arXiv subjects

Letian Zhang

Publications and source records attributed to Letian Zhang.

33 records · Page 2Linked to original sources

arXiv2025

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these models and their training data creates a significant barrier for open-source research. To bridge this gap, we introduce GPT-IMAGE-EDIT-1.5M, a publicly available, large-scale image-editing corpus containing more than 1.5 million high-quality triplets (instruction, source image, edited image). We systematically construct this dataset by leveraging the versatile capabilities of GPT-4o to unify and refine three popular image-editing datasets: OmniEdit, HQ-Edit, and UltraEdit. Specifically, our methodology involves 1) regenerating output images to enhance visual quality and instruction alignment, and 2) selectively rewriting prompts to improve semantic clarity. To validate the efficacy of our dataset, we fine-tune advanced open-source models on GPT-IMAGE-EDIT-1.5M. The empirical results are exciting, e.g., the fine-tuned FluxKontext achieves highly competitive performance across a comprehensive suite of benchmarks, including 7.24 on GEdit-EN, 3.80 on ImgEdit-Full, and 8.78 on Complex-Edit, showing stronger instruction following and higher perceptual quality while maintaining identity. These scores markedly exceed all previously published open-source methods and substantially narrow the gap to leading proprietary models. We hope the full release of GPT-IMAGE-EDIT-1.5M can help to catalyze further open research in instruction-guided image editing.

cs.CV↗

arXiv2025

EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models

Vision-language retrieval (VLR) has attracted significant attention in both academia and industry, which involves using text (or images) as queries to retrieve corresponding images (or text). However, existing methods often neglect the rich visual semantics knowledge of entities, thus leading to incorrect retrieval results. To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries. Specifically, since humans recognize entities through visual cues, we employ a large language model (LLM) to generate Entity Visual Descriptions (EVDs) as alignment cues to complement textual data. These EVDs are then integrated into raw queries to create visually-rich, EVD-enhanced queries. Furthermore, recognizing that EVD-enhanced queries may introduce noise or low-quality expansions, we develop a novel, trainable EVD-aware Rewriter (EaRW) for vision-language retrieval tasks. EaRW utilizes EVD knowledge and the generative capabilities of the language model to effectively rewrite queries. With our specialized training strategy, EaRW can generate high-quality and low-noise EVD-enhanced queries. Extensive quantitative and qualitative experiments on image-text retrieval benchmarks validate the superiority of EvdCLIP on vision-language retrieval tasks.

cs.CV↗

arXiv2025

Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis

The success of multi-modal large language models (MLLMs) has been largely attributed to the large-scale training data. However, the training data of many MLLMs is unavailable due to privacy concerns. The expensive and labor-intensive process of collecting multi-modal data further exacerbates the problem. Is it possible to synthesize multi-modal training data automatically without compromising diversity and quality? In this paper, we propose a new method, Oasis, to synthesize high-quality multi-modal data with only images. Oasis breaks through traditional methods by prompting only images to the MLLMs, thus extending the data diversity by a large margin. Our method features a delicate quality control method which ensures the data quality. We collected over 500k data and conducted incremental experiments on LLaVA-NeXT. Extensive experiments demonstrate that our method can significantly improve the performance of MLLMs. The image-based synthesis also allows us to focus on the specific-domain ability of MLLMs. Code and dataset are publicly available at https://github.com/Letian2003/MM_INF.

cs.CV↗

arXiv2025

Skill dependencies uncover nested human capital

Modern economies require increasingly diverse and specialized skills, many of which depend on the acquisition of other skills first. Here we analyse US survey data to reveal a nested structure within skill portfolios, where the direction of dependency is inferred from asymmetrical conditional probabilities-occupations require one skill conditional on another. This directional nature suggests that advanced, specific skills and knowledge are often built upon broader, fundamental ones. We examine 70 million job transitions to show that human capital development and career progression follow this structured pathway in which skills more aligned with the nested structure command higher wage premiums, require longer education and are less likely to be automated. These disparities are evident across genders and racial-ethnic groups, explaining long-term wage penalties. Finally, we find that this nested structure has become even more pronounced over the past two decades, indicating increased barriers to upward job mobility.

physics.soc-ph↗

arXiv2024

Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains

Federated learning (FL) allows collaborative machine learning training without sharing private data. While most FL methods assume identical data domains across clients, real-world scenarios often involve heterogeneous data domains. Federated Prototype Learning (FedPL) addresses this issue, using mean feature vectors as prototypes to enhance model generalization. However, existing FedPL methods create the same number of prototypes for each client, leading to cross-domain performance gaps and disparities for clients with varied data distributions. To mitigate cross-domain feature representation variance, we introduce FedPLVM, which establishes variance-aware dual-level prototypes clustering and employs a novel $α$-sparsity prototype loss. The dual-level prototypes clustering strategy creates local clustered prototypes based on private data features, then performs global prototypes clustering to reduce communication complexity and preserve local data privacy. The $α$-sparsity prototype loss aligns samples from underrepresented domains, enhancing intra-class similarity and reducing inter-class similarity. Evaluations on Digit-5, Office-10, and DomainNet datasets demonstrate our method's superiority over existing approaches.

cs.LG↗

arXiv2024

Learning the Optimal Path and DNN Partition for Collaborative Edge Inference

Recent advancements in Deep Neural Networks (DNNs) have catalyzed the development of numerous intelligent mobile applications and services. However, they also introduce significant computational challenges for resource-constrained mobile devices. To address this, collaborative edge inference has been proposed. This method involves partitioning a DNN inference task into several subtasks and distributing these across multiple network nodes. Despite its potential, most current approaches presume known network parameters -- like node processing speeds and link transmission rates -- or rely on a fixed sequence of nodes for processing the DNN subtasks. In this paper, we tackle a more complex scenario where network parameters are unknown and must be learned, and multiple network paths are available for distributing inference tasks. Specifically, we explore the learning problem of selecting the optimal network path and assigning DNN layers to nodes along this path, considering potential security threats and the costs of switching paths. We begin by deriving structural insights from the DNN layer assignment with complete network information, which narrows down the decision space and provides crucial understanding of optimal assignments. We then cast the learning problem with incomplete network information as a novel adversarial group linear bandits problem with switching costs, featuring rewards generation through a combined stochastic and adversarial process. We introduce a new bandit algorithm, B-EXPUCB, which combines elements of the classical blocked EXP3 and LinUCB algorithms, and demonstrate its sublinear regret. Extensive simulations confirm B-EXPUCB's superior performance in learning for collaborative edge inference over existing algorithms.

cs.LG↗

arXiv2024

Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning

The advancement of large language models (LLMs) has significantly broadened the scope of applications in natural language processing, with multi-modal LLMs extending these capabilities to integrate and interpret visual data. However, existing benchmarks for visual language models (VLMs) predominantly focus on single-image inputs, neglecting the crucial aspect of multi-image understanding. In this paper, we introduce a Multi-Image Relational Benchmark MIRB, designed to evaluate VLMs' ability to compare, analyze, and reason across multiple images. Our benchmark encompasses four categories: perception, visual world knowledge, reasoning, and multi-hop reasoning. Through a comprehensive evaluation of a wide range of open-source and closed-source models, we demonstrate that while open-source VLMs were shown to approach the performance of GPT-4V in single-image tasks, a significant performance gap remains in multi-image reasoning tasks. Our findings also reveal that even the state-of-the-art GPT-4V model struggles with our benchmark, underscoring the need for further research and development in this area. We believe our contribution of MIRB could serve as a testbed for developing the next-generation multi-modal models.

cs.CV↗

arXiv2024

ImageNet3D: Towards General-Purpose Object-Level 3D Understanding

A vision model with general-purpose object-level 3D understanding should be capable of inferring both 2D (e.g., class name and bounding box) and 3D information (e.g., 3D location and 3D viewpoint) for arbitrary rigid objects in natural images. This is a challenging task, as it involves inferring 3D information from 2D signals and most importantly, generalizing to rigid objects from unseen categories. However, existing datasets with object-level 3D annotations are often limited by the number of categories or the quality of annotations. Models developed on these datasets become specialists for certain categories or domains, and fail to generalize. In this work, we present ImageNet3D, a large dataset for general-purpose object-level 3D understanding. ImageNet3D augments 200 categories from the ImageNet dataset with 2D bounding box, 3D pose, 3D location annotations, and image captions interleaved with 3D information. With the new annotations available in ImageNet3D, we could (i) analyze the object-level 3D awareness of visual foundation models, and (ii) study and develop general-purpose models that infer both 2D and 3D information for arbitrary rigid objects in natural images, and (iii) integrate unified 3D models with large language models for 3D-related reasoning.. We consider two new tasks, probing of object-level 3D awareness and open vocabulary pose estimation, besides standard classification and pose estimation. Experimental results on ImageNet3D demonstrate the potential of our dataset in building vision models with stronger general-purpose object-level 3D understanding.

cs.CV↗

arXiv2024

Pre-Trained Vision-Language Models as Partial Annotators

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better adapt pre-trained models to the requirements of downstream tasks, people usually use methods such as few-shot or parameter-efficient fine-tuning and knowledge distillation. However, annotating samples is laborious, while a large number of unlabeled samples can be easily obtained. In this paper, we investigate a novel "pre-trained annotating - weakly-supervised learning" paradigm for pre-trained model application and experiment on image classification tasks. Specifically, based on CLIP, we annotate image samples with multiple prompt templates to obtain multiple candidate labels to form the noisy partial label dataset, and design a collaborative consistency regularization algorithm to solve this problem. Our method simultaneously trains two neural networks, which collaboratively purify training labels for each other and obtain pseudo-labels for self-training, while adopting prototypical similarity alignment and noisy supervised contrastive learning to optimize model representation. In experiments, our method achieves performances far beyond zero-shot inference without introducing additional label information, and outperforms other weakly supervised learning and few-shot fine-tuning methods, and obtains smaller deployed models. Our code is available at: \url{https://anonymous.4open.science/r/Co-Reg-8CF9}.

cs.CV↗

arXiv2024

What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models

Counterfactual reasoning, a fundamental aspect of human cognition, involves contemplating alternatives to established facts or past events, significantly enhancing our abilities in planning and decision-making. In light of the advancements in current multi-modal large language models, we explore their effectiveness in counterfactual reasoning. To facilitate this investigation, we introduce a novel dataset, C-VQA, specifically designed to test the counterfactual reasoning capabilities of modern multi-modal large language models. This dataset is constructed by infusing original questions with counterfactual presuppositions, spanning various types such as numerical and boolean queries. It encompasses a mix of real and synthetic data, representing a wide range of difficulty levels. Our thorough evaluations of contemporary vision-language models using this dataset have revealed substantial performance drops, with some models showing up to a 40% decrease, highlighting a significant gap between current models and human-like vision reasoning capabilities. We hope our dataset will serve as a vital benchmark for evaluating the counterfactual reasoning capabilities of models. Code and dataset are publicly available at https://bzhao.me/C-VQA/.

cs.CL↗

arXiv2023

IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment

Neural radiance fields (NeRF) is a promising approach for generating photorealistic images and representing complex scenes. However, when processing data sequentially, it can suffer from catastrophic forgetting, where previous data is easily forgotten after training with new data. Existing incremental learning methods using knowledge distillation assume that continuous data chunks contain both 2D images and corresponding camera pose parameters, pre-estimated from the complete dataset. This poses a paradox as the necessary camera pose must be estimated from the entire dataset, even though the data arrives sequentially and future chunks are inaccessible. In contrast, we focus on a practical scenario where camera poses are unknown. We propose IL-NeRF, a novel framework for incremental NeRF training, to address this challenge. IL-NeRF's key idea lies in selecting a set of past camera poses as references to initialize and align the camera poses of incoming image data. This is followed by a joint optimization of camera poses and replay-based NeRF distillation. Our experiments on real-world indoor and outdoor scenes show that IL-NeRF handles incremental NeRF training and outperforms the baselines by up to $54.04\%$ in rendering quality.

cs.CV↗

arXiv2023

Envisioning a Next Generation Extended Reality Conferencing System with Efficient Photorealistic Human Rendering

Meeting online is becoming the new normal. Creating an immersive experience for online meetings is a necessity towards more diverse and seamless environments. Efficient photorealistic rendering of human 3D dynamics is the core of immersive meetings. Current popular applications achieve real-time conferencing but fall short in delivering photorealistic human dynamics, either due to limited 2D space or the use of avatars that lack realistic interactions between participants. Recent advances in neural rendering, such as the Neural Radiance Field (NeRF), offer the potential for greater realism in metaverse meetings. However, the slow rendering speed of NeRF poses challenges for real-time conferencing. We envision a pipeline for a future extended reality metaverse conferencing system that leverages monocular video acquisition and free-viewpoint synthesis to enhance data and hardware efficiency. Towards an immersive conferencing experience, we explore an accelerated NeRF-based free-viewpoint synthesis algorithm for rendering photorealistic human dynamics more efficiently. We show that our algorithm achieves comparable rendering quality while performing training and inference 44.5% and 213% faster than state-of-the-art methods, respectively. Our exploration provides a design basis for constructing metaverse conferencing systems that can handle complex application scenarios, including dynamic scene relighting with customized themes and multi-user conferencing that harmonizes real-world people into an extended world.

cs.CV↗

arXiv2023

E$^3$Pose: Energy-Efficient Edge-assisted Multi-camera System for Multi-human 3D Pose Estimation

Multi-human 3D pose estimation plays a key role in establishing a seamless connection between the real world and the virtual world. Recent efforts adopted a two-stage framework that first builds 2D pose estimations in multiple camera views from different perspectives and then synthesizes them into 3D poses. However, the focus has largely been on developing new computer vision algorithms on the offline video datasets without much consideration on the energy constraints in real-world systems with flexibly-deployed and battery-powered cameras. In this paper, we propose an energy-efficient edge-assisted multiple-camera system, dubbed E$^3$Pose, for real-time multi-human 3D pose estimation, based on the key idea of adaptive camera selection. Instead of always employing all available cameras to perform 2D pose estimations as in the existing works, E$^3$Pose selects only a subset of cameras depending on their camera view qualities in terms of occlusion and energy states in an adaptive manner, thereby reducing the energy consumption (which translates to extended battery lifetime) and improving the estimation accuracy. To achieve this goal, E$^3$Pose incorporates an attention-based LSTM to predict the occlusion information of each camera view and guide camera selection before cameras are selected to process the images of a scene, and runs a camera selection algorithm based on the Lyapunov optimization framework to make long-term adaptive selection decisions. We build a prototype of E$^3$Pose on a 5-camera testbed, demonstrate its feasibility and evaluate its performance. Our results show that a significant energy saving (up to 31.21%) can be achieved while maintaining a high 3D pose estimation accuracy comparable to state-of-the-art methods.

cs.CV↗

arXiv2022

LMBAO: A Landmark Map for Bundle Adjustment Odometry in LiDAR SLAM

LiDAR odometry is one of the essential parts of LiDAR simultaneous localization and mapping (SLAM). However, existing LiDAR odometry tends to match a new scan simply iteratively with previous fixed-pose scans, gradually accumulating errors. Furthermore, as an effective joint optimization mechanism, bundle adjustment (BA) cannot be directly introduced into real-time odometry due to the intensive computation of large-scale global landmarks. Therefore, this letter designs a new strategy named a landmark map for bundle adjustment odometry (LMBAO) in LiDAR SLAM to solve these problems. First, BA-based odometry is further developed with an active landmark maintenance strategy for a more accurate local registration and avoiding cumulative errors. Specifically, this paper keeps entire stable landmarks on the map instead of just their feature points in the sliding window and deletes the landmarks according to their active grade. Next, the sliding window length is reduced, and marginalization is performed to retain the scans outside the window but corresponding to active landmarks on the map, greatly simplifying the computation and improving the real-time properties. In addition, experiments on three challenging datasets show that our algorithm achieves real-time performance in outdoor driving and outperforms state-of-the-art LiDAR SLAM algorithms, including Lego-LOAM and VLOM.

cs.CV↗

arXiv2021

Autodidactic Neurosurgeon: Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning

Recent breakthroughs in deep learning (DL) have led to the emergence of many intelligent mobile applications and services, but in the meanwhile also pose unprecedented computing challenges on resource-constrained mobile devices. This paper builds a collaborative deep inference system between a resource-constrained mobile device and a powerful edge server, aiming at joining the power of both on-device processing and computation offloading. The basic idea of this system is to partition a deep neural network (DNN) into a front-end part running on the mobile device and a back-end part running on the edge server, with the key challenge being how to locate the optimal partition point to minimize the end-to-end inference delay. Unlike existing efforts on DNN partitioning that rely heavily on a dedicated offline profiling stage to search for the optimal partition point, our system has a built-in online learning module, called Autodidactic Neurosurgeon (ANS), to automatically learn the optimal partition point on-the-fly. Therefore, ANS is able to closely follow the changes of the system environment by generating new knowledge for adaptive decision making. The core of ANS is a novel contextual bandit learning algorithm, called $μ$LinUCB, which not only has provable theoretical learning performance guarantee but also is ultra-lightweight for easy real-world implementation. We implement our system on a video stream object detection testbed to validate the design of ANS and evaluate its performance. The experiments show that ANS significantly outperforms state-of-the-art benchmarks in terms of tracking system changes and reducing the end-to-end inference delay.

cs.LG↗