Search Results for author:
Found 28 papers, 7 papers with code
On Isotropy Calibration of Transformer Models
Different studies of the embedding space of transformer models suggest that the distribution of contextual representations is highly anisotropic - the embeddings are distributed in a narrow cone.
Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting
Our framework and model introduce the following key aspects: (1) to learn real-world adaptive semantic representation for objects with diverse and complex structures under real-world scenes, we introduce extra semantic segmentation and edge detection tasks on more diverse real-world data with segmentation annotations; (2) to avoid overfitting on low-level details, we propose a module to utilize the inconsistency between learned segmentation and matting representations to regularize detail refinement; (3) we propose a novel background line detection task into our auxiliary learning framework, to suppress interference of background lines or textures.
Data-driven Energy Consumption Modelling for Electric Micromobility using an Open Dataset
Furthermore, we provide a comprehensive analysis of energy consumption modelling based on the dataset using a set of representative machine learning algorithms and compare their performance against the contemporary mathematical models as a baseline.
Perceptual learning in contour detection transfer across changes in contour path and orientation
The integration of local elements into shape contours is critical for target detection and identification in cluttered scenes.
Optimal Design and Implementation of an Open-source Emulation Platform for User-Centric Shared E-mobility Services
In response to the escalating global challenge of increasing emissions and pollution in transportation, shared electric mobility services, encompassing e-cars, e-bikes, and e-scooters, have emerged as a popular strategy.
YOLO-MED : Multi-Task Interaction Network for Biomedical Images
Object detection and semantic segmentation are pivotal components in biomedical image analysis.
Task Indicating Transformer for Task-conditional Dense Predictions
The task-conditional model is a distinctive stream for efficient multi-task learning.
Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study
The innovative Federated Multi-Task Learning (FMTL) approach consolidates the benefits of Federated Learning (FL) and Multi-Task Learning (MTL), enabling collaborative model training on multi-task learning datasets.
Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training
The 2D human pose estimation (HPE) is a basic visual problem.
Enhancing cross-domain detection: adaptive class-aware contrastive transformer
Recently, the detection transformer has gained substantial attention for its inherent minimal post-processing requirement. However, this paradigm relies on abundant training data, yet in the context of the cross-domain adaptation, insufficient labels in the target domain exacerbate issues of class imbalance and model performance degradation. To address these challenges, we propose a novel class-aware cross domain detection transformer based on the adversarial learning and mean-teacher framework. First, considering the inconsistencies between the classification and regression tasks, we introduce an IoU-aware prediction branch and exploit the consistency of classification and location scores to filter and reweight pseudo labels. Second, we devise a dynamic category threshold refinement to adaptively manage model confidence. Third, to alleviate the class imbalance, an instance-level class-aware contrastive learning module is presented to encourage the generation of discriminative features for each class, particularly benefiting minority classes. Experimental results across diverse domain-adaptive scenarios validate our method's effectiveness in improving performance and alleviating class imbalance issues, which outperforms the state-of-the-art transformer based methods.
PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation
In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM.
Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure
Then, we introduce a penalty to items with high exposure probability to avoid the overestimation of user preference for biased samples.
FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning
Moreover, we employ learnable Hyper Aggregation Weights for each client to customize personalized parameter updates.
UNIDEAL: Curriculum Knowledge Distillation Federated Learning
Federated Learning (FL) has emerged as a promising approach to enable collaborative learning among multiple clients while preserving data privacy.
Prompt Guided Transformer for Multi-Task Dense Prediction
Task-conditional architecture offers advantage in parameter efficiency but falls short in performance compared to state-of-the-art multi-decoder methods.
BPJDet: Extended Object Representation for Generic Body-Part Joint Detection
In this paper, we focus on the joint detection of human body and its parts.
EDEN: A Plug-in Equivariant Distance Encoding to Beyond the 1-WL Test
While most existing message-passing graph neural networks (MPNNs) are permutation-invariant in graph-level representation learning and permutation-equivariant in node- and edge-level representation learning, their expressive power is commonly limited by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test.
Position-Aware Subgraph Neural Networks with Data-Efficient Learning
2) Prevailing graph augmentation methods for GEL, including rule-based, sample-based, adaptive, and automated methods, are not suitable for augmenting subgraphs because a subgraph contains fewer nodes but richer information such as position, neighbor, and structure.
Completely Heterogeneous Federated Learning
Federated learning (FL) faces three major difficulties: cross-domain, heterogeneous models, and non-i. i. d.
NoMorelization: Building Normalizer-Free Models from a Sample's Perspective
The normalizing layer has become one of the basic configurations of deep learning models, but it still suffers from computational inefficiency, interpretability difficulties, and low generality.
Task Aligned Meta-learning based Augmented Graph for Cold-Start Recommendation
In this paper, we propose a Task aligned Meta-learning based Augmented Graph (TMAG) to address cold-start recommendation.
On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach
Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations.
FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform
A specialized pipeline is designed, and we further propose a frequency loss function to fit the nature of our frequency-domain task.
Extracting Attentive Social Temporal Excitation for Sequential Recommendation
In this paper, we propose a novel time-aware sequential recommendation framework called Social Temporal Excitation Networks (STEN), which introduces temporal point processes to model the fine-grained impact of friends' behaviors on the user s dynamic interests in an event-level direct paradigm.
ICPE: An Item Cluster-Wise Pareto-Efficient Framework for Recommendation Debiasing
In detail, we define our item cluster-wise optimization target as the recommender model should balance all item clusters that differ in popularity, thus we set the model learning on each item cluster as a unique optimization objective.
On Isotropy Calibration of Transformers
Different studies of the embedding space of transformer models suggest that the distribution of contextual representations is highly anisotropic - the embeddings are distributed in a narrow cone.
DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction
In this paper, we propose a novel model named DemiNet (short for DEpendency-Aware Multi-Interest Network) to address the above two issues.
Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation
To solve the above problem, in this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation.
