Search Results for author:
Found 74 papers, 32 papers with code
Cones 2: Customizable Image Synthesis with Multiple Subjects
Synthesizing images with user-specified subjects has received growing attention due to its practical applications.
Ripple Knowledge Graph Convolutional Networks For Recommendation Systems
Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to effectively improve the model's interpretability and accuracy.
DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase
Differentially private synthetic data is a promising alternative for sensitive data release.
E-MLB: Multilevel Benchmark for Event-Based Camera Denoising
Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and low power consumption, showing great application potential in many fields.
Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection
Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set.
Spatial-Aware Token for Weakly Supervised Object Localization
Specifically, a spatial token is first introduced in the input space to aggregate representations for localization task.
Grounding 3D Object Affordance from 2D Interactions in Images
Comprehensive experiments on PIAD demonstrate the reliability of the proposed task and the superiority of our method.
Cones: Concept Neurons in Diffusion Models for Customized Generation
Concatenating multiple clusters of concept neurons can vividly generate all related concepts in a single image.
Traffic Scene Parsing through the TSP6K Dataset
Traffic scene parsing is one of the most important tasks to achieve intelligent cities.
P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classification
Inspired by the distribution calibration technique which utilizes the distribution or statistics of the base classes to calibrate the data for few-shot tasks, we propose a novel discrete data calibration operation which is more suitable for NN-based few-shot classification.
Leverage Interactive Affinity for Affordance Learning
Perceiving potential "action possibilities" (i. e., affordance) regions of images and learning interactive functionalities of objects from human demonstration is a challenging task due to the diversity of human-object interactions.
Decoupling-and-Aggregating for Image Exposure Correction
To this end, we inject the addition/difference operation into the convolution process and devise a Contrast Aware (CA) unit and a Detail Aware (DA) unit to facilitate the statistical and structural regularities modeling.
Detecting Change Intervals with Isolation Distributional Kernel
The data-dependent property and finite feature map of IDK enabled iCID to efficiently identify various types of change points in data streams with the tolerance of noise points.
Local Differential Privacy Image Generation Using Flow-based Deep Generative Models
To release and use medical images, we need an algorithm that can simultaneously protect privacy and preserve pathologies in medical images.
Application of Data Encryption in Chinese Named Entity Recognition
Recently, with the continuous development of deep learning, the performance of named entity recognition tasks has been dramatically improved.
Chinese Named Entity Recognition
named-entity-recognition
+1
Grounded Affordance from Exocentric View
Due to the diversity of interactive affordance, the uniqueness of different individuals leads to diverse interactions, which makes it difficult to establish an explicit link between object parts and affordance labels.
PrivateRec: Differentially Private Training and Serving for Federated News Recommendation
Collecting and training over sensitive personal data raise severe privacy concerns in personalized recommendation systems, and federated learning can potentially alleviate the problem by training models over decentralized user data. However, a theoretically private solution in both the training and serving stages of federated recommendation is essential but still lacking. Furthermore, naively applying differential privacy (DP) to the two stages in federated recommendation would fail to achieve a satisfactory trade-off between privacy and utility due to the high-dimensional characteristics of model gradients and hidden representations. In this work, we propose a federated news recommendation method for achieving a better utility in model training and online serving under a DP guarantee. We first clarify the DP definition over behavior data for each round in the life-circle of federated recommendation systems. Next, we propose a privacy-preserving online serving mechanism under this definition based on the idea of decomposing user embeddings with public basic vectors and perturbing the lower-dimensional combination coefficients.
Network Shuffling: Privacy Amplification via Random Walks
However, introducing a centralized entity to the originally local privacy model loses some appeals of not having any centralized entity as in local differential privacy.
FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization
However, its generalization performance to heterogeneous tasks is inferior to other architectures (e. g., CNNs and transformers) due to the extensive retention of domain information.
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation
Dynamic Vision Sensor (DVS) can asynchronously output the events reflecting apparent motion of objects with microsecond resolution, and shows great application potential in monitoring and other fields.
Location-Free Camouflage Generation Network
However, these methods struggle in 1) efficiently generating camouflage images using foreground and background with arbitrary structure; 2) camouflaging foreground objects to regions with multiple appearances (e. g. the junction of the vegetation and the mountains), which limit their practical application.
Learning Affordance Grounding from Exocentric Images
To empower an agent with such ability, this paper proposes a task of affordance grounding from exocentric view, i. e., given exocentric human-object interaction and egocentric object images, learning the affordance knowledge of the object and transferring it to the egocentric image using only the affordance label as supervision.
Towards Data-Efficient Detection Transformers
Besides, we introduce a simple yet effective label augmentation method to provide richer supervision and improve data efficiency.
Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning
Non-exemplar class-incremental learning is to recognize both the old and new classes when old class samples cannot be saved.
Phrase-Based Affordance Detection via Cyclic Bilateral Interaction
In this paper, we explore to perceive affordance from a vision-language perspective and consider the challenging phrase-based affordance detection problem, i. e., given a set of phrases describing the action purposes, all the object regions in a scene with the same affordance should be detected.
OLIVE: Oblivious Federated Learning on Trusted Execution Environment against the risk of sparsification
First, we theoretically analyze the leakage of memory access patterns, revealing the risk of sparsified gradients, which are commonly used in FL to enhance communication efficiency and model accuracy.
Optimizing Random Mixup with Gaussian Differential Privacy
Recently, an algorithm called DPMix is proposed to release high-dimensional data after a random mixup of degree $m$ with differential privacy.
Self-Paced Imbalance Rectification for Class Incremental Learning
Exemplar-based class-incremental learning is to recognize new classes while not forgetting old ones, whose samples can only be saved in limited memory.
Multi-Grained Spatio-Temporal Features Perceived Network for Event-Based Lip-Reading
To recognize words from the event data, we propose a novel Multi-grained Spatio-Temporal Features Perceived Network (MSTP) to perceive fine-grained spatio-temporal features from microsecond time-resolved event data.
Dreaming To Prune Image Deraining Networks
It is based on our observation that deep degradation representations can be clustered by degradation characteristics (types of rain) while independent of image content.
Background Activation Suppression for Weakly Supervised Object Localization
Existing FPM-based methods use cross-entropy (CE) to evaluate the foreground prediction map and to guide the learning of generator.
FP-DETR: Detection Transformer Advanced by Fully Pre-training
To this end, we propose the task adapter which leverages self-attention to model the contextual relation between object query embedding.
Do What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks
While artificial neural networks (ANNs) have been widely adopted in machine learning, researchers are increasingly obsessed by the gaps between ANNs and natural neural networks (NNNs).
Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning
In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e. g., meta-learning.
Learning Visual Affordance Grounding from Demonstration Videos
For the object branch, we introduce a semantic enhancement module (SEM) to make the network focus on different parts of the object according to the action classes and utilize a distillation loss to align the output features of the object branch with that of the video branch and transfer the knowledge in the video branch to the object branch.
Ranked #2 on
Video-to-image Affordance Grounding
on EPIC-Hotspot
One-Shot Object Affordance Detection in the Wild
To empower robots with this ability in unseen scenarios, we first study the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.
Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers
In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains.
Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning
Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
One-Shot Affordance Detection
To empower robots with this ability in unseen scenarios, we consider the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.
Understanding the Interplay between Privacy and Robustness in Federated Learning
Federated Learning (FL) is emerging as a promising paradigm of privacy-preserving machine learning, which trains an algorithm across multiple clients without exchanging their data samples.
FL-Market: Trading Private Models in Federated Learning
FL-Market decouples ML from the need to centrally gather training data on the broker's side using federated learning, an emerging privacy-preserving ML paradigm in which data owners collaboratively train an ML model by uploading local gradients (to be aggregated into a global gradient for model updating).
FakeMix Augmentation Improves Transparent Object Detection
However, these methods usually encounter boundary-related imbalance problem, leading to limited generation capability.
FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
To incorporate high-order user-item interactions, we propose a user-item graph expansion method that can find neighboring users with co-interacted items and exchange their embeddings for expanding the local user-item graphs in a privacy-preserving way.
Transparent Contribution Evaluation for Secure Federated Learning on Blockchain
In this work, we propose a blockchain-based federated learning framework and a protocol to transparently evaluate each participant's contribution.
Quantifying the Privacy-Utility Trade-offs in COVID-19 Contact Tracing Apps
How to contain the spread of the COVID-19 virus is a major concern for most countries.
Computers and Society Cryptography and Security 68P27 H.3.4
PCT-TEE: Trajectory-based Private Contact Tracing System with Trusted Execution Environment
To this end, we design a TEE-based system with flexible trajectory data encoding algorithms.
Cryptography and Security Computers and Society
FLAME: Differentially Private Federated Learning in the Shuffle Model
In this work, by leveraging the \textit{privacy amplification} effect in the recently proposed shuffle model of differential privacy, we achieve the best of two worlds, i. e., accuracy in the curator model and strong privacy without relying on any trusted party.
Finding Acceptable Parameter Regions of Stochastic Hill functions for Multisite Phosphorylation Mechanism
To reduce model complexity, this work aims to simplify the multisite phosphorylation mechanism by a stochastic Hill function model.
Nighttime Dehazing with a Synthetic Benchmark
To address this issue, we propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images, which first reconstructs the scene geometry, then simulates the light rays and object reflectance, and finally renders the haze effects.
P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model
The state-of-the-art approach for this problem is to build a generative model under differential privacy, which offers a rigorous privacy guarantee.
PGLP: Customizable and Rigorous Location Privacy through Policy Graph
Third, we design a private location trace release framework that pipelines the detection of location exposure, policy graph repair, and private trajectory release with customizable and rigorous location privacy.
Cryptography and Security Computers and Society
PANDA: Policy-aware Location Privacy for Epidemic Surveillance
Our system has three primary functions for epidemic surveillance: location monitoring, epidemic analysis, and contact tracing.
Databases Cryptography and Security
Self-Supervised Tuning for Few-Shot Segmentation
Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples.
FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection
To prevent privacy leakages from gradients that are calculated on users' sensitive data, local differential privacy (LDP) has been considered as a privacy guarantee in federated SGD recently.
Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement
Contrast enhancement and noise removal are coupled problems for low-light image enhancement.
Sensor-Augmented Neural Adaptive Bitrate Video Streaming on UAVs
In this paper, we present SA-ABR, a new sensor-augmented system that generates ABR video streaming algorithms with the assistance of various kinds of inherent sensor data that are used to pilot UAVs.
EGNet:Edge Guidance Network for Salient Object Detection
In the second step, we integrate the local edge information and global location information to obtain the salient edge features.
One-Shot Texture Retrieval with Global Context Metric
In this paper, we tackle one-shot texture retrieval: given an example of a new reference texture, detect and segment all the pixels of the same texture category within an arbitrary image.
Reinforcement Learning for Optimal Load Distribution Sequencing in Resource-Sharing System
Divisible Load Theory (DLT) is a powerful tool for modeling divisible load problems in data-intensive systems.
Deep Time-Frequency Representation and Progressive Decision Fusion for ECG Classification
Early recognition of abnormal rhythms in ECG signals is crucial for monitoring and diagnosing patients' cardiac conditions, increasing the success rate of the treatment.
Enhanced-alignment Measure for Binary Foreground Map Evaluation
The existing binary foreground map (FM) measures to address various types of errors in either pixel-wise or structural ways.
Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit
Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with unknown reward distributions.
Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images
Specifically, we propose to randomly shuffle the pixels in the origin images and leverage the shuffled image as input to make CNN more concerned with the statistical properties.
Quantifying Differential Privacy in Continuous Data Release under Temporal Correlations
Our analysis reveals that, the event-level privacy loss of a DP mechanism may \textit{increase over time}.
Databases
Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior
Then, we propose a simple but effective image prior, maximum reflectance prior, to estimate the varying ambient illumination.
Nearly second-order asymptotic optimality of sequential change-point detection with one-sample updates
Our proof is achieved by making a connection between sequential change-point and online convex optimization and leveraging the logarithmic regret bound property of online mirror descent algorithm.
Quantifying Differential Privacy under Temporal Correlations
Our analysis reveals that the privacy leakage of a DP mechanism may accumulate and increase over time.
Databases Cryptography and Security
Nighttime Haze Removal with Illumination Correction
ii) Then it achieves a color-balance result by performing a color correction step after estimating the color characteristics of the incident light.
Multi-Sensor Slope Change Detection
Observations are assumed to be initially normal random variables with known constant means and variances.
Categorical Matrix Completion
We recover a low-rank matrix $X$ by maximizing the likelihood ratio with a constraint on the nuclear norm of $X$, and the observations are mapped from entries of $X$ through multiple link functions.
Sketching for Sequential Change-Point Detection
We study sequential change-point detection procedures based on linear sketches of high-dimensional signal vectors using generalized likelihood ratio (GLR) statistics.
Poisson Matrix Recovery and Completion
We extend the theory of low-rank matrix recovery and completion to the case when Poisson observations for a linear combination or a subset of the entries of a matrix are available, which arises in various applications with count data.
Poisson Matrix Completion
We extend the theory of matrix completion to the case where we make Poisson observations for a subset of entries of a low-rank matrix.
Fast Algorithm for Low-rank matrix recovery in Poisson noise
This paper describes a fast algorithm for recovering low-rank matrices from their linear measurements contaminated with Poisson noise: the Poisson noise Maximum Likelihood Singular Value thresholding (PMLSV) algorithm.
