arXiv subjects

Jingwen Li

Publications and source records attributed to Jingwen Li.

At least 37 records · Page 2Linked to original sources

arXiv2024

Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

Interactive Medical Image Segmentation (IMIS) has long been constrained by the limited availability of large-scale, diverse, and densely annotated datasets, which hinders model generalization and consistent evaluation across different models. In this paper, we introduce the IMed-361M benchmark dataset, a significant advancement in general IMIS research. First, we collect and standardize over 6.4 million medical images and their corresponding ground truth masks from multiple data sources. Then, leveraging the strong object recognition capabilities of a vision foundational model, we automatically generated dense interactive masks for each image and ensured their quality through rigorous quality control and granularity management. Unlike previous datasets, which are limited by specific modalities or sparse annotations, IMed-361M spans 14 modalities and 204 segmentation targets, totaling 361 million masks-an average of 56 masks per image. Finally, we developed an IMIS baseline network on this dataset that supports high-quality mask generation through interactive inputs, including clicks, bounding boxes, text prompts, and their combinations. We evaluate its performance on medical image segmentation tasks from multiple perspectives, demonstrating superior accuracy and scalability compared to existing interactive segmentation models. To facilitate research on foundational models in medical computer vision, we release the IMed-361M and model at https://github.com/uni-medical/IMIS-Bench.

cs.CV↗

arXiv2024

Global Alignment Reference Strategy for Laser Interference Lithography Pattern Arrays

Large-area gratings play a crucial role in various engineering fields. However, traditional interference lithography is limited by the size of optical component apertures, making large-area fabrication a challenging task. Here, a method for fabricating laser interference lithography pattern arrays with a global alignment reference strategy is proposed. This approach enables alignment of each area of the laser interference lithography pattern arrays, including phase, period, and tilt angle. Two reference gratings are utilized: one is detached from the substrate, while the other remains fixed to it. To achieve global alignment, the exposure area is adjusted by alternating between moving the beam and the substrate. In our experiment, a 3 $\times$ 3 regions grating array was fabricated, and the $-1$st-order diffraction wavefront measured by the Fizeau interferometer exhibited good continuity. This technique enables effective and efficient alignment with high accuracy across any regions in an interference lithography pattern array on large substrates.

physics.optics↗

arXiv2024

Functional control of anomalous reflection via engineered metagratings without polarization limitations

Metagratings (MGs) have emerged as a promising platform for manipulating the anomalous propagation of electromagnetic waves. However, traditional methods for designing functional MG-based devices face significant challenges, including complex model structures, time-consuming optimization processes, and specific polarization requirements. In this work, we propose an inverse-design approach to engineer simple MG structures comprising periodic air grooves on a flat metal surface, which can control anomalous reflection without polarization limitations. Through rigorous analytical methods, we derive solutions that achieve perfect retroreflection and perfect specular reflection, thereby leading to functional control over the linearly-polarized electromagnetic waves. Such capabilities enable intriguing functionalities including polarization-dependent retroreflection and polarization-independent retroreflection, as confirmed through full-wave simulations. Our work offers a simple and effective method to control freely electromagnetic waves, with potential applications spanning wavefront engineering, polarization splitting, cloaking technologies, and remote sensing.

physics.optics↗

arXiv2024

Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR

In recent years, impressive performance of deep learning technology has been recognized in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). Since a large amount of annotated data is required in this technique, it poses a trenchant challenge to the issue of obtaining a high recognition rate through less labeled data. To overcome this problem, inspired by the contrastive learning, we proposed a novel framework named Batch Instance Discrimination and Feature Clustering (BIDFC). In this framework, different from that of the objective of general contrastive learning methods, embedding distance between samples should be moderate because of the high similarity between samples in the SAR images. Consequently, our flexible framework is equipped with adjustable distance between embedding, which we term as weakly contrastive learning. Technically, instance labels are assigned to the unlabeled data in per batch and random augmentation and training are performed few times on these augmented data. Meanwhile, a novel Dynamic-Weighted Variance loss (DWV loss) function is also posed to cluster the embedding of enhanced versions for each sample. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) database indicate a 91.25% classification accuracy of our method fine-tuned on only 3.13% training data. Even though a linear evaluation is performed on the same training data, the accuracy can still reach 90.13%. We also verified the effectiveness of BIDFC in OpenSarShip database, indicating that our method can be generalized to other datasets. Our code is avaliable at: https://github.com/Wenlve-Zhou/BIDFC-master.

cs.CV↗

arXiv2024

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

We present InternLM-XComposer-2.5 (IXC-2.5), a versatile large-vision language model that supports long-contextual input and output. IXC-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend. Trained with 24K interleaved image-text contexts, it can seamlessly extend to 96K long contexts via RoPE extrapolation. This long-context capability allows IXC-2.5 to excel in tasks requiring extensive input and output contexts. Compared to its previous 2.0 version, InternLM-XComposer-2.5 features three major upgrades in vision-language comprehension: (1) Ultra-High Resolution Understanding, (2) Fine-Grained Video Understanding, and (3) Multi-Turn Multi-Image Dialogue. In addition to comprehension, IXC-2.5 extends to two compelling applications using extra LoRA parameters for text-image composition: (1) Crafting Webpages and (2) Composing High-Quality Text-Image Articles. IXC-2.5 has been evaluated on 28 benchmarks, outperforming existing open-source state-of-the-art models on 16 benchmarks. It also surpasses or competes closely with GPT-4V and Gemini Pro on 16 key tasks. The InternLM-XComposer-2.5 is publicly available at https://github.com/InternLM/InternLM-XComposer.

cs.CV↗

arXiv2024

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD

The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution. Recent efforts have aimed to enhance the high-resolution understanding capabilities of LVLMs, yet they remain capped at approximately 1500 x 1500 pixels and constrained to a relatively narrow resolution range. This paper represents InternLM-XComposer2-4KHD, a groundbreaking exploration into elevating LVLM resolution capabilities up to 4K HD (3840 x 1600) and beyond. Concurrently, considering the ultra-high resolution may not be necessary in all scenarios, it supports a wide range of diverse resolutions from 336 pixels to 4K standard, significantly broadening its scope of applicability. Specifically, this research advances the patch division paradigm by introducing a novel extension: dynamic resolution with automatic patch configuration. It maintains the training image aspect ratios while automatically varying patch counts and configuring layouts based on a pre-trained Vision Transformer (ViT) (336 x 336), leading to dynamic training resolution from 336 pixels to 4K standard. Our research demonstrates that scaling training resolution up to 4K HD leads to consistent performance enhancements without hitting the ceiling of potential improvements. InternLM-XComposer2-4KHD shows superb capability that matches or even surpasses GPT-4V and Gemini Pro in 10 of the 16 benchmarks. The InternLM-XComposer2-4KHD model series with 7B parameters are publicly available at https://github.com/InternLM/InternLM-XComposer.

cs.CV↗

arXiv2024

InternLM2 Technical Report

The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI). However, replicating such advancements in open-source models has been challenging. This paper introduces InternLM2, an open-source LLM that outperforms its predecessors in comprehensive evaluations across 6 dimensions and 30 benchmarks, long-context modeling, and open-ended subjective evaluations through innovative pre-training and optimization techniques. The pre-training process of InternLM2 is meticulously detailed, highlighting the preparation of diverse data types including text, code, and long-context data. InternLM2 efficiently captures long-term dependencies, initially trained on 4k tokens before advancing to 32k tokens in pre-training and fine-tuning stages, exhibiting remarkable performance on the 200k ``Needle-in-a-Haystack" test. InternLM2 is further aligned using Supervised Fine-Tuning (SFT) and a novel Conditional Online Reinforcement Learning from Human Feedback (COOL RLHF) strategy that addresses conflicting human preferences and reward hacking. By releasing InternLM2 models in different training stages and model sizes, we provide the community with insights into the model's evolution.

cs.CL↗

arXiv2024

InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model

We introduce InternLM-XComposer2, a cutting-edge vision-language model excelling in free-form text-image composition and comprehension. This model goes beyond conventional vision-language understanding, adeptly crafting interleaved text-image content from diverse inputs like outlines, detailed textual specifications, and reference images, enabling highly customizable content creation. InternLM-XComposer2 proposes a Partial LoRA (PLoRA) approach that applies additional LoRA parameters exclusively to image tokens to preserve the integrity of pre-trained language knowledge, striking a balance between precise vision understanding and text composition with literary talent. Experimental results demonstrate the superiority of InternLM-XComposer2 based on InternLM2-7B in producing high-quality long-text multi-modal content and its exceptional vision-language understanding performance across various benchmarks, where it not only significantly outperforms existing multimodal models but also matches or even surpasses GPT-4V and Gemini Pro in certain assessments. This highlights its remarkable proficiency in the realm of multimodal understanding. The InternLM-XComposer2 model series with 7B parameters are publicly available at https://github.com/InternLM/InternLM-XComposer.

cs.CV↗

arXiv2023

InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition

We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition. The innovative nature of our model is highlighted by three appealing properties: 1) Interleaved Text-Image Composition: InternLM-XComposer can effortlessly generate coherent and contextual articles that seamlessly integrate images, providing a more engaging and immersive reading experience. Simply provide a writing instruction, and our system will generate the corresponding manuscript. It can intelligently identify the areas in the text where images would enhance the content and automatically insert the most appropriate visual candidates. 2) Comprehension with Rich Multilingual Knowledge: The text-image comprehension is empowered by training on an extensive multi-modal multilingual database with carefully crafted strategies, resulting in a deep understanding of visual content. 3) State-of-the-art Performance: Our model consistently achieves state-of-the-art results across various mainstream benchmarks for vision-language foundational models, including MME Benchmark, MMBench, MMBench-CN, Seed-Bench, CCBench (Chinese Cultural Benchmark), QBench and Tiny LVLM. Owing to the absence of established metrics for quantitatively assessing text-image composition, we have devised a robust evaluation procedure that comprises both human and GPT4-Vision (GPT4-V) to ensure reliability. Notably, our InternLM-XComposer achieves competitive text-image composition scores compared to public solutions, including GPT4-V and GPT3.5. Collectively, InternLM-XComposer seamlessly blends advanced text-image comprehension and composition, revolutionizing vision-language interaction and offering new insights and opportunities. The InternLM-XComposer model series are publicly available at https://github.com/InternLM/InternLM-XComposer.

cs.CV↗

arXiv2023

Fine-Grained Extraction of Road Networks via Joint Learning of Connectivity and Segmentation

Road network extraction from satellite images is widely applicated in intelligent traffic management and autonomous driving fields. The high-resolution remote sensing images contain complex road areas and distracted background, which make it a challenge for road extraction. In this study, we present a stacked multitask network for end-to-end segmenting roads while preserving connectivity correctness. In the network, a global-aware module is introduced to enhance pixel-level road feature representation and eliminate background distraction from overhead images; a road-direction-related connectivity task is added to ensure that the network preserves the graph-level relationships of the road segments. We also develop a stacked multihead structure to jointly learn and effectively utilize the mutual information between connectivity learning and segmentation learning. We evaluate the performance of the proposed network on three public remote sensing datasets. The experimental results demonstrate that the network outperforms the state-of-the-art methods in terms of road segmentation accuracy and connectivity maintenance.

cs.CV↗

arXiv2022

Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer

Recently, Transformer has become a prevailing deep architecture for solving vehicle routing problems (VRPs). However, it is less effective in learning improvement models for VRP because its positional encoding (PE) method is not suitable in representing VRP solutions. This paper presents a novel Dual-Aspect Collaborative Transformer (DACT) to learn embeddings for the node and positional features separately, instead of fusing them together as done in existing ones, so as to avoid potential noises and incompatible correlations. Moreover, the positional features are embedded through a novel cyclic positional encoding (CPE) method to allow Transformer to effectively capture the circularity and symmetry of VRP solutions (i.e., cyclic sequences). We train DACT using Proximal Policy Optimization and design a curriculum learning strategy for better sample efficiency. We apply DACT to solve the traveling salesman problem (TSP) and capacitated vehicle routing problem (CVRP). Results show that our DACT outperforms existing Transformer based improvement models, and exhibits much better generalization performance across different problem sizes on synthetic and benchmark instances, respectively.

cs.LG↗

arXiv2022

Efficient Neural Neighborhood Search for Pickup and Delivery Problems

We present an efficient Neural Neighborhood Search (N2S) approach for pickup and delivery problems (PDPs). In specific, we design a powerful Synthesis Attention that allows the vanilla self-attention to synthesize various types of features regarding a route solution. We also exploit two customized decoders that automatically learn to perform removal and reinsertion of a pickup-delivery node pair to tackle the precedence constraint. Additionally, a diversity enhancement scheme is leveraged to further ameliorate the performance. Our N2S is generic, and extensive experiments on two canonical PDP variants show that it can produce state-of-the-art results among existing neural methods. Moreover, it even outstrips the well-known LKH3 solver on the more constrained PDP variant. Our implementation for N2S is available online.

cs.LG↗

arXiv2022

Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem

Existing deep reinforcement learning (DRL) based methods for solving the capacitated vehicle routing problem (CVRP) intrinsically cope with homogeneous vehicle fleet, in which the fleet is assumed as repetitions of a single vehicle. Hence, their key to construct a solution solely lies in the selection of the next node (customer) to visit excluding the selection of vehicle. However, vehicles in real-world scenarios are likely to be heterogeneous with different characteristics that affect their capacity (or travel speed), rendering existing DRL methods less effective. In this paper, we tackle heterogeneous CVRP (HCVRP), where vehicles are mainly characterized by different capacities. We consider both min-max and min-sum objectives for HCVRP, which aim to minimize the longest or total travel time of the vehicle(s) in the fleet. To solve those problems, we propose a DRL method based on the attention mechanism with a vehicle selection decoder accounting for the heterogeneous fleet constraint and a node selection decoder accounting for the route construction, which learns to construct a solution by automatically selecting both a vehicle and a node for this vehicle at each step. Experimental results based on randomly generated instances show that, with desirable generalization to various problem sizes, our method outperforms the state-of-the-art DRL method and most of the conventional heuristics, and also delivers competitive performance against the state-of-the-art heuristic method, i.e., SISR. Additionally, the results of extended experiments demonstrate that our method is also able to solve CVRPLib instances with satisfactory performance.

cs.LG↗

arXiv2022

Word Segmentation and Morphological Parsing for Sanskrit

We describe our participation in the Word Segmentation and Morphological Parsing (WSMP) for Sanskrit hackathon. We approach the word segmentation task as a sequence labelling task by predicting edit operations from which segmentations are derived. We approach the morphological analysis task by predicting morphological tags and rules that transform inflected words into their corresponding stems. Also, we propose an end-to-end trainable pipeline model for joint segmentation and morphological analysis. Our model performed best in the joint segmentation and analysis subtask (80.018 F1 score) and performed second best in the individual subtasks (segmentation: 96.189 F1 score / analysis: 69.180 F1 score). Finally, we analyse errors made by our models and suggest future work and possible improvements regarding data and evaluation.

cs.CL↗

arXiv2021

Control core of undirected complex networks

With the development of complex networks, many researchers have paid greater attention to studying the control of complex networks over the last decade. Although some theoretical breakthroughs allow us to identify all driver nodes, we still lack an efficient method to identify the driver nodes and understand the roles of individual nodes in contributing to the control of a large complex network. Here, we apply a leaf removal process (LRP) to find a substructure of an undirected network, which is considered as the control core of the original network. Based on a strict mathematical proof, the control core obtained by the LRP has the same controllability as the original network, and it contains at least one set of driver nodes. With this method, we systematically investigate the structural property of the control core with respect to different average degrees of the original networks ($\langle k \rangle$). We denote the node density ($n_\text{core}$) and link density ($l_\text{core}$) to characterize the control core when applying the LRP, and we study the impact of $\langle k \rangle$ on $n_\text{core}$ and $l_\text{core}$ in two artificial networks: undirected Erdös-Rényi (ER) random networks and undirected scale-free (SF) networks. We find that $n_\text{core}$ and $l_\text{core}$ both change nonmonotonously with increasing $\langle k \rangle$ in the two typical undirected networks. With the aid of core percolation theory, we can offer the theoretical predictions for both $n_\text{core}$ and $l_\text{core}$ as a function of $\langle k \rangle$. Then, we recognize that finding the driver nodes in the control core is much more efficient than in the original network by comparing $n_{\text{D}}$, the controllability of the original network, and $n_{\text{core}}$, regardless of how $\langle k \rangle$ increases.

physics.soc-ph↗

arXiv2021

Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning

Recently, there is an emerging trend to apply deep reinforcement learning to solve the vehicle routing problem (VRP), where a learnt policy governs the selection of next node for visiting. However, existing methods could not handle well the pairing and precedence relationships in the pickup and delivery problem (PDP), which is a representative variant of VRP. To address this challenging issue, we leverage a novel neural network integrated with a heterogeneous attention mechanism to empower the policy in deep reinforcement learning to automatically select the nodes. In particular, the heterogeneous attention mechanism specifically prescribes attentions for each role of the nodes while taking into account the precedence constraint, i.e., the pickup node must precede the pairing delivery node. Further integrated with a masking scheme, the learnt policy is expected to find higher-quality solutions for solving PDP. Extensive experimental results show that our method outperforms the state-of-the-art heuristic and deep learning model, respectively, and generalizes well to different distributions and problem sizes.

cs.LG↗

arXiv2021

Photonic Crystal Terahertz Leaky-Wave Antenna

Current wireless systems are experiencing unprecedented pressure that could be relieved by shifting carrier frequencies towards the terahertz spectrum. Yet, components are required to enable spectrally efficient communications at such high frequencies. Recently, the photonic crystal platform has been shown to enable signal processing at the chip-scale. Similarly, leaky-wave antennas were used to generate highly directional THz beams. Here, we combine photonic crystals with leaky-wave antennas. Practically, we propose to use an array of cylinders sandwiched between two plates, and we demonstrate a bandgap in the 250-350 GHz range by judicious geometric design. We introduce a linear defect in the crystal by removing a row of cylinders, allowing to guide the THz beam. Then, a careful study of the relation dispersion of the guided mode shows that its propagation constant is larger to that of free space. This allows the mode to efficiently outcouple when a thin aperture slot is introduced above the defect. We numerically demonstrate that the far-field diffracted beam can cover a wide angular range from 30 to 90 degrees. Finally, we show how the photonic crystals can be further engineered to enable coverage in two opposite angular directions.

physics.optics↗

arXiv2021

Protein-Polymer Mixtures in the Colloid Limit: Aggregation, Sedimentation and Crystallization

While proteins have been treated as particles with a spherically symmetric interaction, of course in reality the situation is rather more complex. A simple step towards higher complexity is to treat the proteins as non--spherical particles and that is the approach we pursue here. We investigate the phase behavior of enhanced green fluorescent protein (eGFP) under the addition of a non--adsorbing polymer, polyethylene glycol (PEG). From small angle x-ray scattering we infer that the eGFP undergoes dimerization and we treat the dimers as spherocylinders with aspect ratio $L/D-1 = 1.05$. Despite the complex nature of the proteins, we find that the phase behaviour is similar to that of hard spherocylinders with ideal polymer depletant, exhibiting aggregation and, in a small region of the phase diagram, crystallization. By comparing our measurements of the onset of aggregation with predictions for hard colloids and ideal polymers [S.V. Savenko and M. Dijkstra, J. Chem. Phys 124, 234902 (2006) and F. lo Verso et al., Phys. Rev. E 73, 061407 (2006)] we find good agreement, which suggests that the eGFP proteins are consistent with hard spherocylinders and ideal polymer.

cond-mat.soft↗