Search Results for author:
Found 28 papers, 10 papers with code
Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience
We have built a custom mobile multi-camera large-space dense light field capture system, which provides a series of high-quality and sufficiently dense light field images for various scenarios.
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
Additionally, DPA models user preferences as directions (i. e., unit vectors) in the reward space to achieve user-dependent preference control.
Enhancing Compositional Generalization via Compositional Feature Alignment
To delve into the CG challenge, we develop CG-Bench, a suite of CG benchmarks derived from existing real-world image datasets, and observe that the prevalent pretraining-finetuning paradigm on foundational models, such as CLIP and DINOv2, struggles with the challenge.
Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms
First, in the binary classification setup of Rosenfeld et al. (2021), we show that our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments.
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
By applying our method to SAM and CLIP, we obtain SAM-CLIP: a unified model that combines the capabilities of SAM and CLIP into a single vision transformer.
Gradual Domain Adaptation: Theory and Algorithms
Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way.
Mitigating the Alignment Tax of RLHF
Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different reward-tax trade-offs, we propose Adaptive Model Averaging (AMA) to adaptively find various combination ratios of model layers.
ImmersiveNeRF: Hybrid Radiance Fields for Unbounded Immersive Light Field Reconstruction
This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolation.
Federated Learning with Classifier Shift for Class Imbalance
Federated learning aims to learn a global model collaboratively while the training data belongs to different clients and is not allowed to be exchanged.
AuE-IPA: An AU Engagement Based Infant Pain Assessment Method
Recent studies have found that pain in infancy has a significant impact on infant development, including psychological problems, possible brain injury, and pain sensitivity in adulthood.
Predicting Properties of Quantum Systems with Conditional Generative Models
For many ground states of gapped Hamiltonians, generative models can learn from measurements of a single quantum state to reconstruct the state accurately enough to predict local observables.
Attention Based Relation Network for Facial Action Units Recognition
In this paper, we propose a novel Attention Based Relation Network (ABRNet) for AU recognition, which can automatically capture AU relations without unnecessary or even disturbing predefined rules.
Future Gradient Descent for Adapting the Temporal Shifting Data Distribution in Online Recommendation Systems
One of the key challenges of learning an online recommendation model is the temporal domain shift, which causes the mismatch between the training and testing data distribution and hence domain generalization error.
Asynchronous Training Schemes in Distributed Learning with Time Delay
In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance.
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
Gradual domain adaptation (GDA), on the other hand, assumes a path of $(T-1)$ unlabeled intermediate domains bridging the source and target, and aims to provide better generalization in the target domain by leveraging the intermediate ones.
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
We show that the performance of MetaNTK-NAS is comparable or better than the state-of-the-art NAS method designed for few-shot learning while enjoying more than 100x speedup.
Provable Domain Generalization via Invariant-Feature Subspace Recovery
Our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments under the data model of Rosenfeld et al. (2021).
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
Despite the subtle difference between MTL and meta-learning in the problem formulation, both learning paradigms share the same insight that the shared structure between existing training tasks could lead to better generalization and adaptation.
Ranked #17 on
Few-Shot Image Classification
on FC100 5-way (1-shot)
Privacy Preserving in Non-Intrusive Load Monitoring: A Differential Privacy Perspective
In this paper, we cast one-shot non-intrusive load monitoring (NILM) in the compressive sensing framework, and bridge the gap between theoretical accuracy of NILM inference and differential privacy's parameters.
Global Convergence and Generalization Bound of Gradient-Based Meta-Learning with Deep Neural Nets
Gradient-based meta-learning (GBML) with deep neural nets (DNNs) has become a popular approach for few-shot learning.
Robust Data-driven Profile-based Pricing Schemes
To enable an efficient electricity market, a good pricing scheme is of vital importance.
Learning Positive Functions with Pseudo Mirror Descent
The nonparametric learning of positive-valued functions appears widely in machine learning, especially in the context of estimating intensity functions of point processes.
Vulnerability Analysis for Data Driven Pricing Schemes
In this paper, from an adversarial machine learning point of view, we examine the vulnerability of data-driven electricity market design.
A Novel VHR Image Change Detection Algorithm Based on Image Fusion and Fuzzy C-Means Clustering
This thesis describes a study to perform change detection on Very High Resolution satellite images using image fusion based on 2D Discrete Wavelet Transform and Fuzzy C-Means clustering algorithm.
Super-resolution Reconstruction of SAR Image based on Non-Local Means Denoising Combined with BP Neural Network
In this article, we propose a super-resolution method to resolve the problem of image low spatial because of the limitation of imaging devices.
Optimizing Top Precision Performance Measure of Content-Based Image Retrieval by Learning Similarity Function
To fill this gap, in this paper, we propose a novel similarity learning method to maximize the top precision measure.
Multiple kernel multivariate performance learning using cutting plane algorithm
The learning of the classifier parameter and the kernel weight are unified in a single objective function considering to minimize the upper boundary of the given multivariate performance measure.
Image tag completion by local learning
The problem of tag completion is to learn the missing tags of an image.
