Search Results for author:
Found 20 papers, 6 papers with code
Distance Metric Learning with Joint Representation Diversification
Distance metric learning (DML) is to learn a representation space equipped with a metric, such that examples from the same class are closer than examples from different classes with respect to the metric.
LoRA Dropout as a Sparsity Regularizer for Overfitting Control
We then demonstrate the theoretical mechanism of our LoRA Dropout mechanism from the perspective of sparsity regularization by providing a generalization error bound under this framework.
Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
With the increasingly powerful performances and enormous scales of Pretrained Language Models (PLMs), promoting parameter efficiency in fine-tuning has become a crucial need for effective and efficient adaptation to various downstream tasks.
ProNet: Progressive Neural Network for Multi-Horizon Time Series Forecasting
In this paper, we introduce ProNet, an novel deep learning approach designed for multi-horizon time series forecasting, adaptively blending autoregressive (AR) and non-autoregressive (NAR) strategies.
AMLNet: Adversarial Mutual Learning Neural Network for Non-AutoRegressive Multi-Horizon Time Series Forecasting
This knowledge transfer is facilitated through two key mechanisms: 1) outcome-driven KD, which dynamically weights the contribution of KD losses from the teacher models, enabling the shallow NAR decoder to incorporate the ensemble's diversity; and 2) hint-driven KD, which employs adversarial training to extract valuable insights from the model's hidden states for distillation.
Learning to Correct Noisy Labels for Fine-Grained Entity Typing via Co-Prediction Prompt Tuning
Fine-grained entity typing (FET) is an essential task in natural language processing that aims to assign semantic types to entities in text.
A Boundary Offset Prediction Network for Named Entity Recognition
By leveraging the guiding semantics of boundary offsets, BOPN establishes connections between non-entity and entity spans, enabling non-entity spans to function as additional positive samples for entity detection.
Coupling a Recurrent Neural Network to SPAD TCSPC Systems for Real-time Fluorescence Lifetime Imaging
To explore the ultimate limits of the approach, we derived the Cramer-Rao lower bound of the measurement, showing that RNN yields lifetime estimations with near-optimal precision.
Empirical Analysis of AI-based Energy Management in Electric Vehicles: A Case Study on Reinforcement Learning
The empirical analysis is developed in four aspects: algorithm, perception and decision granularity, hyperparameters, and reward function.
Progress and summary of reinforcement learning on energy management of MPS-EV
RL has received continuous attention and research, but there is still a lack of systematic analysis of the design elements of RL-based EMS.
Fetal Brain Tissue Annotation and Segmentation Challenge Results
Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context.
Benchmarking Deep Models for Salient Object Detection
In recent years, deep network-based methods have continuously refreshed state-of-the-art performance on Salient Object Detection (SOD) task.
SSDNet: State Space Decomposition Neural Network for Time Series Forecasting
In this paper, we present SSDNet, a novel deep learning approach for time series forecasting.
FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
Network quantization significantly reduces model inference complexity and has been widely used in real-world deployments.
Ranked #1 on
Quantization
on ImageNet
Temporal Convolutional Attention Neural Networks for Time Series Forecasting
TCAN requires less number of convolutional layers than TCNN for an extended receptive field, is faster to train and is able to visualize the most important timesteps for the prediction.
Multivariate Time Series Forecasting
Probabilistic Time Series Forecasting
+1
A Scalable Optimization Mechanism for Pairwise based Discrete Hashing
Based on this significant discovery and the proposed strategy, we introduce a scalable symmetric discrete hashing algorithm that gradually and smoothly updates each batch of binary codes.
Multi-Label Robust Factorization Autoencoder and its Application in Predicting Drug-Drug Interactions
However, the shallow models leveraging bilinear forms suffer from limitations on capturing complicated nonlinear interactions between drug pairs.
ConvPath: A Software Tool for Lung Adenocarcinoma Digital Pathological Image Analysis Aided by Convolutional Neural Network
By identifying cells and classifying cell types, this pipeline can convert a pathology image into a spatial map of tumor, stromal and lymphocyte cells.
A vision based system for underwater docking
In the experiments, we first evaluate performance of the proposed detection module on UDID and its deformed variations.
Forward Backward Similarity Search in Knowledge Networks
Similarity search is a fundamental problem in social and knowledge networks like GitHub, DBLP, Wikipedia, etc.
