Search Results for author:
Found 62 papers, 38 papers with code
基于义原表示学习的词向量表示方法(Word Representation based on Sememe Representation Learning)
“本文利用知网(HowNet)中的知识, 并将Word2vec模型的结构和思想迁移至义原表示学习过程中, 提出了一个基于义原表示学习的词向量表示方法。首先, 本文利用OpenHowNet获取义原知识库中的所有义原、所有中文词汇以及所有中文词汇和其对应的义原集合, 作为实验的数据集。然后, 基于Skip-gram模型, 训练义原表示学习模型, 进而获得词向量。最后, 通过词相似度任务、词义消歧任务、词汇类比和观察最近邻义原, 来评价本文提出的方法获取的词向量的效果。通过和基线模型比较, 发现本文提出的方法既高效又准确, 不依赖大规模语料也不需要复杂的网络结构和繁多的参数, 也能提升各种自然语言处理任务的准确率。”
DifFRelight: Diffusion-Based Facial Performance Relighting
We present a novel framework for free-viewpoint facial performance relighting using diffusion-based image-to-image translation.
T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
To address the risks of encountering inappropriate or harmful content, researchers managed to incorporate several harmful contents datasets with machine learning methods to detect harmful concepts.
Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders
Despite being prevalent in the general field of Natural Language Processing (NLP), pre-trained language models inherently carry privacy and copyright concerns due to their nature of training on large-scale web-scraped data.
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs.
Membership Inference Attack Against Masked Image Modeling
Masked Image Modeling (MIM) has achieved significant success in the realm of self-supervised learning (SSL) for visual recognition.
Jailbreaking Text-to-Image Models with LLM-Based Agents
Atlas consists of two agents, namely the mutation agent and the selection agent, each comprising four key modules: a vision-language model (VLM) or LLM brain, planning, memory, and tool usage.
JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
In this study, we investigate the vulnerability of image watermarks to diffusion-model-based image editing, a challenge exacerbated by the computational cost of accessing gradient information and the closed-source nature of many diffusion models.
Detecting Adversarial Data via Perturbation Forgery
By learning to distinguish this open covering from the distribution of natural data, we can develop a detector with strong generalization capabilities against all types of adversarial attacks.
FASTTRACK: Fast and Accurate Fact Tracing for LLMs
Existing approaches to fact tracing rely on assessing the similarity between each training sample and the query along a certain dimension, such as lexical similarity, gradient, or embedding space.
HaVTR: Improving Video-Text Retrieval Through Augmentation Using Large Foundation Models
While recent progress in video-text retrieval has been driven by the exploration of powerful model architectures and training strategies, the representation learning ability of video-text retrieval models is still limited due to low-quality and scarce training data annotations.
Reference-Based 3D-Aware Image Editing with Triplanes
Generative Adversarial Networks (GANs) have emerged as powerful tools for high-quality image generation and real image editing by manipulating their latent spaces.
RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
The innovative use of constrained optimization and a fusion-based guardrail approach represents a significant step forward in developing more secure and reliable LLMs, setting a new standard for content moderation frameworks in the face of evolving digital threats.
C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models
Specifically, we provide conformal risk analysis for RAG models and certify an upper confidence bound of generation risks, which we refer to as conformal generation risk.
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
We show that Shadowcast are highly effective in achieving attacker's intentions using as few as 50 poison samples.
Continual Adversarial Defense
In response to the rapidly evolving nature of adversarial attacks against visual classifiers on a monthly basis, numerous defenses have been proposed to generalize against as many known attacks as possible.
X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning
To enable this framework, we devise a scalable pipeline that automatically generates high-quality, instruction-tuning datasets from readily available captioning data across different modalities, and contribute 24K QA data for audio and 250K QA data for 3D.
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
Several membership inference attacks (MIAs) have been proposed to exhibit the privacy vulnerability of generative models by classifying a query image as a training dataset member or nonmember.
AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors
Moreover, results demonstrate that (1) the deepfake detection accuracy can be significantly and consistently improved (from 71. 06% to 92. 11%, in average accuracy over unseen domains) using pretrained vision-language models with prompt tuning; (2) our superior performance is at less cost of training data and trainable parameters, resulting in an effective and efficient solution for deepfake detection.
Generated Graph Detection
Graph generative models become increasingly effective for data distribution approximation and data augmentation.
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages.
UMDFood: Vision-language models boost food composition compilation
Nutrition information is crucial in precision nutrition and the food industry.
ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
It achieves a new SOTA of 50. 6% (top-1) on Objaverse-LVIS and 84. 7% (top-1) on ModelNet40 in zero-shot classification.
Ranked #9 on
3D Point Cloud Classification
on ScanObjectNN
(using extra training data)
Detecting Adversarial Faces Using Only Real Face Self-Perturbations
Adversarial attacks aim to disturb the functionality of a target system by adding specific noise to the input samples, bringing potential threats to security and robustness when applied to facial recognition systems.
RoSteALS: Robust Steganography using Autoencoder Latent Space
Data hiding such as steganography and invisible watermarking has important applications in copyright protection, privacy-preserved communication and content provenance.
Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations
In summary, an OV method learns task-specific information using strong supervision from base annotations and novel category information using weak supervision from image-captions pairs.
GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
Empirical results show that GlueNet can be trained efficiently and enables various capabilities beyond previous state-of-the-art models: 1) multilingual language models such as XLM-Roberta can be aligned with existing T2I models, allowing for the generation of high-quality images from captions beyond English; 2) GlueNet can align multi-modal encoders such as AudioCLIP with the Stable Diffusion model, enabling sound-to-image generation; 3) it can also upgrade the current text encoder of the latent diffusion model for challenging case generation.
HIVE: Harnessing Human Feedback for Instructional Visual Editing
Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences.
Learning Prototype Classifiers for Long-Tailed Recognition
In this work, we show that learning prototype classifiers addresses the biased softmax problem in LTR.
Ranked #8 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
Hierarchical Point Attention for Indoor 3D Object Detection
By plugging our proposed modules into the state-of-the-art transformer-based 3D detectors, we improve the previous best results on both benchmarks, with more significant improvements on smaller objects.
LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
Graphic layout designs play an essential role in visual communication.
AugTriever: Unsupervised Dense Retrieval by Scalable Data Augmentation
In this study, we aim to develop unsupervised methods for improving dense retrieval models.
DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models
To tackle this problem, we pioneer a systematic study on the detection and attribution of fake images generated by text-to-image generation models.
SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models
In this paper, we contribute the first systematic approach that simulates various OOD scenarios along different dimensions of source code data properties and study the fine-tuned model behaviors in such scenarios.
Membership Inference Attacks Against Text-to-image Generation Models
The empirical results show that all of the proposed attacks can achieve significant performance, in some cases even close to an accuracy of 1, and thus the corresponding risk is much more severe than that shown by existing membership inference attacks.
UnGANable: Defending Against GAN-based Face Manipulation
Extensive experiments on four popular GAN models trained on two benchmark face datasets show that UnGANable achieves remarkable effectiveness and utility performance, and outperforms multiple baseline methods.
Auditing Membership Leakages of Multi-Exit Networks
Furthermore, we propose a hybrid attack that exploits the exit information to improve the performance of existing attacks.
Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand
We claim that the performance of inpainting algorithms can be better judged by the generated structures and textures.
RelaxLoss: Defending Membership Inference Attacks without Losing Utility
As a long-term threat to the privacy of training data, membership inference attacks (MIAs) emerge ubiquitously in machine learning models.
RepMix: Representation Mixing for Robust Attribution of Synthesized Images
Uniquely, we present a solution to this task capable of 1) matching images invariant to their semantic content; 2) robust to benign transformations (changes in quality, resolution, shape, etc.)
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images.
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
The rapid advances in deep generative models over the past years have led to highly {realistic media, known as deepfakes,} that are commonly indistinguishable from real to human eyes.
Dual Contrastive Loss and Attention for GANs
Lastly, we study different attention architectures in the discriminator, and propose a reference attention mechanism.
KNN, An Underestimated Model for Regional Rainfall Forecasting
Regional rainfall forecasting is an important issue in hydrology and meteorology.
Deep Video Inpainting Detection
This paper studies video inpainting detection, which localizes an inpainted region in a video both spatially and temporally.
Responsible Disclosure of Generative Models Using Scalable Fingerprinting
Over the past years, deep generative models have achieved a new level of performance.
Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
While Generative Adversarial Networks (GANs) show increasing performance and the level of realism is becoming indistinguishable from natural images, this also comes with high demands on data and computation.
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
Thus, we seek a proactive and sustainable solution on deepfake detection, that is agnostic to the evolution of generative models, by introducing artificial fingerprints into the models.
6 nm super-resolution optical transmission and scattering spectroscopic imaging of carbon nanotubes using a nanometer-scale white light source
Optical hyperspectral imaging based on absorption and scattering of photons at the visible and adjacent frequencies denotes one of the most informative and inclusive characterization methods in material research.
Super-Resolution
Optics
Materials Science
Corpus Development for Studying Online Disinformation Campaign: A Narrative + Stance Approach
Instead, we label the narrative and stance of tweets and YouTube comments about White Helmets.
Inclusive GAN: Improving Data and Minority Coverage in Generative Models
Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images.
Long-Tailed Recognition Using Class-Balanced Experts
Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets.
Ranked #21 on
Long-tail Learning
on Places-LT
AI-Powered GUI Attack and Its Defensive Methods
Since the first Graphical User Interface (GUI) prototype was invented in the 1970s, GUI systems have been deployed into various personal computer systems and server platforms.
Macrocosm: Social Media Persona Linking for Open Source Intelligence Applications
Online Social Networks (OSNs) provide a wealth of intelligence to analysts in assisting tasks such as tracking cyber-attacks, human trafficking activities, and misinformation campaigns.
GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
In addition, we propose the first generic attack model that can be instantiated in a large range of settings and is applicable to various kinds of deep generative models.
Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
This paper addresses the problem of interpolating visual textures.
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
Our experiments show that (1) GANs carry distinct model fingerprints and leave stable fingerprints in their generated images, which support image attribution; (2) even minor differences in GAN training can result in different fingerprints, which enables fine-grained model authentication; (3) fingerprints persist across different image frequencies and patches and are not biased by GAN artifacts; (4) fingerprint finetuning is effective in immunizing against five types of adversarial image perturbations; and (5) comparisons also show our learned fingerprints consistently outperform several baselines in a variety of setups.
Three-Stream Convolutional Networks for Video-based Person Re-Identification
This paper aims to develop a new architecture that can make full use of the feature maps of convolutional networks.
Reconstruction of Hidden Representation for Robust Feature Extraction
We believe that minimizing the reconstruction error of the hidden representation is more robust than minimizing the Frobenius norm of the Jacobian matrix of the hidden representation.
Learning to Detect Multiple Photographic Defects
Our new dataset enables us to formulate the problem as a multi-task learning problem and train a multi-column deep convolutional neural network (CNN) to simultaneously predict the severity of all the defects.
