Search Results for author:
Found 22 papers, 6 papers with code
GPS: Distilling Compact Memories via Grid-based Patch Sampling for Efficient Online Class-Incremental Learning
Online class-incremental learning aims to enable models to continuously adapt to new classes with limited access to past data, while mitigating catastrophic forgetting.
Style Quantization for Data-Efficient GAN Training
Instead of direct quantization, we first map the input latent variables into a less entangled ``style'' space and apply quantization using a learnable codebook.
Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints
In the realm of high-frequency data streams, achieving real-time learning within varying memory constraints is paramount.
E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing
Specifically, we propose a systematical algorithm termed Extended Single-Step Synthetic Features Compressing (E-3SFC), which consists of three sub-components, i. e., the Single-Step Synthetic Features Compressor (3SFC), a double-way compression algorithm, and a communication budget scheduler.
MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data
Generative adversarial networks (GANs) have made impressive advances in image generation, but they often require large-scale training data to avoid degradation caused by discriminator overfitting.
An Empirical Study of Parameter Efficient Fine-tuning on Vision-Language Pre-train Model
A natural expectation for PEFTs is that the performance of various PEFTs is positively related to the data size and fine-tunable parameter size.
Federated cINN Clustering for Accurate Clustered Federated Learning
However, a significant challenge arises when coordinating FL with crowd intelligence which diverse client groups possess disparate objectives due to data heterogeneity or distinct tasks.
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential
Next, we construct a graph convolution training acceleration mechanism to optimize the back-propagation computing of dynamic graph learning with 55. 08\% speed-up.
Ranked #8 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Que2Engage: Embedding-based Retrieval for Relevant and Engaging Products at Facebook Marketplace
In this paper we presents Que2Engage, a search EBR system built towards bridging the gap between retrieval and ranking for end-to-end optimizations.
DeFTA: A Plug-and-Play Decentralized Replacement for FedAvg
Federated learning (FL) is identified as a crucial enabler for large-scale distributed machine learning (ML) without the need for local raw dataset sharing, substantially reducing privacy concerns and alleviating the isolated data problem.
Image Search with Text Feedback by Additive Attention Compositional Learning
Effective image retrieval with text feedback stands to impact a range of real-world applications, such as e-commerce.
Hierarchical Segment-based Optimization for SLAM
This paper presents a hierarchical segment-based optimization method for Simultaneous Localization and Mapping (SLAM) system.
Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observations
We introduce an experience replay approach to tackle an exemplary task of continual neural mapping: approximating a continuous signed distance function (SDF) from sequential depth images as a scene geometry representation.
AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptation
Neural network-based semantic segmentation has achieved remarkable results when large amounts of annotated data are available, that is, in the supervised case.
Discriminative and Semantic Feature Selection for Place Recognition towards Dynamic Environments
In this paper, we address the challenges of place recognition due to dynamics and confusable patterns by proposing a discriminative and semantic feature selection network, dubbed as DSFeat.
A Collaborative Visual SLAM Framework for Service Robots
We present a collaborative visual simultaneous localization and mapping (SLAM) framework for service robots.
Scale Aware Adaptation for Land-Cover Classification in Remote Sensing Imagery
Land-cover classification using remote sensing imagery is an important Earth observation task.
RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Features for Indoor Localization
Experimental results show that the proposed RaP-Net trained with OpenLORIS-Location dataset achieves excellent performance in the feature matching task and significantly outperforms state-of-the-arts feature algorithms in indoor localization.
iffDetector: Inference-aware Feature Filtering for Object Detection
In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages.
Generalizing Deep Models for Overhead Image Segmentation Through Getis-Ord Gi* Pooling
Inspired by this, we investigate methods to inform or guide deep learning models for geospatial image analysis to increase their performance when a limited amount of training data is available or when they are applied to scenarios other than which they were trained on.
Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM
We also design benchmarking metrics for lifelong SLAM, with which the robustness and accuracy of pose estimation are evaluated separately.
Task-oriented Word Embedding for Text Classification
In this paper, we propose a task-oriented word embedding method and apply it to the text classification task.
Ranked #23 on
Text Classification
on AG News
