arXiv subjects

Hao Zhang

Publications and source records attributed to Hao Zhang.

At least 775 records · Page 43Linked to original sources

arXiv2023

Revisiting Single Image Reflection Removal In the Wild

This research focuses on the issue of single-image reflection removal (SIRR) in real-world conditions, examining it from two angles: the collection pipeline of real reflection pairs and the perception of real reflection locations. We devise an advanced reflection collection pipeline that is highly adaptable to a wide range of real-world reflection scenarios and incurs reduced costs in collecting large-scale aligned reflection pairs. In the process, we develop a large-scale, high-quality reflection dataset named Reflection Removal in the Wild (RRW). RRW contains over 14,950 high-resolution real-world reflection pairs, a dataset forty-five times larger than its predecessors. Regarding perception of reflection locations, we identify that numerous virtual reflection objects visible in reflection images are not present in the corresponding ground-truth images. This observation, drawn from the aligned pairs, leads us to conceive the Maximum Reflection Filter (MaxRF). The MaxRF could accurately and explicitly characterize reflection locations from pairs of images. Building upon this, we design a reflection location-aware cascaded framework, specifically tailored for SIRR. Powered by these innovative techniques, our solution achieves superior performance than current leading methods across multiple real-world benchmarks. Codes and datasets will be publicly available.

cs.CV↗

arXiv2023

ShaDDR: Interactive Example-Based Geometry and Texture Generation via 3D Shape Detailization and Differentiable Rendering

We present ShaDDR, an example-based deep generative neural network which produces a high-resolution textured 3D shape through geometry detailization and conditional texture generation applied to an input coarse voxel shape. Trained on a small set of detailed and textured exemplar shapes, our method learns to detailize the geometry via multi-resolution voxel upsampling and generate textures on voxel surfaces via differentiable rendering against exemplar texture images from a few views. The generation is interactive, taking less than 1 second to produce a 3D model with voxel resolutions up to 512^3. The generated shape preserves the overall structure of the input coarse voxel model, while the style of the generated geometric details and textures can be manipulated through learned latent codes. In the experiments, we show that our method can generate higher-resolution shapes with plausible and improved geometric details and clean textures compared to prior works. Furthermore, we showcase the ability of our method to learn geometric details and textures from shapes reconstructed from real-world photos. In addition, we have developed an interactive modeling application to demonstrate the generalizability of our method to various user inputs and the controllability it offers, allowing users to interactively sculpt a coarse voxel shape to define the overall structure of the detailized 3D shape. Code and data are available at https://github.com/qiminchen/ShaDDR.

cs.CV↗

arXiv2023

Visual In-Context Prompting

In-context prompting in large language models (LLMs) has become a prevalent approach to improve zero-shot capabilities, but this idea is less explored in the vision domain. Existing visual prompting methods focus on referring segmentation to segment the most relevant object, falling short of addressing many generic vision tasks like open-set segmentation and detection. In this paper, we introduce a universal visual in-context prompting framework for both tasks. In particular, we build on top of an encoder-decoder architecture, and develop a versatile prompt encoder to support a variety of prompts like strokes, boxes, and points. We further enhance it to take an arbitrary number of reference image segments as the context. Our extensive explorations show that the proposed visual in-context prompting elicits extraordinary referring and generic segmentation capabilities to refer and detect, yielding competitive performance to close-set in-domain datasets and showing promising results on many open-set segmentation datasets. By joint training on COCO and SA-1B, our model achieves $57.7$ PQ on COCO and $23.2$ PQ on ADE20K. Code will be available at https://github.com/UX-Decoder/DINOv.

cs.CV↗

arXiv2023

Role Taxonomy of Units in Deep Neural Networks

Identifying the role of network units in deep neural networks (DNNs) is critical in many aspects including giving understandings on the mechanisms of DNNs and building basic connections between deep learning and neuroscience. However, there remains unclear on which roles the units in DNNs with different generalization ability could present. To this end, we give role taxonomy of units in DNNs via introducing the retrieval-of-function test, where units are categorized into four types in terms of their functional preference on separately the training set and testing set. We show that ratios of the four categories are highly associated with the generalization ability of DNNs from two distinct perspectives, based on which we give signs of DNNs with well generalization.

cs.CV↗

arXiv2023

Estimating the Generalization in Deep Neural Networks via Sparsity

Generalization is the key capability for deep neural networks (DNNs). However, it is challenging to give a reliable measure of the generalization ability of a DNN via only its nature. In this paper, we propose a novel method for estimating the generalization gap based on network sparsity. In our method, two key quantities are proposed first. They have close relationship with the generalization ability and can be calculated directly from the training results alone. Then a simple linear model involving two key quantities are constructed to give accurate estimation of the generalization gap. By training DNNs with a wide range of generalization gap on popular datasets, we show that our key quantities and linear model could be efficient tools for estimating the generalization gap of DNNs.

cs.CV↗

arXiv2023

Vacuum Decay in Time-Dependent Backgrounds

We develop semiclassical methods for studying bubble nucleation in models with parameters that vary slowly in time. Introducing a more general rotation of the time contour allows access to a larger set of final states, and typically a non-Euclidean rotation is necessary in order to find the most relevant tunneling solution. We work primarily with effective quantum mechanical models parametrizing tunneling along restricted trajectories in field theories, which are sufficient, for example, to study thin wall bubble nucleation. We also give one example of an exact instanton solution in a particular Kaluza-Klein cosmology where the circumference of the internal circle is changing in time.

hep-th↗

arXiv2023

Future Full-Ocean Deep SSPs Prediction based on Hierarchical Long Short-Term Memory Neural Networks

The spatial-temporal distribution of underwater sound velocity affects the propagation mode of underwater acoustic signals. Therefore, rapid estimation and prediction of underwater sound velocity distribution is crucial for providing underwater positioning, navigation and timing (PNT) services. Currently, sound speed profile (SSP) inversion methods have a faster time response rate compared to direct measurement methods, however, most SSP inversion methods focus on constructing spatial dimensional sound velocity fields and are highly dependent on sonar observation data, thus high requirements have been placed on observation data sources. To explore the distribution pattern of sound velocity in the time dimension and achieve future SSP prediction without sonar observation data, we propose a hierarchical long short-term memory (H-LSTM) neural network for SSP prediction. By our SSP prediction method, the sound speed distribution could be estimated without any on-site data measurement process, so that the time efficiency could be greatly improved. Through comparing with other state-of-the-art methods, H-LSTM has better accuracy performance on prediction of monthly average sound velocity distribution, which is less than 1 m/s in different depth layers.

cs.SD↗

arXiv2023

Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box

With the rapid development of detectors, Bounding Box Regression (BBR) loss function has constantly updated and optimized. However, the existing IoU-based BBR still focus on accelerating convergence by adding new loss terms, ignoring the limitations of IoU loss term itself. Although theoretically IoU loss can effectively describe the state of bounding box regression,in practical applications, it cannot adjust itself according to different detectors and detection tasks, and does not have strong generalization. Based on the above, we first analyzed the BBR model and concluded that distinguishing different regression samples and using different scales of auxiliary bounding boxes to calculate losses can effectively accelerate the bounding box regression process. For high IoU samples, using smaller auxiliary bounding boxes to calculate losses can accelerate convergence, while larger auxiliary bounding boxes are suitable for low IoU samples. Then, we propose Inner-IoU loss, which calculates IoU loss through auxiliary bounding boxes. For different datasets and detectors, we introduce a scaling factor ratio to control the scale size of the auxiliary bounding boxes for calculating losses. Finally, integrate Inner-IoU into the existing IoU-based loss functions for simulation and comparative experiments. The experiment result demonstrate a further enhancement in detection performance with the utilization of the method proposed in this paper, verifying the effectiveness and generalization ability of Inner-IoU loss. Code is available at https://github.com/malagoutou/Inner-IoU.

cs.CV↗

arXiv2023

LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents

LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models. It maintains a skill repository of pre-trained vision and vision-language models and can activate relevant tools based on users' inputs to fulfill real-world tasks. LLaVA-Plus is trained on multimodal instruction-following data to acquire the ability to use tools, covering visual understanding, generation, external knowledge retrieval, and compositions. Empirical results show that LLaVA-Plus outperforms LLaVA in existing capabilities and exhibits new ones. It is distinct in that the image query is directly grounded and actively engaged throughout the entire human-AI interaction sessions, significantly improving tool use performance and enabling new scenarios.

cs.CV↗

arXiv2023

Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

We present Set-of-Mark (SoM), a new visual prompting method, to unleash the visual grounding abilities of large multimodal models (LMMs), such as GPT-4V. As illustrated in Fig. 1 (right), we employ off-the-shelf interactive segmentation models, such as SEEM/SAM, to partition an image into regions at different levels of granularity, and overlay these regions with a set of marks e.g., alphanumerics, masks, boxes. Using the marked image as input, GPT-4V can answer the questions that require visual grounding. We perform a comprehensive empirical study to validate the effectiveness of SoM on a wide range of fine-grained vision and multimodal tasks. For example, our experiments show that GPT-4V with SoM in zero-shot setting outperforms the state-of-the-art fully-finetuned referring expression comprehension and segmentation model on RefCOCOg. Code for SoM prompting is made public at: https://github.com/microsoft/SoM.

cs.CV↗

arXiv2023

Few-shot Learning using Data Augmentation and Time-Frequency Transformation for Time Series Classification

Deep neural networks (DNNs) that tackle the time series classification (TSC) task have provided a promising framework in signal processing. In real-world applications, as a data-driven model, DNNs are suffered from insufficient data. Few-shot learning has been studied to deal with this limitation. In this paper, we propose a novel few-shot learning framework through data augmentation, which involves transformation through the time-frequency domain and the generation of synthetic images through random erasing. Additionally, we develop a sequence-spectrogram neural network (SSNN). This neural network model composes of two sub-networks: one utilizing 1D residual blocks to extract features from the input sequence while the other one employing 2D residual blocks to extract features from the spectrogram representation. In the experiments, comparison studies of different existing DNN models with/without data augmentation are conducted on an amyotrophic lateral sclerosis (ALS) dataset and a wind turbine fault (WTF) dataset. The experimental results manifest that our proposed method achieves 93.75% F1 score and 93.33% accuracy on the ALS datasets while 95.48% F1 score and 95.59% accuracy on the WTF datasets. Our methodology demonstrates its applicability of addressing the few-shot problems for time series classification.

cs.CV↗

arXiv2023

Spatial Process Approximations: Assessing Their Necessity

In spatial statistics and machine learning, the kernel matrix plays a pivotal role in prediction, classification, and maximum likelihood estimation. A thorough examination reveals that for large sample sizes, the kernel matrix becomes ill-conditioned, provided the sampling locations are fairly evenly distributed. This condition poses significant challenges to numerical algorithms used in prediction and estimation computations and necessitates an approximation to prediction and the Gaussian likelihood. A review of current methodologies for managing large spatial data indicates that some fail to address this ill-conditioning problem. Such ill-conditioning often results in low-rank approximations of the stochastic processes. This paper introduces various optimality criteria and provides solutions for each.

stat.ML↗

arXiv2023

Improvement of response bandwidth and sensitivity of Rydberg Receiver using multi-channel excitations

We investigate the response bandwidth of a superheterodyne Rydberg receiver at a room-temperature vapor cell, and present an architecture of multi-channel lasers excitation to increase the response bandwidth and keep sensitivity, simultaneously. Two microwave fields, denoted as a local oscillator (LO) $E_{LO}$ and a signal field $E_{Sig}$, couple two Rydberg states transition of $|52D_{5/2}\rangle\to |53P_{3/2}\rangle$. In the presence of the LO field, the frequency difference between two fields can be read out as an intermediate frequency (IF) signal using Rydberg electromagnetically induced transparency (EIT) spectroscopy. The bandwidth of the Rydberg receiver is obtained by measuring the output power of IF signal versus the frequency difference between two fields. The bandwidth dependence on the Rabi frequency of excitation lasers is presented, which shows the bandwidth decrease with the probe Rabi frequency, while it is quadratic dependence on the coupling Rabi frequency. Meanwhile, we investigate the effect of probe laser waist on the bandwidth, showing that the bandwidth is inversely proportional to the laser waist. We achieve a maximum response bandwidth of the receiver about 6.8~MHz. Finally, we design an architecture of multi-channel lasers excitation for increasing the response and keeping the sensitivity, simultaneously. Our work has the potential to extend the applications of Rydberg atoms in communications.

physics.atom-ph↗

arXiv2023

DiViNeT: 3D Reconstruction from Disparate Views via Neural Template Regularization

We present a volume rendering-based neural surface reconstruction method that takes as few as three disparate RGB images as input. Our key idea is to regularize the reconstruction, which is severely ill-posed and leaving significant gaps between the sparse views, by learning a set of neural templates to act as surface priors. Our method, coined DiViNet, operates in two stages. It first learns the templates, in the form of 3D Gaussian functions, across different scenes, without 3D supervision. In the reconstruction stage, our predicted templates serve as anchors to help "stitch'' the surfaces over sparse regions. We demonstrate that our approach is not only able to complete the surface geometry but also reconstructs surface details to a reasonable extent from a few disparate input views. On the DTU and BlendedMVS datasets, our approach achieves the best reconstruction quality among existing methods in the presence of such sparse views and performs on par, if not better, with competing methods when dense views are employed as inputs.

cs.CV↗

arXiv2023

Large zeta sums

In this article, we investigate the behaviour of values of zeta sums $\sum_{n\le x}n^{it}$ when $t$ is large. We show some asymptotic behaviour and Omega results of zeta sums, which are analogous to previous results of large character sums $\sum_{n\le x}χ(n)$.

math.NT↗

arXiv2023

Sentence Bag Graph Formulation for Biomedical Distant Supervision Relation Extraction

We introduce a novel graph-based framework for alleviating key challenges in distantly-supervised relation extraction and demonstrate its effectiveness in the challenging and important domain of biomedical data. Specifically, we propose a graph view of sentence bags referring to an entity pair, which enables message-passing based aggregation of information related to the entity pair over the sentence bag. The proposed framework alleviates the common problem of noisy labeling in distantly supervised relation extraction and also effectively incorporates inter-dependencies between sentences within a bag. Extensive experiments on two large-scale biomedical relation datasets and the widely utilized NYT dataset demonstrate that our proposed framework significantly outperforms the state-of-the-art methods for biomedical distant supervision relation extraction while also providing excellent performance for relation extraction in the general text mining domain.

cs.LG↗

arXiv2023

TLM: Token-Level Masking for Transformers

Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers. In this paper, we propose a new regularization scheme based on token-level rather than structure-level to reduce overfitting. Specifically, we devise a novel Token-Level Masking (TLM) training strategy for Transformers to regularize the connections of self-attention, which consists of two masking techniques that are effective and easy to implement. The underlying idea is to manipulate the connections between tokens in the multi-head attention via masking, where the networks are forced to exploit partial neighbors' information to produce a meaningful representation. The generality and effectiveness of TLM are thoroughly evaluated via extensive experiments on 4 diversified NLP tasks across 18 datasets, including natural language understanding benchmark GLUE, ChineseGLUE, Chinese Grammatical Error Correction, and data-to-text generation. The results indicate that TLM can consistently outperform attention dropout and DropHead, e.g., it increases by 0.5 points relative to DropHead with BERT-large on GLUE. Moreover, TLM can establish a new record on the data-to-text benchmark Rotowire (18.93 BLEU). Our code will be publicly available at https://github.com/Young1993/tlm.

cs.CL↗

arXiv2023

Regularized Data Programming with Automated Bayesian Prior Selection

The cost of manual data labeling can be a significant obstacle in supervised learning. Data programming (DP) offers a weakly supervised solution for training dataset creation, wherein the outputs of user-defined programmatic labeling functions (LFs) are reconciled through unsupervised learning. However, DP can fail to outperform an unweighted majority vote in some scenarios, including low-data contexts. This work introduces a Bayesian extension of classical DP that mitigates failures of unsupervised learning by augmenting the DP objective with regularization terms. Regularized learning is achieved through maximum a posteriori estimation with informative priors. Majority vote is proposed as a proxy signal for automated prior parameter selection. Results suggest that regularized DP improves performance relative to maximum likelihood and majority voting, confers greater interpretability, and bolsters performance in low-data regimes.

cs.LG↗