arXiv subjects

Feng Li

Publications and source records attributed to Feng Li.

At least 181 records · Page 10Linked to original sources

arXiv2023

Convolutional Neural Networks for Segmentation of Malignant Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance)

Malignant pleural mesothelioma (MPM) is the most common form of mesothelioma. To assess response to treatment, tumor measurements are acquired and evaluated based on a patient's longitudinal computed tomography (CT) scans. Tumor volume, however, is the more accurate metric for assessing tumor burden and response. Automated segmentation methods using deep learning can be employed to acquire volume, which otherwise is a tedious task performed manually. The deep learning-based tumor volume and contours can then be compared with a standard reference to assess the robustness of the automated segmentations. The purpose of this study was to evaluate the impact of probability map threshold on MPM tumor delineations generated using a convolutional neural network (CNN). Eighty-eight CT scans from 21 MPM patients were segmented by a VGG16/U-Net CNN. A radiologist modified the contours generated at a 0.5 probability threshold. Percent difference of tumor volume and overlap using the Dice Similarity Coefficient (DSC) were compared between the standard reference provided by the radiologist and CNN outputs for thresholds ranging from 0.001 to 0.9. CNN annotations consistently yielded smaller tumor volumes than radiologist contours. Reducing the probability threshold from 0.5 to 0.1 decreased the absolute percent volume difference, on average, from 43.96% to 24.18%. Median and mean DSC ranged from 0.58 to 0.60, with a peak at a threshold of 0.5; no distinct threshold was found for percent volume difference. No single output threshold in the CNN probability maps was optimal for both tumor volume and DSC. This work underscores the need to assess tumor volume and spatial overlap when evaluating CNN performance. While automated segmentations may yield comparable tumor volumes to that of the reference standard, the spatial region delineated by the CNN at a specific threshold is equally important.

eess.IV↗

arXiv2023

Infinite forecast combinations based on Dirichlet process

Forecast combination integrates information from various sources by consolidating multiple forecast results from the target time series. Instead of the need to select a single optimal forecasting model, this paper introduces a deep learning ensemble forecasting model based on the Dirichlet process. Initially, the learning rate is sampled with three basis distributions as hyperparameters to convert the infinite mixture into a finite one. All checkpoints are collected to establish a deep learning sub-model pool, and weight adjustment and diversity strategies are developed during the combination process. The main advantage of this method is its ability to generate the required base learners through a single training process, utilizing the decaying strategy to tackle the challenge posed by the stochastic nature of gradient descent in determining the optimal learning rate. To ensure the method's generalizability and competitiveness, this paper conducts an empirical analysis using the weekly dataset from the M4 competition and explores sensitivity to the number of models to be combined. The results demonstrate that the ensemble model proposed offers substantial improvements in prediction accuracy and stability compared to a single benchmark model.

cs.LG↗

arXiv2023

T-Rex: Counting by Visual Prompting

We introduce T-Rex, an interactive object counting model designed to first detect and then count any objects. We formulate object counting as an open-set object detection task with the integration of visual prompts. Users can specify the objects of interest by marking points or boxes on a reference image, and T-Rex then detects all objects with a similar pattern. Guided by the visual feedback from T-Rex, users can also interactively refine the counting results by prompting on missing or falsely-detected objects. T-Rex has achieved state-of-the-art performance on several class-agnostic counting benchmarks. To further exploit its potential, we established a new counting benchmark encompassing diverse scenarios and challenges. Both quantitative and qualitative results show that T-Rex possesses exceptional zero-shot counting capabilities. We also present various practical application scenarios for T-Rex, illustrating its potential in the realm of visual prompting.

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

Probabilistic Forecast Reconciliation with Kullback-Leibler Divergence Regularization

As the popularity of hierarchical point forecast reconciliation methods increases, there is a growing interest in probabilistic forecast reconciliation. Many studies have utilized machine learning or deep learning techniques to implement probabilistic forecasting reconciliation and have made notable progress. However, these methods treat the reconciliation step as a fixed and hard post-processing step, leading to a trade-off between accuracy and coherency. In this paper, we propose a new approach for probabilistic forecast reconciliation. Unlike existing approaches, our proposed approach fuses the prediction step and reconciliation step into a deep learning framework, making the reconciliation step more flexible and soft by introducing the Kullback-Leibler divergence regularization term into the loss function. The approach is evaluated using three hierarchical time series datasets, which shows the advantages of our approach over other probabilistic forecast reconciliation methods.

cs.AI↗

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

An Approach for Multi-Object Tracking with Two-Stage Min-Cost Flow

The minimum network flow algorithm is widely used in multi-target tracking. However, the majority of the present methods concentrate exclusively on minimizing cost functions whose values may not indicate accurate solutions under occlusions. In this paper, by exploiting the properties of tracklets intersections and low-confidence detections, we develop a two-stage tracking pipeline with an intersection mask that can accurately locate inaccurate tracklets which are corrected in the second stage. Specifically, we employ the minimum network flow algorithm with high-confidence detections as input in the first stage to obtain the candidate tracklets that need correction. Then we leverage the intersection mask to accurately locate the inaccurate parts of candidate tracklets. The second stage utilizes low-confidence detections that may be attributed to occlusions for correcting inaccurate tracklets. This process constructs a graph of nodes in inaccurate tracklets and low-confidence nodes and uses it for the second round of minimum network flow calculation. We perform sufficient experiments on popular MOT benchmark datasets and achieve 78.4 MOTA on the test set of MOT16, 79.2 on MOT17, and 76.4 on MOT20, which shows that the proposed method is effective.

cs.CV↗

arXiv2023

Effective potential engineering by emergent anisotropy in a tunable open-access microcavity

Photonic spin-orbit (SO) coupling is an important physical mechanism leading to numerous interesting phenomena in the systems of microcavity photons and exciton-polaritons. We report the effect of SO coupling in a tunable open-access microcavity embedded with anisotropic active media. The SO coupling associated with the TE-TM splitting results in an emergent anisotropy, which further leads to fine energy splittings allowing clear observation of the full set of eigenstates, in sharp contrast with the isotropic situation which leads to the isotropic eigenstates of spin vortices. We show that the photonic potential can be engineered by playing with the relation between the emergent anisotropy and the cavity ellipticity. All the experimental results are well reproduced by the degenerate perturbation theory. Our results constitute a significant extension to the research field of microcavity spinoptronics, with potential applications in polarization control and optical property measurement of photonic devices and materials.

physics.optics↗

arXiv2023

Deep Charge: A Deep Learning Model of Electron Density from One-Shot Density Functional Theory Calculation

Electron charge density is a fundamental physical quantity, determining various properties of matter. In this study, we have proposed a deep-learning model for accurate charge density prediction. Our model naturally preserves physical symmetries and can be effectively trained from one-shot density functional theory calculation toward high accuracy. It captures detailed atomic environment information, ensuring accurate predictions of charge density across bulk, surface, molecules, and amorphous structures. This implementation exhibits excellent scalability and provides efficient analyses of material properties in large-scale condensed matter systems.

cond-mat.mtrl-sci↗

arXiv2023

Forecasting large collections of time series: feature-based methods

In economics and many other forecasting domains, the real world problems are too complex for a single model that assumes a specific data generation process. The forecasting performance of different methods changes depending on the nature of the time series. When forecasting large collections of time series, two lines of approaches have been developed using time series features, namely feature-based model selection and feature-based model combination. This chapter discusses the state-of-the-art feature-based methods, with reference to open-source software implementations.

cs.LG↗

arXiv2023

Nilpotent center conditions in cubic switching polynomial Liénard systems by higher-order analysis

The aim of this paper is to investigate two classical problems related to nilpotent center conditions and bifurcation of limit cycles in switching polynomial systems. Due to the difficulty in calculating the Lyapunov constants of switching polynomial systems at non-elementary singular points, it is extremely difficult to use the existing Poincaré-Lyapunov method to study these two problems. In this paper, we develop a higher-order Poincaré-Lyapunov method to consider the nilpotent center problem in switching polynomial systems, with particular attention focused on cubic switching Liénard systems. With proper perturbations, explicit center conditions are derived for switching Liénard systems at a nilpotent center, which is characterized as global. Moreover, with Bogdanov-Takens bifurcation theory, the existence of five limit cycles around the nilpotent center is proved for a class of switching Liénard systems, which is a new lower bound of cyclicity for such polynomial systems around a nilpotent center.

math.DS↗

arXiv2023

Neural Interactive Keypoint Detection

This work proposes an end-to-end neural interactive keypoint detection framework named Click-Pose, which can significantly reduce more than 10 times labeling costs of 2D keypoint annotation compared with manual-only annotation. Click-Pose explores how user feedback can cooperate with a neural keypoint detector to correct the predicted keypoints in an interactive way for a faster and more effective annotation process. Specifically, we design the pose error modeling strategy that inputs the ground truth pose combined with four typical pose errors into the decoder and trains the model to reconstruct the correct poses, which enhances the self-correction ability of the model. Then, we attach an interactive human-feedback loop that allows receiving users' clicks to correct one or several predicted keypoints and iteratively utilizes the decoder to update all other keypoints with a minimum number of clicks (NoC) for efficient annotation. We validate Click-Pose in in-domain, out-of-domain scenes, and a new task of keypoint adaptation. For annotation, Click-Pose only needs 1.97 and 6.45 NoC@95 (at precision 95%) on COCO and Human-Art, reducing 31.4% and 36.3% efforts than the SOTA model (ViTPose) with manual correction, respectively. Besides, without user clicks, Click-Pose surpasses the previous end-to-end model by 1.4 AP on COCO and 3.0 AP on Human-Art. The code is available at https://github.com/IDEA-Research/Click-Pose.

cs.CV↗

arXiv2023

Soliton frequency comb generation in a low Q microcavity coupled to a gain microcavity

Soliton frequency comb generation in coupled nonlinear microcavities is attractive because a coupled microcavity offers more flexibility and possibilities compared to a single nonlinear microcavity. In this paper, we investigate how an amplifying auxiliary cavity affects the bistability region of the main cavity and soliton frequency comb generation. When the auxiliary cavity has a small gain, it can partially compensate for the loss of the main cavity allowing the generation of soliton combs with a relatively low Q-factor in the main cavity. A low Q-factor microcavity would reduce the difficulty of fabrication and extend the microcavity platform to different types of materials. However, if the gain of the auxiliary cavity is too large, a frequency comb cannot be generated because the coupled nonlinear microcavity system is no longer dissipative. Our results provide a theoretical understanding and experimental guidance for the bistability region and soliton frequency comb generation in coupled nonlinear microcavities with an amplifying auxiliary cavity. The results will facilitate the development of chip-scale integrated optical frequency comb sources.

physics.optics↗

arXiv2023

A Forecaster's Review of Judea Pearl's Causality: Models, Reasoning and Inference, Second Edition, 2009

With the big popularity and success of Judea Pearl's original causality book, this review covers the main topics updated in the second edition in 2009 and illustrates an easy-to-follow causal inference strategy in a forecast scenario. It further discusses some potential benefits and challenges for causal inference with time series forecasting when modeling the counterfactuals, estimating the uncertainty and incorporating prior knowledge to estimate causal effects in different forecasting scenarios.

stat.ME↗

arXiv2023

Efficient near-infrared organic light-emitting diodes with emission from spin doublet excitons

The development of luminescent organic radicals has resulted in materials with excellent optical properties for near-infrared (NIR) emission. Applications of light generation in this range span from bioimaging to surveillance. Whilst the unpaired electron arrangements of radicals enable efficient radiative transitions within the doublet-spin manifold in organic light-emitting diodes (OLEDs), their performance is limited by non-radiative pathways introduced in electroluminescence. Here, we present a host:guest design for OLEDs that exploits energy transfer with demonstration of up to 9.6% external quantum efficiency (EQE) for 800 nm emission. The tris(2,4,6-trichlorophenyl)methyl-triphenylamine (TTM-TPA) radical guest is energy-matched to the triplet state in a charge-transporting anthracene-derivative host. We show from optical spectroscopy and quantum-chemical modelling that reversible host-guest triplet-doublet energy transfer allows efficient harvesting of host triplet excitons.

physics.app-ph↗

arXiv2023

Nonlinear Topological Mechanics in Elliptically Geared Isostatic Metamaterials

Despite the extensive studies of topological systems, the experimental characterizations of strongly nonlinear topological phases have been lagging. To address this shortcoming, we design and build elliptically geared isostatic metamaterials. Their nonlinear topological transitions can be realized by collective soliton motions, which stem from the transition of nonlinear Berry phase. Endowed by the intrinsic nonlinear topological mechanics, surface polar elasticity and dislocation-bound zero modes can be created or annihilated as the topological polarization reverses orientation. Our approach integrates topological physics with strongly nonlinear mechanics and promises multi-phase structures at the micro and macro scales.

cond-mat.mtrl-sci↗

arXiv2023

DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting

In this paper, we propose a new operator, called 3D DeFormable Attention (DFA3D), for 2D-to-3D feature lifting, which transforms multi-view 2D image features into a unified 3D space for 3D object detection. Existing feature lifting approaches, such as Lift-Splat-based and 2D attention-based, either use estimated depth to get pseudo LiDAR features and then splat them to a 3D space, which is a one-pass operation without feature refinement, or ignore depth and lift features by 2D attention mechanisms, which achieve finer semantics while suffering from a depth ambiguity problem. In contrast, our DFA3D-based method first leverages the estimated depth to expand each view's 2D feature map to 3D and then utilizes DFA3D to aggregate features from the expanded 3D feature maps. With the help of DFA3D, the depth ambiguity problem can be effectively alleviated from the root, and the lifted features can be progressively refined layer by layer, thanks to the Transformer-like architecture. In addition, we propose a mathematically equivalent implementation of DFA3D which can significantly improve its memory efficiency and computational speed. We integrate DFA3D into several methods that use 2D attention-based feature lifting with only a few modifications in code and evaluate on the nuScenes dataset. The experiment results show a consistent improvement of +1.41\% mAP on average, and up to +15.1\% mAP improvement when high-quality depth information is available, demonstrating the superiority, applicability, and huge potential of DFA3D. The code is available at https://github.com/IDEA-Research/3D-deformable-attention.git.

cs.CV↗