Search Results for author:
Found 67 papers, 27 papers with code
CN: Channel Normalization For Point Cloud Recognition
In 3D recognition, to fuse multi-scale structure information, existing methods apply hierarchical frameworks stacked by multiple fusion layers for integrating current relative locations with structure information from the previous level.
Surrogate-Assisted Evolution for Efficient Multi-branch Connection Design in Deep Neural Networks
To efficiently design the DNNs, we use surrogate-assisted EAs.
Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
While numerous CL methods aim to achieve this trade-off, they often overlook the impact of network architecture on stability and plasticity, restricting the trade-off to the parameter level.
Adapt before Continual Learning
Continual Learning (CL) seeks to enable neural networks to incrementally acquire new knowledge (plasticity) while retaining existing knowledge (stability).
LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models
Experimental results on six language models and two vision-language models demonstrate that LAS achieves loss-less conversion.
Detect Anything 3D in the Wild
Despite the success of deep learning in close-set 3D object detection, existing approaches struggle with zero-shot generalization to novel objects and camera configurations.
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?
Multi-step spatial reasoning entails understanding and reasoning about spatial relationships across multiple sequential steps, which is crucial for tackling complex real-world applications, such as robotic manipulation, autonomous navigation, and automated assembly.
FaceShot: Bring Any Character into Life
With this powerful generalization capability, FaceShot can significantly extend the application of portrait animation by breaking the limitation of realistic portrait landmark detection for any stylized character and driven video.
FAS: Fast ANN-SNN Conversion for Spiking Large Language Models
Existing methods for creating Spiking LLMs, i. e., direct training and ANN-SNN conversion, often suffer from performance degradation and relatively high computational costs.
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.
Test-time Correction with Human Feedback: An Online 3D Detection System via Visual Prompting
This paper introduces Test-time Correction (TTC) system, a novel online 3D detection system designated for online correction of test-time errors via human feedback, to guarantee the safety of deployed autonomous driving systems.
An Architectural Approach to Enhance Deep Long-Tailed Learning
This ensures that the architecture obtained through our search process incorporates superior components.
StyleShot: A Snapshot on Any Style
In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning.
Ranked #1 on
Style Transfer
on StyleBench
AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation
To address these challenges, we propose AnyControl, a multi-control image synthesis framework that supports arbitrary combinations of diverse control signals.
CAP: A Context-Aware Neural Predictor for NAS
Neural predictors are effective in boosting the time-consuming performance evaluation stage in neural architecture search (NAS), owing to their direct estimation of unseen architectures.
Towards Accurate and Robust Architectures via Neural Architecture Search
To defend deep neural networks from adversarial attacks, adversarial training has been drawing increasing attention for its effectiveness.
Revisiting Neural Networks for Continual Learning: An Architectural Perspective
This paper seeks to bridge this gap between network architecture design and CL, and to present a holistic study on the impact of network architectures on CL.
Genetic Auto-prompt Learning for Pre-trained Code Intelligence Language Models
We conduct GenAP on three popular code intelligence PLMs with three canonical code intelligence tasks including defect prediction, code summarization, and code translation.
A First Step Towards Runtime Analysis of Evolutionary Neural Architecture Search
Evolutionary neural architecture search (ENAS) employs evolutionary algorithms to find high-performing neural architectures automatically, and has achieved great success.
Visual Point Cloud Forecasting enables Scalable Autonomous Driving
To resolve this, we bring up a new pre-training task termed as visual point cloud forecasting - predicting future point clouds from historical visual input.
Exploring the Robustness of Decentralized Training for Large Language Models
Decentralized training of large language models has emerged as an effective way to democratize this technology.
TL-nvSRAM-CIM: Ultra-High-Density Three-Level ReRAM-Assisted Computing-in-nvSRAM with DC-Power Free Restore and Ternary MAC Operations
Accommodating all the weights on-chip for large-scale NNs remains a great challenge for SRAM based computing-in-memory (SRAM-CIM) with limited on-chip capacity.
UniBoost: Unsupervised Unimodal Pre-training for Boosting Zero-shot Vision-Language Tasks
Our thorough studies validate that models pre-trained as such can learn rich representations of both modalities, improving their ability to understand how images and text relate to each other.
Differentiable Genetic Programming for High-dimensional Symbolic Regression
With these designs, the proposed DGP method can efficiently search for the GP trees with higher performance, thus being capable of dealing with high-dimensional SR. To demonstrate the effectiveness of DGP, we conducted various experiments against the state of the arts based on both GP and deep neural networks.
Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence
Reducing communication overhead in federated learning (FL) is challenging but crucial for large-scale distributed privacy-preserving machine learning.
Efficient Evaluation Methods for Neural Architecture Search: A Survey
In surveying each category, we further discuss the design principles and analyze the strengths and weaknesses to clarify the landscape of existing EEMs, thus making easily understanding the research trends of EEMs.
Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity
Instead, our method resorts to spatial and temporal sparsity for solving general UHR matting.
Differentiable Search of Accurate and Robust Architectures
Deep neural networks (DNNs) are found to be vulnerable to adversarial attacks, and various methods have been proposed for the defense.
DAS: Neural Architecture Search via Distinguishing Activation Score
NAS without training (WOT) score is such a metric, which estimates the final trained accuracy of the architecture through the ability to distinguish different inputs in the activation layer.
H-VFI: Hierarchical Frame Interpolation for Videos with Large Motions
The learnt deformable kernel is then utilized in convolving the input frames for predicting the interpolated frame.
Bridge the Gap Between Architecture Spaces via A Cross-Domain Predictor
To solve this issue, we propose a Cross-Domain Predictor (CDP), which is trained based on the existing NAS benchmark datasets (e. g., NAS-Bench-101), but can be used to find high-performance architectures in large-scale search spaces.
Analyzing the Expected Hitting Time of Evolutionary Computation-based Neural Architecture Search Algorithms
Evolutionary computation-based neural architecture search (ENAS) is a popular technique for automating architecture design of deep neural networks.
Continuously Controllable Facial Expression Editing in Talking Face Videos
In this paper, we propose a high-quality facial expression editing method for talking face videos, allowing the user to control the target emotion in the edited video continuously.
Architecture Augmentation for Performance Predictor Based on Graph Isomorphism
Performance predictors can greatly alleviate the prohibitive cost of NAS by directly predicting the performance of DNNs.
Human Instance Matting via Mutual Guidance and Multi-Instance Refinement
A new instance matting metric called instance matting quality (IMQ) is proposed, which addresses the absence of a unified and fair means of evaluation emphasizing both instance recognition and matting quality.
Automating Neural Architecture Design without Search
Specifically, the proposed approach is built by learning the knowledge of high-level experts in designing state-of-the-art architectures, and then the new architecture is directly generated upon the knowledge learned.
Dynamic Neural Textures: Generating Talking-Face Videos with Continuously Controllable Expressions
In this paper, we propose a method to generate talking-face videos with continuously controllable expressions in real-time.
A Unified Query-based Paradigm for Point Cloud Understanding
This is achieved by introducing an intermediate representation, i. e., Q-representation, in the querying stage to serve as a bridge between the embedding stage and task heads.
Ranked #8 on
Semantic Segmentation
on S3DIS
Evolving Deep Neural Networks for Collaborative Filtering
As a consequence, it requires the designers to develop expertise in both CF and DNNs, which limits the application of deep learning methods in CF and the accuracy of recommended results.
BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search
The paper conducts efficient comparison experiments on eight ENAS algorithms with high GPU utilization on this platform.
Homogeneous Architecture Augmentation for Neural Predictor
Specifically, a homogeneous architecture augmentation algorithm is proposed in HAAP to generate sufficient training data taking the use of homogeneous representation.
Autoregressive Stylized Motion Synthesis With Generative Flow
Motion style transfer is an important problem in many computer graphics and computer vision applications, including human animation, games, and robotics.
Heart-Darts: Classification of Heartbeats Using Differentiable Architecture Search
In this paper, we propose a novel approach, Heart-Darts, to efficiently classify the ECG signals by automatically designing the CNN model with the differentiable architecture search (i. e., Darts, a cell-based neural architecture search method).
Deep Video Matting via Spatio-Temporal Alignment and Aggregation
Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack of large-scale video matting datasets.
Semantic Image Matting
Specifically, we consider and learn 20 classes of matting patterns, and propose to extend the conventional trimap to semantic trimap.
PSO-PS: Parameter Synchronization with Particle Swarm Optimization for Distributed Training of Deep Neural Networks
Synchronous methods are widely used in distributed training the Deep Neural Networks (DNNs).
A Novel Training Protocol for Performance Predictors of Evolutionary Neural Architecture Search Algorithms
Performance predictors are a type of regression models which can assist to accomplish the search, while without exerting much computational resource.
A Survey on Evolutionary Neural Architecture Search
Deep Neural Networks (DNNs) have achieved great success in many applications.
Evolving Deep Convolutional Neural Networks for Hyperspectral Image Denoising
Hyperspectral images (HSIs) are susceptible to various noise factors leading to the loss of information, and the noise restricts the subsequent HSIs object detection and classification tasks.
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision
GSNet utilizes a unique four-way feature extraction and fusion scheme and directly regresses 6DoF poses and shapes in a single forward pass.
Ranked #1 on
Autonomous Driving
on ApolloCar3D
DBS: Dynamic Batch Size For Distributed Deep Neural Network Training
Specifically, the performance of each worker is evaluatedfirst based on the fact in the previous epoch, and then the batch size and datasetpartition are dynamically adjusted in consideration of the current performanceof the worker, thereby improving the utilization of the cluster.
3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Face Photos
The most challenging issue for our system is that the source domain of face photos (characterized by normal 2D faces) is significantly different from the target domain of 3D caricatures (characterized by 3D exaggerated face shapes and textures).
3DSSD: Point-based 3D Single Stage Object Detector
Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well, with inference speed more than 25 FPS, 2x faster than former state-of-the-art point-based methods.
ArcText: A Unified Text Approach to Describing Convolutional Neural Network Architectures
Data mining on existing CNN can discover useful patterns and fundamental sub-comments from their architectures, providing researchers with strong prior knowledge to design proper CNN architectures when they have no expertise in CNNs.
STD: Sparse-to-Dense 3D Object Detector for Point Cloud
We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD).
Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classification
In recent years, convolutional neural networks (CNNs) have become deeper in order to achieve better classification accuracy in image classification.
A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks
Three major contributions of this work are: Firstly, a new encoding strategy is proposed to encode a CNN, where the architecture and the shortcut connections are encoded separately; Secondly, a hybrid two-level EC method, which combines particle swarm optimisation and genetic algorithms, is developed to search for the optimal CNNs; Lastly, an adjustable learning rate is introduced for the fitness evaluations, which provides a better learning rate for the training process given a fixed number of epochs.
IPOD: Intensive Point-based Object Detector for Point Cloud
We present a novel 3D object detection framework, named IPOD, based on raw point cloud.
Ranked #1 on
3D Object Detection
on KITTI Pedestrians Easy
Automatically Evolving CNN Architectures Based on Blocks
The proposed algorithm is evaluated on CIFAR10 and CIFAR100 against 18 state-of-the-art peer competitors.
A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification
In this paper, a new hybrid differential evolution (DE) algorithm with a newly added crossover operator is proposed to evolve the architectures of CNNs of any lengths, which is named DECNN.
Automatically designing CNN architectures using genetic algorithm for image classification
Convolutional Neural Networks (CNNs) have gained a remarkable success on many image classification tasks in recent years.
Evolving Deep Convolutional Neural Networks by Variable-length Particle Swarm Optimization for Image Classification
Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design.
IGD Indicator-based Evolutionary Algorithm for Many-objective Optimization Problems
Inverted Generational Distance (IGD) has been widely considered as a reliable performance indicator to concurrently quantify the convergence and diversity of multi- and many-objective evolutionary algorithms.
Improved Regularity Model-based EDA for Many-objective Optimization
Finally, by assigning the Pareto-optimal solutions to the uniformly distributed reference vectors, a set of solutions with excellent diversity and convergence is obtained.
Evolving Unsupervised Deep Neural Networks for Learning Meaningful Representations
Specifically, error classification rate on MNIST with $1. 15\%$ is reached by the proposed algorithm consistently, which is a very promising result against state-of-the-art unsupervised DL algorithms.
A Particle Swarm Optimization-based Flexible Convolutional Auto-Encoder for Image Classification
Convolutional auto-encoders have shown their remarkable performance in stacking to deep convolutional neural networks for classifying image data during past several years.
Evolving Deep Convolutional Neural Networks for Image Classification
Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights.
