Search Results for author:
Found 46 papers, 13 papers with code
Drift to Remember
Tested on GPT-2 and RoBERTa, DriftNet is a robust, cost-effective solution for lifelong learning in LLMs.
Are Large Language Models Possible to Conduct Cognitive Behavioral Therapy?
Many concerns have been raised by mental health experts regarding the use of LLMs for therapy.
Focus on Low-Resolution Information: Multi-Granular Information-Lossless Model for Low-Resolution Human Pose Estimation
Furthermore, we design a Coarse-grained Information Interaction (CII) module to adequately leverage human body structural information.
Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation
In this framework, we construct a scale-adaptive projector ensemble (SAPE) module to spatially align feature maps between models of varying input resolutions.
Patch Spatio-Temporal Relation Prediction for Video Anomaly Detection
To mitigate memory consumption, we convert the order information prediction task into a multi-label learning problem, and the inter-patch similarity prediction task into a distance matrix regression problem.
A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint
There are two distinctions between nighttime and daytime haze.
AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior
Language significantly influences the formation and evolution of Human emergent behavior, which is crucial in understanding collective intelligence within human societies.
Mutual Information-driven Triple Interaction Network for Efficient Image Dehazing
Multi-stage architectures have exhibited efficacy in image dehazing, which usually decomposes a challenging task into multiple more tractable sub-tasks and progressively estimates latent hazy-free images.
Potential-based Credit Assignment for Cooperative RL-based Testing of Autonomous Vehicles
While autonomous vehicles (AVs) may perform remarkably well in generic real-life cases, their irrational action in some unforeseen cases leads to critical safety concerns.
SPSQL: Step-by-step Parsing Based Framework for Text-to-SQL Generation
Then, we construct data formats of different subtasks based on existing data and improve the accuracy of the overall model by improving the accuracy of each submodel.
Autoencoders with Intrinsic Dimension Constraints for Learning Low Dimensional Image Representations
Motivated by the important role of ID, in this paper, we propose a novel deep representation learning approach with autoencoder, which incorporates regularization of the global and local ID constraints into the reconstruction of data representations.
UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
Trained on our synthesized large-scale dexterous grasp dataset, this model enables us to sample diverse and high-quality dexterous grasp poses for the object point cloud. For the second stage, we propose to replace the motion planning used in parallel gripper grasping with a goal-conditioned grasp policy, due to the complexity involved in dexterous grasping execution.
Adaptive Dynamic Filtering Network for Image Denoising
To alleviate these issues, we propose to employ dynamic convolution to improve the learning of high-frequency and multi-scale features.
ISA-Net: Improved spatial attention network for PET-CT tumor segmentation
In this paper, we propose a deep learning segmentation method based on multimodal positron emission tomography-computed tomography (PET-CT), which combines the high sensitivity of PET and the precise anatomical information of CT. We design an improved spatial attention network(ISA-Net) to increase the accuracy of PET or CT in detecting tumors, which uses multi-scale convolution operation to extract feature information and can highlight the tumor region location information and suppress the non-tumor region location information.
Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey
The availability of representative datasets is an essential prerequisite for many successful artificial intelligence and machine learning models.
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description.
Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classification
We propose an algorithmic framework that leverages the advantages of the DNNs for data self-expression and task-specific predictions, to improve image classification.
Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrations
Generalizable object manipulation skills are critical for intelligent and multi-functional robots to work in real-world complex scenes.
HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction.
Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy.
Identifying Influential Users in Unknown Social Networks for Adaptive Incentive Allocation Under Budget Restriction
To tackle the aforementioned challenges, in this paper, we propose a novel algorithm for exploring influential users in unknown networks, which can estimate the influential relationships among users based on their historical behaviors and without knowing the topology of the network.
Deep auxiliary learning for visual localization using colorization task
Meanwhile an attention mechanism is introduced for the benefit of localization performance.
Analysis and Optimisation of Bellman Residual Errors with Neural Function Approximation
First, we conduct a critical point analysis of the error function and provide technical insights on optimisation and design choices for neural networks.
Large $N$ limit of the $O(N)$ linear sigma model in 3D
We prove tightness of the invariant measures in the large N limit.
Quantization
Probability
Mathematical Physics
Analysis of PDEs
Mathematical Physics
Dynamic Texture Recognition via Nuclear Distances on Kernelized Scattering Histogram Spaces
Distance-based dynamic texture recognition is an important research field in multimedia processing with applications ranging from retrieval to segmentation of video data.
Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning
This white paper provides an introduction and discussion of this emerging field in machine learning research.
End-to-End Video Instance Segmentation with Transformers
Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem.
Ranked #24 on
Video Instance Segmentation
on YouTube-VIS validation
Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes
Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and localization of vision-based robots.
Metapath- and Entity-aware Graph Neural Network for Recommendation
In this paper, we employ collaborative subgraphs (CSGs) and metapaths to form metapath-aware subgraphs, which explicitly capture sequential semantics in graph structures.
Ranked #1 on
Link Prediction
on MovieLens 25M
3D Scene Geometry-Aware Constraint for Camera Localization with Deep Learning
Camera localization is a fundamental and key component of autonomous driving vehicles and mobile robots to localize themselves globally for further environment perception, path planning and motion control.
CenterMask: single shot instance segmentation with point representation
Accordingly, we decompose the instance segmentation into two parallel subtasks: Local Shape prediction that separates instances even in overlapping conditions, and Global Saliency generation that segments the whole image in a pixel-to-pixel manner.
A New Dataset and Boundary-Attention Semantic Segmentation for Face Parsing
The dataset is publicly accessible to the community for boosting the advance of face parsing. 1 Second, a simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a three-branch network with elaborately developed loss functions to fully exploit the boundary information.
Ranked #9 on
Face Parsing
on LaPa
A High-Efficiency Framework for Constructing Large-Scale Face Parsing Benchmark
Each image is provided with accurate annotation of a 11-category pixel-level label map along with coordinates of 106-point landmarks.
Grand Challenge of 106-Point Facial Landmark Localization
However, previous competitions on facial landmark localization (i. e., the 300-W, 300-VW and Menpo challenges) aim to predict 68-point landmarks, which are incompetent to depict the structure of facial components.
Joint Learning of Discriminative Low-dimensional Image Representations Based on Dictionary Learning and Two-layer Orthogonal Projections
There are some inadequacies in the language description of this paper that require further improvement.
A Generative Map for Image-based Camera Localization
For localization, we show that Generative Map achieves comparable performance with current regression models.
A Differential Topological View of Challenges in Learning with Feedforward Neural Networks
Among many unsolved puzzles in theories of Deep Neural Networks (DNNs), there are three most fundamental challenges that highly demand solutions, namely, expressibility, optimisability, and generalisability.
Trace Quotient with Sparsity Priors for Learning Low Dimensional Image Representations
We propose a generic algorithmic framework, which leverages two classic representation learning paradigms, i. e., sparse representation and the trace quotient criterion.
Dynamic Variational Autoencoders for Visual Process Modeling
This work studies the problem of modeling visual processes by leveraging deep generative architectures for learning linear, Gaussian representations from observed sequences.
Towards a Mathematical Understanding of the Difficulty in Learning with Feedforward Neural Networks
Training deep neural networks for solving machine learning problems is one great challenge in the field, mainly due to its associated optimisation problem being highly non-convex.
Reinforcement Learning in Conflicting Environments for Autonomous Vehicles
In this work, we investigate the application of Reinforcement Learning to two well known decision dilemmas, namely Newcomb's Problem and Prisoner's Dilemma.
$\ell_1$ Regularized Gradient Temporal-Difference Learning
In this paper, we study the Temporal Difference (TD) learning with linear value function approximation.
Trace Quotient Meets Sparsity: A Method for Learning Low Dimensional Image Representations
This paper presents an algorithm that allows to learn low dimensional representations of images in an unsupervised manner.
Subsampled terahertz data reconstruction based on spatio-temporal dictionary learning
In this paper, the problem of terahertz pulsed imaging and reconstruction is addressed.
Texture Retrieval via the Scattering Transform
Our approach employs a recently developed method, the so-called Scattering transform, for the process of feature extraction in texture retrieval.
An Adaptive Dictionary Learning Approach for Modeling Dynamical Textures
Video representation is an important and challenging task in the computer vision community.
