Search Results for author:
Found 43 papers, 10 papers with code
AIM 2024 Challenge on Video Saliency Prediction: Methods and Results
The goal of the participants was to develop a method for predicting accurate saliency maps for the provided set of video sequences.
MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning
Diffusion models have emerged as frontrunners in text-to-image generation, however, their fixed image resolution during training often leads to challenges in high-resolution image generation, such as semantic deviations and object replication.
Active Testing of Large Language Model via Multi-Stage Sampling
Given that LLMs' diverse task-handling abilities stem from large volumes of training data, a comprehensive evaluation also necessitates abundant, well-annotated, and representative test data to assess LLM performance across various downstream tasks.
HPC: Hierarchical Progressive Coding Framework for Volumetric Video
Volumetric video based on Neural Radiance Field (NeRF) holds vast potential for various 3D applications, but its substantial data volume poses significant challenges for compression and transmission.
SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation
In this context, we focus on robust video polyp segmentation by enhancing the adjacent feature consistency and rebuilding the reliable polyp representation.
Ranked #3 on
Video Polyp Segmentation
on SUN-SEG-Easy (Unseen)
JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compression
Neural Radiance Field (NeRF) excels in photo-realistically static scenes, inspiring numerous efforts to facilitate volumetric videos.
DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition
The denoised text classes help OVAR models classify visual samples more accurately; in return, classified visual samples help better denoising.
Enhancing Fault Detection for Large Language Models via Mutation-Based Confidence Smoothing
Large language models (LLMs) achieved great success in multiple application domains and attracted huge attention from different research communities recently.
MonoBox: Tightness-free Box-supervised Polyp Segmentation using Monotonicity Constraint
We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption.
Importance Guided Data Augmentation for Neural-Based Code Understanding
In this paper, we introduce a general data augmentation framework, GenCode, to enhance the training of code understanding models.
Efficient Dynamic-NeRF Based Volumetric Video Coding with Rate Distortion Optimization
Volumetric videos, benefiting from immersive 3D realism and interactivity, hold vast potential for various applications, while the tremendous data volume poses significant challenges for compression.
VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams
In this paper, we introduce VideoRF, the first approach to enable real-time streaming and rendering of dynamic radiance fields on mobile platforms.
IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors
In response, we propose two innovative learning fashions, Improved Box-dice (IBox) and Contrastive Latent-Anchors (CLA), and combine them to train a robust box-supervised model IBoxCLA.
Evaluating the Robustness of Test Selection Methods for Deep Neural Networks
Testing deep learning-based systems is crucial but challenging due to the required time and labor for labeling collected raw data.
CodeLens: An Interactive Tool for Visualizing Code Representations
Representing source code in a generic input format is crucial to automate software engineering tasks, e. g., applying machine learning algorithms to extract information.
LMs: Understanding Code Syntax and Semantics for Code Analysis
We break down the abilities needed for artificial intelligence~(AI) models to address SE tasks related to code analysis into three categories: 1) syntax understanding, 2) static behavior understanding, and 3) dynamic behavior understanding.
A Black-Box Attack on Code Models via Representation Nearest Neighbor Search
Furthermore, the perturbation of adversarial examples introduced by RNNS is smaller compared to the baselines in terms of the number of replaced variables and the change in variable length.
Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos
The success of the Neural Radiance Fields (NeRFs) for modeling and free-view rendering static objects has inspired numerous attempts on dynamic scenes.
Boosting Source Code Learning with Data Augmentation: An Empirical Study
The next era of program understanding is being propelled by the use of machine learning to solve software problems.
NEPHELE: A Neural Platform for Highly Realistic Cloud Radiance Rendering
Using such a cloud platform compatible with neural rendering, we further showcase the capabilities of our cloud radiance rendering through a series of applications, ranging from cloud VR/AR rendering.
Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities
These structures are fundamental to understanding code.
Dynamic Feature Pruning and Consolidation for Occluded Person Re-Identification
The framework mainly consists of a sparse encoder, a multi-view feature mathcing module, and a feature consolidation decoder.
On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processing
Graph neural network (GNN)-based graph learning has been popular in natural language and programming language processing, particularly in text and source code classification.
MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentation
Data augmentation has been a popular approach to supplement training data in domains such as computer vision and NLP.
Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation
Recent studies show that test selection for DNN is a promising direction that tackles this issue by selecting minimal representative data to label and using these data to assess the model.
Preprocessing Enhanced Image Compression for Machine Vision
Specifically, we propose a neural preprocessing module before the encoder to maintain the useful semantic information for the downstream tasks and suppress the irrelevant information for bitrate saving.
CodeS: Towards Code Model Generalization Under Distribution Shift
Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation.
LaF: Labeling-Free Model Selection for Automated Deep Neural Network Reusing
Applying deep learning to science is a new trend in recent years which leads DL engineering to become an important problem.
Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment
The results reveal that 1) data with distribution shifts happen more disagreements than without.
WCL-BBCD: A Contrastive Learning and Knowledge Graph Approach to Named Entity Recognition
The model first trains the sentence pairs in the text, calculate similarity between sentence pairs, and fine-tunes BERT used for the named entity recognition task according to the similarity, so as to alleviate word ambiguity.
GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges
However, although numerous algorithms are proposed based on fundus images or OCT volumes in computer-aided diagnosis, there are still few methods leveraging both of the modalities for the glaucoma assessment.
Learning Based Multi-Modality Image and Video Compression
Specifically, given the image in the reference modality (e. g., the infrared image), we use the channel-wise alignment module to produce the aligned features based on the affine transform.
Robust Active Learning: Sample-Efficient Training of Robust Deep Learning Models
Our acquisition function -- named density-based robust sampling with entropy (DRE) -- outperforms the other acquisition functions (including random) in terms of robustness by up to 24. 40\% (3. 84\% than random particularly), while remaining competitive on accuracy.
MUTEN: Boosting Gradient-Based Adversarial Attacks via Mutant-Based Ensembles
In this paper, we propose MUTEN, a low-cost method to improve the success rate of well-known attacks against gradient-masking models.
Understanding Deep MIMO Detection
We demonstrate that data-driven DL detector asymptotically approaches to the maximum a posterior (MAP) detector in various scenarios but requires enough training samples to converge in time-varying channels.
TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation
Medical image segmentation - the prerequisite of numerous clinical needs - has been significantly prospered by recent advances in convolutional neural networks (CNNs).
Ranked #15 on
Medical Image Segmentation
on ETIS-LARIBPOLYPDB
LGNN: A Context-aware Line Segment Detector
We present a novel real-time line segment detection scheme called Line Graph Neural Network (LGNN).
Towards Characterizing Adversarial Defects of Deep Learning Software from the Lens of Uncertainty
Based on this, we propose an automated testing technique to generate multiple types of uncommon AEs and BEs that are largely missed by existing techniques.
An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms
However, the differences in architecture designs and implementations of existing frameworks and platforms bring new challenges for DL software development and deployment.
An Orchestrated Empirical Study on Deep Learning Frameworks and Platforms
Up to the present, it still lacks a comprehensive study on how current diverse DL frameworks and platforms influence the DL software development process.
Nearly-tight bounds on linear regions of piecewise linear neural networks
The developments of deep neural networks (DNN) in recent years have ushered a brand new era of artificial intelligence.
Secure Deep Learning Engineering: A Software Quality Assurance Perspective
Over the past decades, deep learning (DL) systems have achieved tremendous success and gained great popularity in various applications, such as intelligent machines, image processing, speech processing, and medical diagnostics.
Enhancing HEVC Compressed Videos with a Partition-masked Convolutional Neural Network
In this paper, we propose a partition-masked Convolution Neural Network (CNN) to achieve compressed-video enhancement for the state-of-the-art coding standard, High Efficiency Video Coding (HECV).
Multimedia
