KWS model. Helped with the denoising task, we further introduce an audio context bias module to leverage the real keyword samples and bias the network to better iscriminate keywords in noisy conditions. Feature merge and complex context linear modules are also introduced to strength such discrimination and to effectively leverage contextual information respectively. Experiments on the internal challenging dataset and the HIMIYA public dataset show that our DCCRN-KWS system is superior in performance, while ablation study demonstrates the good design of the whole model.

eess.AS↗

arXiv2023

Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducer

It is difficult for an E2E ASR system to recognize words such as entities appearing infrequently in the training data. A widely used method to mitigate this issue is feeding contextual information into the acoustic model. Previous works have proven that a compact and accurate contextual list can boost the performance significantly. In this paper, we propose an efficient approach to obtain a high quality contextual list for a unified streaming/non-streaming based E2E model. Specifically, we make use of the phone-level streaming output to first filter the predefined contextual word list then fuse it into non-casual encoder and decoder to generate the final recognition results. Our approach improve the accuracy of the contextual ASR system and speed up the inference process. Experiments on two datasets demonstrates over 20% CER reduction comparing to the baseline system. Meanwhile, the RTF of our system can be stabilized within 0.15 when the size of the contextual word list grows over 6,000.

cs.SD↗

arXiv2023

Bilevel Fast Scene Adaptation for Low-Light Image Enhancement

Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision. The mainstream learning-based methods mainly acquire the enhanced model by learning the data distribution from the specific scenes, causing poor adaptability (even failure) when meeting real-world scenarios that have never been encountered before. The main obstacle lies in the modeling conundrum from distribution discrepancy across different scenes. To remedy this, we first explore relationships between diverse low-light scenes based on statistical analysis, i.e., the network parameters of the encoder trained in different data distributions are close. We introduce the bilevel paradigm to model the above latent correspondence from the perspective of hyperparameter optimization. A bilevel learning framework is constructed to endow the scene-irrelevant generality of the encoder towards diverse scenes (i.e., freezing the encoder in the adaptation and testing phases). Further, we define a reinforced bilevel learning framework to provide a meta-initialization for scene-specific decoder to further ameliorate visual quality. Moreover, to improve the practicability, we establish a Retinex-induced architecture with adaptive denoising and apply our built learning framework to acquire its parameters by using two training losses including supervised and unsupervised forms. Extensive experimental evaluations on multiple datasets verify our adaptability and competitive performance against existing state-of-the-art works. The code and datasets will be available at https://github.com/vis-opt-group/BL.

cs.CV↗

arXiv2023

MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenes

3D object detection plays a crucial role in numerous intelligent vision systems. Detection in the open world inevitably encounters various adverse scenes, such as dense fog, heavy rain, and low light conditions. Although existing efforts primarily focus on diversifying network architecture or training schemes, resulting in significant progress in 3D object detection, most of these learnable modules fail in adverse scenes, thereby hindering detection performance. To address this issue, this paper proposes a monocular 3D detection model designed to perceive twin depth in adverse scenes, termed MonoTDP, which effectively mitigates the degradation of detection performance in various harsh environments. Specifically, we first introduce an adaptive learning strategy to aid the model in handling uncontrollable weather conditions, significantly resisting degradation caused by various degrading factors. Then, to address the depth/content loss in adverse regions, we propose a novel twin depth perception module that simultaneously estimates scene and object depth, enabling the integration of scene-level features and object-level features. Additionally, we assemble a new adverse 3D object detection dataset encompassing a wide range of challenging scenes, including rainy, foggy, and low light weather conditions, with each type of scene containing 7,481 images. Experimental results demonstrate that our proposed method outperforms current state-of-the-art approaches by an average of 3.12% in terms of AP_R40 for car category across various adverse environments.

cs.CV↗

arXiv2023

Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond

Recently, multi-modality scene perception tasks, e.g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems. However, early efforts always consider boosting a single task unilaterally and neglecting others, seldom investigating their underlying connections for joint promotion. To overcome these limitations, we establish the hierarchical dual tasks-driven deep model to bridge these tasks. Concretely, we firstly construct an image fusion module to fuse complementary characteristics and cascade dual task-related modules, including a discriminator for visual effects and a semantic network for feature measurement. We provide a bi-level perspective to formulate image fusion and follow-up downstream tasks. To incorporate distinct task-related responses for image fusion, we consider image fusion as a primary goal and dual modules as learnable constraints. Furthermore, we develop an efficient first-order approximation to compute corresponding gradients and present dynamic weighted aggregation to balance the gradients for fusion learning. Extensive experiments demonstrate the superiority of our method, which not only produces visually pleasant fused results but also realizes significant promotion for detection and segmentation than the state-of-the-art approaches.

cs.CV↗

arXiv2023

PAI at SemEval-2023 Task 2: A Universal System for Named Entity Recognition with External Entity Information

The MultiCoNER II task aims to detect complex, ambiguous, and fine-grained named entities in low-context situations and noisy scenarios like the presence of spelling mistakes and typos for multiple languages. The task poses significant challenges due to the scarcity of contextual information, the high granularity of the entities(up to 33 classes), and the interference of noisy data. To address these issues, our team {\bf PAI} proposes a universal Named Entity Recognition (NER) system that integrates external entity information to improve performance. Specifically, our system retrieves entities with properties from the knowledge base (i.e. Wikipedia) for a given text, then concatenates entity information with the input sentence and feeds it into Transformer-based models. Finally, our system wins 2 first places, 4 second places, and 1 third place out of 13 tracks. The code is publicly available at \url{https://github.com/diqiuzhuanzhuan/semeval-2023}.

cs.CL↗

arXiv2023

DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model

Wav2vec 2.0 (W2V2) has shown impressive performance in automatic speech recognition (ASR). However, the large model size and the non-streaming architecture make it hard to be used under low-resource or streaming scenarios. In this work, we propose a two-stage knowledge distillation method to solve these two problems: the first step is to make the big and non-streaming teacher model smaller, and the second step is to make it streaming. Specially, we adopt the MSE loss for the distillation of hidden layers and the modified LF-MMI loss for the distillation of the prediction layer. Experiments are conducted on Gigaspeech, Librispeech, and an in-house dataset. The results show that the distilled student model (DistillW2V2) we finally get is 8x faster and 12x smaller than the original teacher model. For the 480ms latency setup, the DistillW2V2's relative word error rate (WER) degradation varies from 9% to 23.4% on test sets, which reveals a promising way to extend the W2V2's application scope.

eess.AS↗

arXiv2022

Adjacent Slice Feature Guided 2.5D Network for Pulmonary Nodule Segmentation

More and more attention has been paid to the segmentation of pulmonary nodules. Among the current methods based on deep learning, 3D segmentation methods directly input 3D images, which takes up a lot of memory and brings huge computation. However, most of the 2D segmentation methods with less parameters and calculation have the problem of lacking spatial relations between slices, resulting in poor segmentation performance. In order to solve these problems, we propose an adjacent slice feature guided 2.5D network. In this paper, we design an adjacent slice feature fusion model to introduce information from adjacent slices. To further improve the model performance, we construct a multi-scale fusion module to capture more context information, in addition, we design an edge-constrained loss function to optimize the segmentation results in the edge region. Fully experiments show that our method performs better than other existing methods in pulmonary nodule segmentation task.

eess.IV↗

arXiv2022

Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement

Underwater image enhancement has become an attractive topic as a significant technology in marine engineering and aquatic robotics. However, the limited number of datasets and imperfect hand-crafted ground truth weaken its robustness to unseen scenarios, and hamper the application to high-level vision tasks. To address the above limitations, we develop an efficient and compact enhancement network in collaboration with a high-level semantic-aware pretrained model, aiming to exploit its hierarchical feature representation as an auxiliary for the low-level underwater image enhancement. Specifically, we tend to characterize the shallow layer features as textures while the deep layer features as structures in the semantic-aware model, and propose a multi-path Contextual Feature Refinement Module (CFRM) to refine features in multiple scales and model the correlation between different features. In addition, a feature dominative network is devised to perform channel-wise modulation on the aggregated texture and structure features for the adaptation to different feature patterns of the enhancement network. Extensive experiments on benchmarks demonstrate that the proposed algorithm achieves more appealing results and outperforms state-of-the-art methods by large margins. We also apply the proposed algorithm to the underwater salient object detection task to reveal the favorable semantic-aware ability for high-level vision tasks. The code is available at STSC.

cs.CV↗

arXiv2022

Incommensurate magnetic order in Sm$_3$BWO$_9$ with the distorted kagome lattice

We investigate the magnetic ground state of Sm$_3$BWO$_9$ with the distorted kagome lattice. A magnetic phase transition is identified at $T_N=0.75$ K from the temperature dependence of specific heat. From $^{11}$B nuclear magnetic resonance (NMR) measurements, an incommensurate magnetic order is shown by the double-horn type spectra under a $c$-axis magnetic field. While, absence of line splitting is observed for field oriented within the $ab$-plane, indicating the incommensurate modulation of the internal field strictly along $c$-axis. From the spin dynamics, the critical slowing down behavior is observed in the temperature dependence of $1/T_1$ with $μ_0H\perp c$-axis, which is completely absent in that with $μ_0H||c$-axis. Based on the local symmetry of $^{11}$B sites, we analyze the hyperfine coupling tensors and propose two constraints on the possible magnetic structure. The single ion anisotropy should play an important role in the determination of the contrasting ground states of Sm$_3$BWO$_9$ and Pr$_3$BWO$_9$.

cond-mat.str-el↗

arXiv2022

CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformer

Customized keyword spotting (KWS) has great potential to be deployed on edge devices to achieve hands-free user experience. However, in real applications, false alarm (FA) would be a serious problem for spotting dozens or even hundreds of keywords, which drastically affects user experience. To solve this problem, in this paper, we leverage the recent advances in transducer and transformer based acoustic models and propose a new multi-stage customized KWS framework named Cascaded Transducer-Transformer KWS (CaTT-KWS), which includes a transducer based keyword detector, a frame-level phone predictor based force alignment module and a transformer based decoder. Specifically, the streaming transducer module is used to spot keyword candidates in audio stream. Then force alignment is implemented using the phone posteriors predicted by the phone predictor to finish the first stage keyword verification and refine the time boundaries of keyword. Finally, the transformer decoder further verifies the triggered keyword. Our proposed CaTT-KWS framework reduces FA rate effectively without obviously hurting keyword recognition accuracy. Specifically, we can get impressively 0.13 FA per hour on a challenging dataset, with over 90% relative reduction on FA comparing to the transducer based detection model, while keyword recognition accuracy only drops less than 2%.

cs.SD↗

arXiv2022

Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR

Leveraging context information is an intuitive idea to improve performance on conversational automatic speech recognition(ASR). Previous works usually adopt recognized hypotheses of historical utterances as preceding context, which may bias the current recognized hypothesis due to the inevitable historicalrecognition errors. To avoid this problem, we propose an audio-textual cross-modal representation extractor to learn contextual representations directly from preceding speech. Specifically, it consists of two modal-related encoders, extracting high-level latent features from speech and the corresponding text, and a cross-modal encoder, which aims to learn the correlation between speech and text. We randomly mask some input tokens and input sequences of each modality. Then a token-missing or modal-missing prediction with a modal-level CTC loss on the cross-modal encoder is performed. Thus, the model captures not only the bi-directional context dependencies in a specific modality but also relationships between different modalities. Then, during the training of the conversational ASR system, the extractor will be frozen to extract the textual representation of preceding speech, while such representation is used as context fed to the ASR decoder through attention mechanism. The effectiveness of the proposed approach is validated on several Mandarin conversation corpora and the highest character error rate (CER) reduction up to 16% is achieved on the MagicData dataset.

eess.AS↗