Search Results for author:
Found 38 papers, 22 papers with code
Reducing Distributional Uncertainty by Mutual Information Maximisation and Transferable Feature Learning
Distributional uncertainty exists broadly in many real-world applications, one of which in the form of domain discrepancy.
An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
Heterogeneous Federated Learning (HtFL) enables collaborative learning on multiple clients with different model architectures while preserving privacy.
CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
In response, we present Contrasting Gradient Inversion for Diffusion Models (CGI-DM), a novel method featuring vivid visual representations for digital copyright authentication.
Efficient One-stage Video Object Detection by Exploiting Temporal Consistency
Based on the analysis, we present a simple yet efficient framework to address the computational bottlenecks and achieve efficient one-stage VOD by exploiting the temporal consistency in video frames.
TDViT: Temporal Dilated Video Transformer for Dense Video Tasks
Deep video models, for example, 3D CNNs or video transformers, have achieved promising performance on sparse video tasks, i. e., predicting one result per video.
Spatio-temporal Prompting Network for Robust Video Feature Extraction
Then, these video prompts are prepended to the patch embeddings of the current frame as the updated input for video feature extraction.
MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection
However, we argue that these memory structures are not efficient or sufficient because of two implied operations: (1) concatenating all features in memory for enhancement, leading to a heavy computational cost; (2) frame-wise memory updating, preventing the memory from capturing more temporal information.
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
To reduce the high communication cost of transmitting model parameters, a major challenge in HtFL, prototype-based HtFL methods are proposed to solely share class representatives, a. k. a, prototypes, among heterogeneous clients while maintaining the privacy of clients' models.
SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks
Specifically, the FL server applies parameter-level masks to model updates uploaded by clients and trains the masks over a small clean dataset (i. e., root dataset) to learn the subtle difference between benign and malicious model updates in a high-dimension space.
PFLlib: Personalized Federated Learning Algorithm Library
Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL) has gained significant prominence as a research direction within the FL domain.
Eliminating Domain Bias for Federated Learning in Representation Space
Recently, federated learning (FL) is popular for its privacy-preserving and collaborative learning abilities.
GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning
Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities.
Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
Federated learning (FL) has been widely deployed to enable machine learning training on sensitive data across distributed devices.
FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
To address this, we propose the Federated Conditional Policy (FedCP) method, which generates a conditional policy for each sample to separate the global information and personalized information in its features and then processes them by a global head and a personalized head, respectively.
Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style.
FedALA: Adaptive Local Aggregation for Personalized Federated Learning
A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client.
ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State
For the issue (2), the effectiveness of ProSelfLC defends entropy minimisation.
Parallel Network with Channel Attention and Post-Processing for Carotid Arteries Vulnerable Plaque Segmentation in Ultrasound Images
Test results show that the proposed method with dice loss function yields a Dice value of 0. 820, an IoU of 0. 701, Acc of 0. 969, and modified Hausdorff distance (MHD) of 1. 43 for 30 vulnerable cases of plaques, it outperforms some of the conventional CNN-based methods on these metrics.
Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques
Deep learning is pervasive in our daily life, including self-driving cars, virtual assistants, social network services, healthcare services, face recognition, etc.
Robust Bayesian Neural Networks by Spectral Expectation Bound Regularization
Bayesian neural networks have been widely used in many applications because of the distinctive probabilistic representation framework.
Fast and Accurate Scene Parsing via Bi-direction Alignment Networks
Motivated by this, we propose a novel network by aligning two-path information into each other through a learned flow field.
Self-Supervised Vessel Segmentation via Adversarial Learning
Vessel segmentation is critically essential for diagnosinga series of diseases, e. g., coronary artery disease and retinal disease.
Off-Policy Self-Critical Training for Transformer in Visual Paragraph Generation
We tackle this problem by proposing an off-policy RL learning algorithm where a behaviour policy represented by GRUs performs the sampling.
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
Keywords: entropy minimisation, maximum entropy, confidence penalty, self knowledge distillation, label correction, label noise, semi-supervised learning, output regularisation
ParaCNN: Visual Paragraph Generation via Adversarial Twin Contextual CNNs
Furthermore, to enable the ParaCNN to model paragraph comprehensively, we also propose an adversarial twin net training scheme.
Object-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation
This strategy efficiently filters out some irrelevant proposals and avoids the redundant computation for feature extraction, which enables our method to operate faster than conventional classification-based tracking methods.
Instance Cross Entropy for Deep Metric Learning
Loss functions play a crucial role in deep metric learning thus a variety of them have been proposed.
ID-aware Quality for Set-based Person Re-identification
This way it can prevent overfitting to trivial images, and alleviate the influence of outliers.
ROBUST DISCRIMINATIVE REPRESENTATION LEARNING VIA GRADIENT RESCALING: AN EMPHASIS REGULARISATION PERSPECTIVE
It is fundamental and challenging to train robust and accurate Deep Neural Networks (DNNs) when semantically abnormal examples exist.
Derivative Manipulation for General Example Weighting
By DM, we connect the design of loss function and example weighting together.
Ranked #30 on
Image Classification
on Clothing1M
(using extra training data)
IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters
In this work, we study robust deep learning against abnormal training data from the perspective of example weighting built in empirical loss functions, i. e., gradient magnitude with respect to logits, an angle that is not thoroughly studied so far.
Ranked #33 on
Image Classification
on Clothing1M
(using extra training data)
GAN-based Pose-aware Regulation for Video-based Person Re-identification
Video-based person re-identification deals with the inherent difficulty of matching unregulated sequences with different length and with incomplete target pose/viewpoint structure.
Ranked List Loss for Deep Metric Learning
To address this, we propose to build a set-based similarity structure by exploiting all instances in the gallery.
IEGAN: Multi-purpose Perceptual Quality Image Enhancement Using Generative Adversarial Network
Despite the breakthroughs in quality of image enhancement, an end-to-end solution for simultaneous recovery of the finer texture details and sharpness for degraded images with low resolution is still unsolved.
Deep Metric Learning by Online Soft Mining and Class-Aware Attention
Therefore, we propose a novel sample mining method, called Online Soft Mining (OSM), which assigns one continuous score to each sample to make use of all samples in the mini-batch.
Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States
To advance subtle expression recognition, we contribute a Large-scale Subtle Emotions and Mental States in the Wild database (LSEMSW).
Attribute-Enhanced Face Recognition With Neural Tensor Fusion Networks
To solve this problem, we establish a theoretical equivalence between tensor optimisation and a two-stream gated neural network.
Online Object Tracking with Proposal Selection
Tracking-by-detection approaches are some of the most successful object trackers in recent years.
