arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 721 records · Page 40Linked to original sources

arXiv2022

Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World

Monocular visual odometry (VO) has attracted extensive research attention by providing real-time vehicle motion from cost-effective camera images. However, state-of-the-art optimization-based monocular VO methods suffer from the scale inconsistency problem for long-term predictions. Deep learning has recently been introduced to address this issue by leveraging stereo sequences or ground-truth motions in the training dataset. However, it comes at an additional cost for data collection, and such training data may not be available in all datasets. In this work, we propose VRVO, a novel framework for retrieving the absolute scale from virtual data that can be easily obtained from modern simulation environments, whereas in the real domain no stereo or ground-truth data are required in either the training or inference phases. Specifically, we first train a scale-aware disparity network using both monocular real images and stereo virtual data. The virtual-to-real domain gap is bridged by using an adversarial training strategy to map images from both domains into a shared feature space. The resulting scale-consistent disparities are then integrated with a direct VO system by constructing a virtual stereo objective that ensures the scale consistency over long trajectories. Additionally, to address the suboptimality issue caused by the separate optimization backend and the learning process, we further propose a mutual reinforcement pipeline that allows bidirectional information flow between learning and optimization, which boosts the robustness and accuracy of each other. We demonstrate the effectiveness of our framework on the KITTI and vKITTI2 datasets.

cs.CV↗

arXiv2022

Compactness and Guessing Principles in the Radin Extensions

We investigate the interaction between compactness principles and guessing principles in the Radin forcing extensions. In particular, we show that in any Radin forcing extension with respect to a measure sequence on $κ$, if $κ$ is weakly compact, then $\diamondsuit(κ)$ holds. This provides contrast with a well-known theorem of Woodin, who showed that in a certain Radin extension over a suitably prepared ground model relative to the existence of large cardinals, the diamond principle fails at a strongly inaccessible Mahlo cardinal. Refining the analysis of the Radin extensions, we consistently demonstrate a scenario where a compactness principle, stronger than the diagonal stationary reflection principle, holds yet the diamond principle fails at a strongly inaccessible cardinal, improving a result from \cite{BN19}.

math.LO↗

arXiv2022

Deep Interest Highlight Network for Click-Through Rate Prediction in Trigger-Induced Recommendation

In many classical e-commerce platforms, personalized recommendation has been proven to be of great business value, which can improve user satisfaction and increase the revenue of platforms. In this paper, we present a new recommendation problem, Trigger-Induced Recommendation (TIR), where users' instant interest can be explicitly induced with a trigger item and follow-up related target items are recommended accordingly. TIR has become ubiquitous and popular in e-commerce platforms. In this paper, we figure out that although existing recommendation models are effective in traditional recommendation scenarios by mining users' interests based on their massive historical behaviors, they are struggling in discovering users' instant interests in the TIR scenario due to the discrepancy between these scenarios, resulting in inferior performance. To tackle the problem, we propose a novel recommendation method named Deep Interest Highlight Network (DIHN) for Click-Through Rate (CTR) prediction in TIR scenarios. It has three main components including 1) User Intent Network (UIN), which responds to generate a precise probability score to predict user's intent on the trigger item; 2) Fusion Embedding Module (FEM), which adaptively fuses trigger item and target item embeddings based on the prediction from UIN; and (3) Hybrid Interest Extracting Module (HIEM), which can effectively highlight users' instant interest from their behaviors based on the result of FEM. Extensive offline and online evaluations on a real-world e-commerce platform demonstrate the superiority of DIHN over state-of-the-art methods.

cs.IR↗

arXiv2022

Complicated colorings, revisited

In a paper from 1997, Shelah asked whether $Pr_1(λ^+,λ^+,λ^+,λ)$ holds for every inaccessible cardinal $λ$. Here, we prove that an affirmative answer follows from $\square(λ^+)$. Furthermore, we establish that for every pair $χ<κ$ of regular uncountable cardinals, $\square(κ)$ implies $Pr_1(κ,κ,κ,χ)$.

math.LO↗

arXiv2022

Exploring Depth Contribution for Camouflaged Object Detection

Camouflaged object detection (COD) aims to segment camouflaged objects hiding in the environment, which is challenging due to the similar appearance of camouflaged objects and their surroundings. Research in biology suggests depth can provide useful object localization cues for camouflaged object discovery. In this paper, we study the depth contribution for camouflaged object detection, where the depth maps are generated with existing monocular depth estimation (MDE) methods. Due to the domain gap between the MDE dataset and our COD dataset, the generated depth maps are not accurate enough to be directly used. We then introduce two solutions to avoid the noisy depth maps from dominating the training process. Firstly, we present an auxiliary depth estimation branch ("ADE"), aiming to regress the depth maps. We find that "ADE" is especially necessary for our "generated depth" scenario. Secondly, we introduce a multi-modal confidence-aware loss function via a generative adversarial network to weigh the contribution of depth for camouflaged object detection. Our extensive experiments on various camouflaged object detection datasets explain that the existing "sensor depth" based RGB-D segmentation techniques work poorly with "generated depth", and our proposed two solutions work cooperatively, achieving effective depth contribution exploration for camouflaged object detection.

cs.CV↗

arXiv2022

Quantum Dynamics of Cold Atomic Gas with $SU(1,1)$ Symmetry

Motivated by recent advances in quantum dynamics, we investigate the dynamics of the system with $SU(1,1)$ symmetry. Instead of performing the time-ordered integral for the evolution operator of the time-dependent Hamiltonian, we show that the time evolution operator can be expressed as an $SU(1,1)$ group element. Since the $SU(1,1)$ group describes the "rotation" on a hyperbolic surface, the dynamics can be visualized on a Poincaré disk, a stereographic projection of the upper hyperboloid. As an example, we present the trajectory of the revival of Bose-Einstein condensation and that of the scale-invariant Fermi gas on the Poincaré disk. Further considering the quantum gas in the oscillating lattice, we also study the dynamics of the system with time-dependent single-particle dispersion. Our results are hopefully to be checked in current experiments.

cond-mat.quant-gas↗

arXiv2022

RGB-D Saliency Detection via Cascaded Mutual Information Minimization

Existing RGB-D saliency detection models do not explicitly encourage RGB and depth to achieve effective multi-modal learning. In this paper, we introduce a novel multi-stage cascaded learning framework via mutual information minimization to "explicitly" model the multi-modal information between RGB image and depth data. Specifically, we first map the feature of each mode to a lower dimensional feature vector, and adopt mutual information minimization as a regularizer to reduce the redundancy between appearance features from RGB and geometric features from depth. We then perform multi-stage cascaded learning to impose the mutual information minimization constraint at every stage of the network. Extensive experiments on benchmark RGB-D saliency datasets illustrate the effectiveness of our framework. Further, to prosper the development of this field, we contribute the largest (7x larger than NJU2K) dataset, which contains 15,625 image pairs with high quality polygon-/scribble-/object-/instance-/rank-level annotations. Based on these rich labels, we additionally construct four new benchmarks with strong baselines and observe some interesting phenomena, which can motivate future model design. Source code and dataset are available at "https://github.com/JingZhang617/cascaded_rgbd_sod".

cs.CV↗

arXiv2022

SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection

Although point-based networks are demonstrated to be accurate for 3D point cloud modeling, they are still falling behind their voxel-based competitors in 3D detection. We observe that the prevailing set abstraction design for down-sampling points may maintain too much unimportant background information that can affect feature learning for detecting objects. To tackle this issue, we propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA). Technically, we first add a binary segmentation module as the side output to help identify foreground points. Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling. In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection. Additionally, it is an easy-to-plug-in module and able to boost various point-based detectors, including single-stage and two-stage ones. Extensive experiments on the popular KITTI and nuScenes datasets validate the superiority of SASA, lifting point-based detection models to reach comparable performance to state-of-the-art voxel-based methods.

cs.CV↗

arXiv2022

Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers

The exemplar-free class incremental learning requires classification models to learn new class knowledge incrementally without retaining any old samples. Recently, the framework based on parallel one-class classifiers (POC), which trains a one-class classifier (OCC) independently for each category, has attracted extensive attention, since it can naturally avoid catastrophic forgetting. POC, however, suffers from weak discriminability and comparability due to its independent training strategy for different OOCs. To meet this challenge, we propose a new framework, named Discriminative and Comparable One-class classifiers for Incremental Learning (DisCOIL). DisCOIL follows the basic principle of POC, but it adopts variational auto-encoders (VAE) instead of other well-established one-class classifiers (e.g. deep SVDD), because a trained VAE can not only identify the probability of an input sample belonging to a class but also generate pseudo samples of the class to assist in learning new tasks. With this advantage, DisCOIL trains a new-class VAE in contrast with the old-class VAEs, which forces the new-class VAE to reconstruct better for new-class samples but worse for the old-class pseudo samples, thus enhancing the comparability. Furthermore, DisCOIL introduces a hinge reconstruction loss to ensure the discriminability. We evaluate our method extensively on MNIST, CIFAR10, and Tiny-ImageNet. The experimental results show that DisCOIL achieves state-of-the-art performance.

cs.LG↗

arXiv2022

Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images

Semantic change detection (SCD) extends the multi-class change detection (MCD) task to provide not only the change locations but also the detailed land-cover/land-use (LCLU) categories before and after the observation intervals. This fine-grained semantic change information is very useful in many applications. Recent studies indicate that the SCD can be modeled through a triple-branch Convolutional Neural Network (CNN), which contains two temporal branches and a change branch. However, in this architecture, the communications between the temporal branches and the change branch are insufficient. To overcome the limitations in existing methods, we propose a novel CNN architecture for the SCD, where the semantic temporal features are merged in a deep CD unit. Furthermore, we elaborate on this architecture to reason the bi-temporal semantic correlations. The resulting Bi-temporal Semantic Reasoning Network (Bi-SRNet) contains two types of semantic reasoning blocks to reason both single-temporal and cross-temporal semantic correlations, as well as a novel loss function to improve the semantic consistency of change detection results. Experimental results on a benchmark dataset show that the proposed architecture obtains significant accuracy improvements over the existing approaches, while the added designs in the Bi-SRNet further improves the segmentation of both semantic categories and the changed areas. The codes in this paper are accessible at: github.com/ggsDing/Bi-SRNet.

cs.CV↗

arXiv2022

CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking

Expert finding, a popular service provided by many online websites such as Expertise Finder, LinkedIn, and AMiner, is beneficial to seeking candidate qualifications, consultants, and collaborators. However, its quality is suffered from lack of ample sources of expert information. This paper employs AMiner as the basis with an aim at linking any external experts to the counterparts on AMiner. As it is infeasible to acquire sufficient linkages from arbitrary external sources, we explore the problem of zero-shot expert linking. In this paper, we propose CODE, which first pre-trains an expert linking model by contrastive learning on AMiner such that it can capture the representation and matching patterns of experts without supervised signals, then it is fine-tuned between AMiner and external sources to enhance the models transferability in an adversarial manner. For evaluation, we first design two intrinsic tasks, author identification and paper clustering, to validate the representation and matching capability endowed by contrastive learning. Then the final external expert linking performance on two genres of external sources also implies the superiority of the adversarial fine-tuning method. Additionally, we show the online deployment of CODE, and continuously improve its online performance via active learning.

cs.IR↗

arXiv2021

Siamese Network with Interactive Transformer for Video Object Segmentation

Semi-supervised video object segmentation (VOS) refers to segmenting the target object in remaining frames given its annotation in the first frame, which has been actively studied in recent years. The key challenge lies in finding effective ways to exploit the spatio-temporal context of past frames to help learn discriminative target representation of current frame. In this paper, we propose a novel Siamese network with a specifically designed interactive transformer, called SITVOS, to enable effective context propagation from historical to current frames. Technically, we use the transformer encoder and decoder to handle the past frames and current frame separately, i.e., the encoder encodes robust spatio-temporal context of target object from the past frames, while the decoder takes the feature embedding of current frame as the query to retrieve the target from the encoder output. To further enhance the target representation, a feature interaction module (FIM) is devised to promote the information flow between the encoder and decoder. Moreover, we employ the Siamese architecture to extract backbone features of both past and current frames, which enables feature reuse and is more efficient than existing methods. Experimental results on three challenging benchmarks validate the superiority of SITVOS over state-of-the-art methods.

cs.CV↗

arXiv2021

Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction

Vision transformer networks have shown superiority in many computer vision tasks. In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for salient object detection. Both the vision transformer network and the energy-based prior model are jointly trained via Markov chain Monte Carlo-based maximum likelihood estimation, in which the sampling from the intractable posterior and prior distributions of the latent variables are performed by Langevin dynamics. Further, with the generative vision transformer, we can easily obtain a pixel-wise uncertainty map from an image, which indicates the model confidence in predicting saliency from the image. Different from the existing generative models which define the prior distribution of the latent variables as a simple isotropic Gaussian distribution, our model uses an energy-based informative prior which can be more expressive to capture the latent space of the data. We apply the proposed framework to both RGB and RGB-D salient object detection tasks. Extensive experimental results show that our framework can achieve not only accurate saliency predictions but also meaningful uncertainty maps that are consistent with the human perception.

cs.CV↗

arXiv2021

ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias

Transformers have shown great potential in various computer vision tasks owing to their strong capability in modeling long-range dependency using the self-attention mechanism. Nevertheless, vision transformers treat an image as 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance. Alternatively, they require large-scale training data and longer training schedules to learn the IB implicitly. In this paper, we propose a novel Vision Transformer Advanced by Exploring intrinsic IB from convolutions, ie, ViTAE. Technically, ViTAE has several spatial pyramid reduction modules to downsample and embed the input image into tokens with rich multi-scale context by using multiple convolutions with different dilation rates. In this way, it acquires an intrinsic scale invariance IB and is able to learn robust feature representation for objects at various scales. Moreover, in each transformer layer, ViTAE has a convolution block in parallel to the multi-head self-attention module, whose features are fused and fed into the feed-forward network. Consequently, it has the intrinsic locality IB and is able to learn local features and global dependencies collaboratively. Experiments on ImageNet as well as downstream tasks prove the superiority of ViTAE over the baseline transformer and concurrent works. Source code and pretrained models will be available at GitHub.

cs.CV↗

arXiv2021

Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition

Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual semantics within and between character instances, making them not generalize well to arbitrary shape scene text. To address this issue, we make the first attempt to perform textual reasoning based on visual semantics in this paper. Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity. Then, these subgraphs are sequentially connected by their root nodes and merged into a complete graph. Based on this graph, we devise a graph convolutional network for textual reasoning (GTR) by supervising it with a cross-entropy loss. GTR can be easily plugged in representative STR models to improve their performance owing to better textual reasoning. Specifically, we construct our model, namely S-GTR, by paralleling GTR to the language model in a segmentation-based STR baseline, which can effectively exploit the visual-linguistic complementarity via mutual learning. S-GTR sets new state-of-the-art on six challenging STR benchmarks and generalizes well to multi-linguistic datasets. Code is available at https://github.com/adeline-cs/GTR.

cs.CV↗

arXiv2021

AI-Aided Online Adaptive OFDM Receiver: Design and Experimental Results

Orthogonal frequency division multiplexing (OFDM) has been widely applied in current communication systems. The artificial intelligence (AI)-aided OFDM receivers are currently brought to the forefront to replace and improve the traditional OFDM receivers. In this study, we first compare two AI-aided OFDM receivers, namely, data-driven fully connected deep neural network and model-driven ComNet, through extensive simulation and real-time video transmission using a 5G rapid prototyping system for an over-the-air (OTA) test. We find a performance gap between the simulation and the OTA test caused by the discrepancy between the channel model for offline training and the real environment. We develop a novel online training system, which is called SwitchNet receiver, to address this issue. This receiver has a flexible and extendable architecture and can adapt to real channels by training only several parameters online. From the OTA test, the AI-aided OFDM receivers, especially the SwitchNet receiver, are robust to real environments and promising for future communication systems. We discuss potential challenges and future research inspired by our initial study in this paper.

eess.SP↗

arXiv2021

Residual Matrix Product State for Machine Learning

Tensor network, which originates from quantum physics, is emerging as an efficient tool for classical and quantum machine learning. Nevertheless, there still exists a considerable accuracy gap between tensor network and the sophisticated neural network models for classical machine learning. In this work, we combine the ideas of matrix product state (MPS), the simplest tensor network structure, and residual neural network and propose the residual matrix product state (ResMPS). The ResMPS can be treated as a network where its layers map the "hidden" features to the outputs (e.g., classifications), and the variational parameters of the layers are the functions of the features of the samples (e.g., pixels of images). This is different from neural network, where the layers map feed-forwardly the features to the output. The ResMPS can equip with the non-linear activations and dropout layers, and outperforms the state-of-the-art tensor network models in terms of efficiency, stability, and expression power. Besides, ResMPS is interpretable from the perspective of polynomial expansion, where the factorization and exponential machines naturally emerge. Our work contributes to connecting and hybridizing neural and tensor networks, which is crucial to further enhance our understand of the working mechanisms and improve the performance of both models.

cs.LG↗

arXiv2021

Wide-angle Image Rectification: A Survey

Wide field-of-view (FOV) cameras, which capture a larger scene area than narrow FOV cameras, are used in many applications including 3D reconstruction, autonomous driving, and video surveillance. However, wide-angle images contain distortions that violate the assumptions underlying pinhole camera models, resulting in object distortion, difficulties in estimating scene distance, area, and direction, and preventing the use of off-the-shelf deep models trained on undistorted images for downstream computer vision tasks. Image rectification, which aims to correct these distortions, can solve these problems. In this paper, we comprehensively survey progress in wide-angle image rectification from transformation models to rectification methods. Specifically, we first present a detailed description and discussion of the camera models used in different approaches. Then, we summarize several distortion models including radial distortion and projection distortion. Next, we review both traditional geometry-based image rectification methods and deep learning-based methods, where the former formulate distortion parameter estimation as an optimization problem and the latter treat it as a regression problem by leveraging the power of deep neural networks. We evaluate the performance of state-of-the-art methods on public datasets and show that although both kinds of methods can achieve good results, these methods only work well for specific camera models and distortion types. We also provide a strong baseline model and carry out an empirical study of different distortion models on synthetic datasets and real-world wide-angle images. Finally, we discuss several potential research directions that are expected to further advance this area in the future.

cs.CV↗