arXiv subjects

Long Chen

Publications and source records attributed to Long Chen.

At least 469 records · Page 26Linked to original sources

arXiv2022

Rethinking the Evaluation of Unbiased Scene Graph Generation

Current Scene Graph Generation (SGG) methods tend to predict frequent predicate categories and fail to recognize rare ones due to the severe imbalanced distribution of predicates. To improve the robustness of SGG models on different predicate categories, recent research has focused on unbiased SGG and adopted mean Recall@K (mR@K) as the main evaluation metric. However, we discovered two overlooked issues about this de facto standard metric, which makes current unbiased SGG evaluation vulnerable and unfair: 1) mR@K neglects the correlations among predicates and unintentionally breaks category independence when ranking all the triplet predictions together regardless of the predicate categories. 2) mR@K neglects the compositional diversity of different predicates and assigns excessively high weights to some oversimple category samples with limited composable relation triplet types. In addition, we investigate the under-explored correlation between objects and predicates, which can serve as a simple but strong baseline for unbiased SGG. In this paper, we refine mR@K and propose two complementary evaluation metrics for unbiased SGG: Independent Mean Recall (MR) and weighted IMR (wIMR). These two metrics are designed by considering the category independence and diversity of composable relation triplets, respectively. We compare the proposed metrics with the de facto standard metrics through extensive experiments and discuss the solutions to evaluate unbiased SGG in a more trustworthy way.

cs.CV↗

arXiv2022

Instance Segmentation of Dense and Overlapping Objects via Layering

Instance segmentation aims to delineate each individual object of interest in an image. State-of-the-art approaches achieve this goal by either partitioning semantic segmentations or refining coarse representations of detected objects. In this work, we propose a novel approach to solve the problem via object layering, i.e. by distributing crowded, even overlapping objects into different layers. By grouping spatially separated objects in the same layer, instances can be effortlessly isolated by extracting connected components in each layer. In comparison to previous methods, our approach is not affected by complex object shapes or object overlaps. With minimal post-processing, our method yields very competitive results on a diverse line of datasets: C. elegans (BBBC), Overlapping Cervical Cells (OCC) and cultured neuroblastoma cells (CCDB). The source code is publicly available.

cs.CV↗

arXiv2022

Few-Shot Object Detection with Fully Cross-Transformer

Few-shot object detection (FSOD), with the aim to detect novel objects using very few training examples, has recently attracted great research interest in the community. Metric-learning based methods have been demonstrated to be effective for this task using a two-branch based siamese network, and calculate the similarity between image regions and few-shot examples for detection. However, in previous works, the interaction between the two branches is only restricted in the detection head, while leaving the remaining hundreds of layers for separate feature extraction. Inspired by the recent work on vision transformers and vision-language transformers, we propose a novel Fully Cross-Transformer based model (FCT) for FSOD by incorporating cross-transformer into both the feature backbone and detection head. The asymmetric-batched cross-attention is proposed to aggregate the key information from the two branches with different batch sizes. Our model can improve the few-shot similarity learning between the two branches by introducing the multi-level interactions. Comprehensive experiments on both PASCAL VOC and MSCOCO FSOD benchmarks demonstrate the effectiveness of our model.

cs.CV↗

arXiv2022

Rethinking Data Augmentation for Robust Visual Question Answering

Data Augmentation (DA) -- generating extra training samples beyond original training set -- has been widely-used in today's unbiased VQA models to mitigate the language biases. Current mainstream DA strategies are synthetic-based methods, which synthesize new samples by either editing some visual regions/words, or re-generating them from scratch. However, these synthetic samples are always unnatural and error-prone. To avoid this issue, a recent DA work composes new augmented samples by randomly pairing pristine images and other human-written questions. Unfortunately, to guarantee augmented samples have reasonable ground-truth answers, they manually design a set of heuristic rules for several question types, which extremely limits its generalization abilities. To this end, we propose a new Knowledge Distillation based Data Augmentation for VQA, dubbed KDDAug. Specifically, we first relax the requirements of reasonable image-question pairs, which can be easily applied to any question types. Then, we design a knowledge distillation (KD) based answer assignment to generate pseudo answers for all composed image-question pairs, which are robust to both in-domain and out-of-distribution settings. Since KDDAug is a model-agnostic DA strategy, it can be seamlessly incorporated into any VQA architectures. Extensive ablation studies on multiple backbones and benchmarks have demonstrated the effectiveness and generalization abilities of KDDAug.

cs.CV↗

arXiv2022

Immersed Virtual Element Methods for Elliptic Interface Problems in Two Dimensions

This article presents an immersed virtual element method for solving a class of interface problems that combines the advantages of both body-fitted mesh methods and unfitted mesh methods. A background body-fitted mesh is generated initially. On those interface elements, virtual element spaces are constructed as solution spaces to local interface problems, and exact sequences can be established for these new spaces involving discontinuous coefficients. The discontinuous coefficients of interface problems are recast as Hodge star operators that are the key to project immersed virtual functions to classic immersed finite element (IFE) functions for computing numerical solutions. An a priori convergence analysis is established robust with respect to the interface location. The proposed method is capable of handling more complicated interface element configuration and provides better performance than the conventional penalty-type IFE method for the H(curl)-interface problem arising from Maxwell equations. It also brings a connection between various methods such as body-fitted methods, IFE methods, virtual element methods, etc.

math.NA↗

arXiv2022

The $\bar{\mathrm{MS}}$ renormalization constant of the singlet axial current operator at $\mathcal{O}(α_s^5)$ in QCD

We provide the $\bar{\mathrm{MS}}$ factor of the renormalization constant of the singlet axial-current operator in dimensional regularization at $\mathcal{O}(α_s^5)$ in perturbative Quantum Chromodynamics (QCD). The result is obtained from a formula derived using the Adler-Bell-Jackiw equation in terms of renormalized operators. The required input consists of the complete four-loop results for operator renormalization constants obtained by explicit diagrammatic computation in a previous publication.

hep-ph↗

arXiv2022

Correspondence Matters for Video Referring Expression Comprehension

We investigate the problem of video Referring Expression Comprehension (REC), which aims to localize the referent objects described in the sentence to visual regions in the video frames. Despite the recent progress, existing methods suffer from two problems: 1) inconsistent localization results across video frames; 2) confusion between the referent and contextual objects. To this end, we propose a novel Dual Correspondence Network (dubbed as DCNet) which explicitly enhances the dense associations in both the inter-frame and cross-modal manners. Firstly, we aim to build the inter-frame correlations for all existing instances within the frames. Specifically, we compute the inter-frame patch-wise cosine similarity to estimate the dense alignment and then perform the inter-frame contrastive learning to map them close in feature space. Secondly, we propose to build the fine-grained patch-word alignment to associate each patch with certain words. Due to the lack of this kind of detailed annotations, we also predict the patch-word correspondence through the cosine similarity. Extensive experiments demonstrate that our DCNet achieves state-of-the-art performance on both video and image REC benchmarks. Furthermore, we conduct comprehensive ablation studies and thorough analyses to explore the optimal model designs. Notably, our inter-frame and cross-modal contrastive losses are plug-and-play functions and are applicable to any video REC architectures. For example, by building on top of Co-grounding, we boost the performance by 1.48% absolute improvement on Accu.@0.5 for VID-Sentence dataset.

cs.CV↗

arXiv2022

Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation

The Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image. Although SGG has achieved remarkable progress over the last few years, almost all existing SGG models follow the same training paradigm: they treat both object and predicate classification in SGG as a single-label classification problem, and the ground-truths are one-hot target labels. However, this prevalent training paradigm has overlooked two characteristics of current SGG datasets: 1) For positive samples, some specific subject-object instances may have multiple reasonable predicates. 2) For negative samples, there are numerous missing annotations. Regardless of the two characteristics, SGG models are easy to be confused and make wrong predictions. To this end, we propose a novel model-agnostic Label Semantic Knowledge Distillation (LS-KD) for unbiased SGG. Specifically, LS-KD dynamically generates a soft label for each subject-object instance by fusing a predicted Label Semantic Distribution (LSD) with its original one-hot target label. LSD reflects the correlations between this instance and multiple predicate categories. Meanwhile, we propose two different strategies to predict LSD: iterative self-KD and synchronous self-KD. Extensive ablations and results on three SGG tasks have attested to the superiority and generality of our proposed LS-KD, which can consistently achieve decent trade-off performance between different predicate categories.

cs.CV↗

arXiv2022

Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation

Recently, increasing efforts have been focused on Weakly Supervised Scene Graph Generation (WSSGG). The mainstream solution for WSSGG typically follows the same pipeline: they first align text entities in the weak image-level supervisions (e.g., unlocalized relation triplets or captions) with image regions, and then train SGG models in a fully-supervised manner with aligned instance-level "pseudo" labels. However, we argue that most existing WSSGG works only focus on object-consistency, which means the grounded regions should have the same object category label as text entities. While they neglect another basic requirement for an ideal alignment: interaction-consistency, which means the grounded region pairs should have the same interactions (i.e., visual relations) as text entity pairs. Hence, in this paper, we propose to enhance a simple grounding module with both object-aware and interaction-aware knowledge to acquire more reliable pseudo labels. To better leverage these two types of knowledge, we regard them as two teachers and fuse their generated targets to guide the training process of our grounding module. Specifically, we design two different strategies to adaptively assign weights to different teachers by assessing their reliability on each training sample. Extensive experiments have demonstrated that our method consistently improves WSSGG performance on various kinds of weak supervision.

cs.CV↗

arXiv2022

Flipping of antiferromagnetic to superconducting states in pressurized quasi-one-dimensional manganese-based compounds

One of the universal features of unconventional superconductors is that the superconducting (SC) state is developed in the proximity of an antiferromagnetic (AFM) state. Understanding the interplay between these two states is one of the key issues to uncover the underlying physics of unconventional SC mechanism. Here, we report a pressure-induced flipping of the AFM state to SC state in the quasi-one-dimensional AMn6Bi5 (A = K, Rb, and Cs) compounds. We find that at a critical pressure the AFM state suddenly disappears at a finite temperature and a SC state simultaneously emerges at a lower temperature without detectable structural changes. Intriguingly, all members of the family present the AFM-SC transition at almost the same critical pressures (Pc), though their ambient-pressure unit-cell volumes vary substantially. Our theoretical calculations indicate that the increasing weight of dxz orbital electrons near Fermi energy under the pressure may be the origin of the flipping. These results reveal a diversity of competing nature between the AFM and SC states among the 3d-transition-metal compounds.

cond-mat.supr-con↗

arXiv2022

Deep Motion Prior for Weakly-Supervised Temporal Action Localization

Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels. Currently, most state-of-the-art WSTAL methods follow a Multi-Instance Learning (MIL) pipeline: producing snippet-level predictions first and then aggregating to the video-level prediction. However, we argue that existing methods have overlooked two important drawbacks: 1) inadequate use of motion information and 2) the incompatibility of prevailing cross-entropy training loss. In this paper, we analyze that the motion cues behind the optical flow features are complementary informative. Inspired by this, we propose to build a context-dependent motion prior, termed as motionness. Specifically, a motion graph is introduced to model motionness based on the local motion carrier (e.g., optical flow). In addition, to highlight more informative video snippets, a motion-guided loss is proposed to modulate the network training conditioned on motionness scores. Extensive ablation studies confirm that motionness efficaciously models action-of-interest, and the motion-guided loss leads to more accurate results. Besides, our motion-guided loss is a plug-and-play loss function and is applicable with existing WSTAL methods. Without loss of generality, based on the standard MIL pipeline, our method achieves new state-of-the-art performance on three challenging benchmarks, including THUMOS'14, ActivityNet v1.2 and v1.3.

cs.CV↗

arXiv2022

A Transformer-based Generative Adversarial Network for Brain Tumor Segmentation

Brain tumor segmentation remains a challenge in medical image segmentation tasks. With the application of transformer in various computer vision tasks, transformer blocks show the capability of learning long-distance dependency in global space, which is complementary with CNNs. In this paper, we proposed a novel transformer-based generative adversarial network to automatically segment brain tumors with multi-modalities MRI. Our architecture consists of a generator and a discriminator, which are trained in min-max game progress. The generator is based on a typical "U-shaped" encoder-decoder architecture, whose bottom layer is composed of transformer blocks with resnet. Besides, the generator is trained with deep supervision technology. The discriminator we designed is a CNN-based network with multi-scale $L_{1}$ loss, which is proved to be effective for medical semantic image segmentation. To validate the effectiveness of our method, we conducted experiments on BRATS2015 dataset, achieving comparable or better performance than previous state-of-the-art methods.

eess.IV↗

arXiv2022

Rethinking the Reference-based Distinctive Image Captioning

Distinctive Image Captioning (DIC) -- generating distinctive captions that describe the unique details of a target image -- has received considerable attention over the last few years. A recent DIC work proposes to generate distinctive captions by comparing the target image with a set of semantic-similar reference images, i.e., reference-based DIC (Ref-DIC). It aims to make the generated captions can tell apart the target and reference images. Unfortunately, reference images used by existing Ref-DIC works are easy to distinguish: these reference images only resemble the target image at scene-level and have few common objects, such that a Ref-DIC model can trivially generate distinctive captions even without considering the reference images. To ensure Ref-DIC models really perceive the unique objects (or attributes) in target images, we first propose two new Ref-DIC benchmarks. Specifically, we design a two-stage matching mechanism, which strictly controls the similarity between the target and reference images at object-/attribute- level (vs. scene-level). Secondly, to generate distinctive captions, we develop a strong Transformer-based Ref-DIC baseline, dubbed as TransDIC. It not only extracts visual features from the target image, but also encodes the differences between objects in the target and reference images. Finally, for more trustworthy benchmarking, we propose a new evaluation metric named DisCIDEr for Ref-DIC, which evaluates both the accuracy and distinctiveness of the generated captions. Experimental results demonstrate that our TransDIC can generate distinctive captions. Besides, it outperforms several state-of-the-art models on the two new benchmarks over different metrics.

cs.CV↗

arXiv2022

Explicit Image Caption Editing

Given an image and a reference caption, the image caption editing task aims to correct the misalignment errors and generate a refined caption. However, all existing caption editing works are implicit models, ie, they directly produce the refined captions without explicit connections to the reference captions. In this paper, we introduce a new task: Explicit Caption Editing (ECE). ECE models explicitly generate a sequence of edit operations, and this edit operation sequence can translate the reference caption into a refined one. Compared to the implicit editing, ECE has multiple advantages: 1) Explainable: it can trace the whole editing path. 2) Editing Efficient: it only needs to modify a few words. 3) Human-like: it resembles the way that humans perform caption editing, and tries to keep original sentence structures. To solve this new task, we propose the first ECE model: TIger. TIger is a non-autoregressive transformer-based model, consisting of three modules: Tagger_del, Tagger_add, and Inserter. Specifically, Tagger_del decides whether each word should be preserved or not, Tagger_add decides where to add new words, and Inserter predicts the specific word for adding. To further facilitate ECE research, we propose two new ECE benchmarks by re-organizing two existing datasets, dubbed COCO-EE and Flickr30K-EE, respectively. Extensive ablations on both two benchmarks have demonstrated the effectiveness of TIger.

cs.CV↗

arXiv2022

Embedded Point Iteration Based Recursive Algorithm for Online Identification of Nonlinear Regression Models

This paper presents a novel online identification algorithm for nonlinear regression models. The online identification problem is challenging due to the presence of nonlinear structure in the models. Previous works usually ignore the special structure of nonlinear regression models, in which the parameters can be partitioned into a linear part and a nonlinear part. In this paper, we develop an efficient recursive algorithm for nonlinear regression models based on analyzing the equivalent form of variable projection (VP) algorithm. By introducing the embedded point iteration (EPI) step, the proposed recursive algorithm can properly exploit the coupling relationship of linear parameters and nonlinear parameters. In addition, we theoretically prove that the proposed algorithm is mean-square bounded. Numerical experiments on synthetic data and real-world time series verify the high efficiency and robustness of the proposed algorithm.

math.OC↗

arXiv2022

Balancing the trade-off between cost and reliability for wireless sensor networks: a multi-objective optimized deployment method

The deployment of the sensor nodes (SNs) always plays a decisive role in the system performance of wireless sensor networks (WSNs). In this work, we propose an optimal deployment method for practical heterogeneous WSNs which gives a deep insight into the trade-off between the reliability and deployment cost. Specifically, this work aims to provide the optimal deployment of SNs to maximize the coverage degree and connection degree, and meanwhile minimize the overall deployment cost. In addition, this work fully considers the heterogeneity of SNs (i.e. differentiated sensing range and deployment cost) and three-dimensional (3-D) deployment scenarios. This is a multi-objective optimization problem, non-convex, multimodal and NP-hard. To solve it, we develop a novel swarm-based multi-objective optimization algorithm, known as the competitive multi-objective marine predators algorithm (CMOMPA) whose performance is verified by comprehensive comparative experiments with ten other stateof-the-art multi-objective optimization algorithms. The computational results demonstrate that CMOMPA is superior to others in terms of convergence and accuracy and shows excellent performance on multimodal multiobjective optimization problems. Sufficient simulations are also conducted to evaluate the effectiveness of the CMOMPA based optimal SNs deployment method. The results show that the optimized deployment can balance the trade-off among deployment cost, sensing reliability and network reliability. The source code is available on https://github.com/iNet-WZU/CMOMPA.

cs.NI↗

arXiv2022

Graph-based Multi-View Fusion and Local Adaptation: Mitigating Within-Household Confusability for Speaker Identification

Speaker identification (SID) in the household scenario (e.g., for smart speakers) is an important but challenging problem due to limited number of labeled (enrollment) utterances, confusable voices, and demographic imbalances. Conventional speaker recognition systems generalize from a large random sample of speakers, causing the recognition to underperform for households drawn from specific cohorts or otherwise exhibiting high confusability. In this work, we propose a graph-based semi-supervised learning approach to improve household-level SID accuracy and robustness with locally adapted graph normalization and multi-signal fusion with multi-view graphs. Unlike other work on household SID, fairness, and signal fusion, this work focuses on speaker label inference (scoring) and provides a simple solution to realize household-specific adaptation and multi-signal fusion without tuning the embeddings or training a fusion network. Experiments on the VoxCeleb dataset demonstrate that our approach consistently improves the performance across households with different customer cohorts and degrees of confusability.

eess.AS↗

arXiv2022

Finite Element de Rham and Stokes Complexes in Three Dimensions

Finite element de Rham complexes and finite element Stokes complexes with various smoothness in three dimensions are systematically constructed. First smooth scalar finite elements in three dimensions are derived through a non-overlapping decomposition of the simplicial lattice. Based on the smooth scalar finite elements, both H(div)-conforming finite elements and H(curl)-conforming finite elements with various smoothness are devised, which induce the finite element de Rham complexes with various smoothness and the associated commutative diagrams. The div stability is established for the H(div)-conforming finite elements, and the exactness of these finite element complexes.

math.NA↗