Search Results for author:
Found 27 papers, 9 papers with code
AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generation
Although existing techniques, e. g., data augmentation and semi-supervised learning, can mitigate this scarcity issue to some extent, they are heavily dependent on high-quality labeled data and perform worse in rare object classes.
RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulator
To address these limitations, we introduce the RoboGSim, a real2sim2real robotic simulator, powered by 3D Gaussian Splatting and the physics engine.
GAN-Based Architecture for Low-dose Computed Tomography Imaging Denoising
Generative Adversarial Networks (GANs) have surfaced as a revolutionary element within the domain of low-dose computed tomography (LDCT) imaging, providing an advanced resolution to the enduring issue of reconciling radiation exposure with image quality.
ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks
Recent advances in Generative Artificial Intelligence have fueled numerous applications, particularly those involving Generative Adversarial Networks (GANs), which are essential for synthesizing realistic photos and videos.
A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models
Augmented datasets are feasible for instruction tuning.
ED-ViT: Splitting Vision Transformer for Distributed Inference on Edge Devices
We conduct extensive experiments on five datasets with three model structures, demonstrating that our approach significantly reduces inference latency on edge devices and achieves a model size reduction of up to 28. 9 times and 34. 1 times, respectively, while maintaining test accuracy comparable to the original Vision Transformer.
MMAD: The First-Ever Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection
In the field of industrial inspection, Multimodal Large Language Models (MLLMs) have a high potential to renew the paradigms in practical applications due to their robust language capabilities and generalization abilities.
CAR: Controllable Autoregressive Modeling for Visual Generation
To the best of our knowledge, we are the first to propose a control framework for pre-trained autoregressive visual generation models.
Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel
Evaluation on a realistic case study with gas compressors confirms that TVSafeOpt ensures safety when solving time-varying optimization problems with unknown reward and safety functions.
Blocks as Probes: Dissecting Categorization Ability of Large Multimodal Models
Categorization, a core cognitive ability in humans that organizes objects based on common features, is essential to cognitive science as well as computer vision.
Anno-incomplete Multi-dataset Detection
Object detectors have shown outstanding performance on various public datasets.
P3P: Pseudo-3D Pre-training for Scaling 3D Masked Autoencoders
Inspired by semi-supervised learning leveraging limited labeled data and a large amount of unlabeled data, in this work, we propose a novel self-supervised pre-training framework utilizing the real 3D data and the pseudo-3D data lifted from images by a large depth estimation model.
Decision Boundary-aware Knowledge Consolidation Generates Better Instance-Incremental Learner
Two issues have to be tackled in the new IIL setting: 1) the notorious catastrophic forgetting because of no access to old data, and 2) broadening the existing decision boundary to new observations because of concept drift.
M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models
In this work, we introduce M4U, a novel and challenging benchmark for assessing the capability of multi-discipline multilingual multimodal understanding and reasoning.
Improving Personalisation in Valence and Arousal Prediction using Data Augmentation
This paper presents our work on an enhanced personalisation strategy, that leverages data augmentation to develop tailored models for continuous valence and arousal prediction.
LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking
Deep learning models, particularly those based on transformers, often employ numerous stacked structures, which possess identical architectures and perform similar functions.
Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native
In this paper, we investigate the intersection of large generative AI models and cloud-native computing architectures.
FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
Efficiently aggregating trained neural networks from local clients into a global model on a server is a widely researched topic in federated learning.
Can the Query-based Object Detector Be Designed with Fewer Stages?
Query-based object detectors have made significant advancements since the publication of DETR.
IIDM: Inter and Intra-domain Mixing for Semi-supervised Domain Adaptation in Semantic Segmentation
In this paper, we highlight the significance of exploiting the intra-domain information between the labeled target data and unlabeled target data.
Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes
Unfortunately, the resultant noisy bounding boxes could cause corrupt supervision signals and thus diminish detection performance.
A Survey on Personalized Affective Computing in Human-Machine Interaction
In this paper, we discuss the need for personalization in affective and personality computing (hereinafter referred to as affective computing).
TAP: Accelerating Large-Scale DNN Training Through Tensor Automatic Parallelisation
However, finding a suitable model parallel schedule for an arbitrary neural network is a non-trivial task due to the exploding search space.
MapQA: A Dataset for Question Answering on Choropleth Maps
Our experimental results show that V-MODEQA has better overall performance and robustness on MapQA than the state-of-the-art ChartQA and VQA algorithms by capturing the unique properties in map question answering.
Harmonia: Near-Linear Scalability for Replicated Storage with In-Network Conflict Detection
Experimental results show that Harmonia improves the throughput of these protocols by up to 10X for a replication factor of 10, providing near-linear scalability up to the limit of our testbed.
Distributed, Parallel, and Cluster Computing
Guaranteed Simultaneous Asymmetric Tensor Decomposition via Orthogonalized Alternating Least Squares
We propose a Slicing Initialized Alternating Subspace Iteration (s-ASI) method that is guaranteed to recover top $r$ components ($\epsilon$-close) simultaneously for (a)symmetric tensors almost surely under the noiseless case (with high probability for a bounded noise) using $O(\log(\log \frac{1}{\epsilon}))$ steps of tensor subspace iterations.
