Search Results for author:
Found 16 papers, 7 papers with code
GloSoFarID: Global multispectral dataset for Solar Farm IDentification in satellite imagery
Solar Photovoltaic (PV) technology is increasingly recognized as a pivotal solution in the global pursuit of clean and renewable energy.
Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume
To address this gap, we propose a new metric termed adversarial hypervolume, assessing the robustness of deep learning models comprehensively over a range of perturbation intensities from a multi-objective optimization standpoint.
Smooth Tchebycheff Scalarization for Multi-Objective Optimization
Multi-objective optimization problems can be found in many real-world applications, where the objectives often conflict each other and cannot be optimized by a single solution.
T3DNet: Compressing Point Cloud Models for Lightweight 3D Recognition
We find that the tiny model after network augmentation is much easier for a teacher to distill.
GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints
Self-supervised depth estimation has evolved into an image reconstruction task that minimizes a photometric loss.
PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model's architecture and parameters.
Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models
Based on our analysis with bias-variance decomposition and experimental observations, we attribute the degradation to the spatial fitting error occurring in the training of both the teacher and student model.
Adapting Segment Anything Model (SAM) through Prompt-based Learning for Enhanced Protein Identification in Cryo-EM Micrographs
Cryo-electron microscopy (cryo-EM) remains pivotal in structural biology, yet the task of protein particle picking, integral for 3D protein structure construction, is laden with manual inefficiencies.
Evolutionary Pareto Set Learning with Structure Constraints
In our approach, the Pareto optimality can be traded off with a preferred structure among the whole solution set, which could be crucial for many real-world problems.
Continuation Path Learning for Homotopy Optimization
Homotopy optimization is a traditional method to deal with a complicated optimization problem by solving a sequence of easy-to-hard surrogate subproblems.
Pareto Set Learning for Expensive Multi-Objective Optimization
This work represents the first attempt to model the Pareto set for expensive multi-objective optimization.
Pareto Set Learning for Neural Multi-objective Combinatorial Optimization
In this work, we generalize the idea of neural combinatorial optimization, and develop a learning-based approach to approximate the whole Pareto set for a given MOCO problem without further search procedure.
Template NeRF: Towards Modeling Dense Shape Correspondences from Category-Specific Object Images
By representing object instances within the same category as shape and appearance variation of a shared NeRF template, our proposed method can achieve dense shape correspondences reasoning on images for a wide range of object classes.
Preference Conditioned Neural Multi-objective Combinatorial Optimization
In this work, we generalize the idea of neural combinatorial optimization, and develop a learning-based approach to approximate the whole Pareto set for a given MOCO problem without further search procedure.
Evaluation of Transportation Systems and Novel UV-Oriented Solution for Integration, Resilience, Inclusiveness and Sustainability
ransportation systems have revolutionized the form of society.
Controllable Pareto Multi-Task Learning
With a fixed model capacity, the tasks would be conflicted with each other, and the system usually has to make a trade-off among learning all of them together.
