Search Results for author:
Found 34 papers, 11 papers with code
ITPNet: Towards Instantaneous Trajectory Prediction for Autonomous Driving
Trajectory prediction of agents is crucial for the safety of autonomous vehicles, whereas previous approaches usually rely on sufficiently long-observed trajectory to predict the future trajectory of the agents.
DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model
However, it is difficult to access the training dataset of the target black-box model in reality.
Retrieval-Augmented Personalization for Multimodal Large Language Models
To further improve generation quality and alignment with user-specific information, we design a pipeline for data collection and create a specialized dataset for personalized training of MLLMs.
Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
In this way, we can preserve the low-rank constraint in the optimizer while achieving full-rank training for better performance.
Keypoint-based Progressive Chain-of-Thought Distillation for LLMs
Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models.
On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving
However, the oversized neural networks render them impractical for deployment on resource-constrained systems, which unavoidably requires more computational time and resources during reference. To handle this, knowledge distillation offers a promising approach that compresses models by enabling a smaller student model to learn from a larger teacher model.
Learning to Generate Parameters of ConvNets for Unseen Image Data
Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e. g., SGD or Adam) to learn network parameters, which makes training very time- and resource-intensive.
DREAM: Domain-free Reverse Engineering Attributes of Black-box Model
There is a crucial limitation: these works assume the dataset used for training the target model to be known beforehand and leverage this dataset for model attribute attack.
Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation
Knowledge distillation (KD) has shown to be effective to boost the performance of graph neural networks (GNNs), where the typical objective is to distill knowledge from a deeper teacher GNN into a shallower student GNN.
Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score
Last, we propose an EPS-based adversarial detection (EPS-AD) method, in which we develop EPS-based maximum mean discrepancy (MMD) as a metric to measure the discrepancy between the test sample and natural samples.
Towards Open Temporal Graph Neural Networks
This will bring two big challenges to the existing dynamic GNN methods: (i) How to dynamically propagate appropriate information in an open temporal graph, where new class nodes are often linked to old class nodes.
Robust Knowledge Adaptation for Dynamic Graph Neural Networks
By this means, we can adaptively propagate knowledge to other nodes for learning robust node embedding representations.
Multi-Prior Learning via Neural Architecture Search for Blind Face Restoration
To this end, we propose a Face Restoration Searching Network (FRSNet) to adaptively search the suitable feature extraction architecture within our specified search space, which can directly contribute to the restoration quality.
FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks
Knowledge distillation (KD) has demonstrated its effectiveness to boost the performance of graph neural networks (GNNs), where its goal is to distill knowledge from a deeper teacher GNN into a shallower student GNN.
Blind Face Restoration: Benchmark Datasets and a Baseline Model
To address this problem, we first synthesize two blind face restoration benchmark datasets called EDFace-Celeb-1M (BFR128) and EDFace-Celeb-150K (BFR512).
Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clustering
Inheriting the advantages from information bottleneck, SIB-MSC can learn a latent space for each view to capture common information among the latent representations of different views by removing superfluous information from the view itself while retaining sufficient information for the latent representations of other views.
Deep Unsupervised Active Learning on Learnable Graphs
To make the learnt graph structure more stable and effective, we take into account $k$-nearest neighbor graph as a priori, and learn a relation propagation graph structure.
Learning Deep Representation with Energy-Based Self-Expressiveness for Subspace Clustering
In this paper, we propose a new deep subspace clustering framework, motivated by the energy-based models.
Action Shuffling for Weakly Supervised Temporal Localization
Weakly supervised action localization is a challenging task with extensive applications, which aims to identify actions and the corresponding temporal intervals with only video-level annotations available.
Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior
We first use a coarse deraining network to reduce the rain streaks on the input images, and then adopt a pre-trained semantic segmentation network to extract semantic features from the coarse derained image.
Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors
Images captured in snowy days suffer from noticeable degradation of scene visibility, which degenerates the performance of current vision-based intelligent systems.
Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions
Active learning generally involves querying the most representative samples for human labeling, which has been widely studied in many fields such as image classification and object detection.
On Deep Unsupervised Active Learning
Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating.
Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification
In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem.
AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance.
Similarity Learning via Kernel Preserving Embedding
Data similarity is a key concept in many data-driven applications.
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
Action recognition in videos has attracted a lot of attention in the past decade.
Autoencoder Regularized Network For Driving Style Representation Learning
In this paper, we study learning generalized driving style representations from automobile GPS trip data.
Characterizing Driving Styles with Deep Learning
Characterizing driving styles of human drivers using vehicle sensor data, e. g., GPS, is an interesting research problem and an important real-world requirement from automotive industries.
Self-Paced Multi-Task Learning
In this paper, we propose a novel multi-task learning (MTL) framework, called Self-Paced Multi-Task Learning (SPMTL).
A Self-Paced Regularization Framework for Multi-Label Learning
In this paper, we propose a novel multi-label learning framework, called Multi-Label Self-Paced Learning (MLSPL), in an attempt to incorporate the self-paced learning strategy into multi-label learning regime.
Joint Active Learning with Feature Selection via CUR Matrix Decomposition
In particular, our method runs in one-shot without the procedure of iterative sample selection for progressive labeling.
Dynamic Structure Embedded Online Multiple-Output Regression for Stream Data
MORES can \emph{dynamically} learn the structure of the coefficients change in each update step to facilitate the model's continuous refinement.
Max-Margin based Discriminative Feature Learning
In this paper, we propose a new max-margin based discriminative feature learning method.
