Search Results for author:
Found 72 papers, 26 papers with code
Convolutional Neural Network Transformer (CNNT) for Fluorescence Microscopy image Denoising with Improved Generalization and Fast Adaptation
Previous methods are based on convolutional neural networks (CNNs) which generally require more time-consuming training of separate models for each new imaging experiment, impairing the applicability and generalization.
Imaging transformer for MRI denoising with the SNR unit training: enabling generalization across field-strengths, imaging contrasts, and anatomy
The ability to recover MRI signal from noise is key to achieve fast acquisition, accurate quantification, and high image quality.
Inline AI: Open-source Deep Learning Inference for Cardiac MR
The model was loaded and inference on incoming images were performed while the data acquisition was ongoing, and results were sent back to scanner.
TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models
KEPLMs are pre-trained models that utilize external knowledge to enhance language understanding.
Zippo: Zipping Color and Transparency Distributions into a Single Diffusion Model
Beyond the superiority of the text-to-image diffusion model in generating high-quality images, recent studies have attempted to uncover its potential for adapting the learned semantic knowledge to visual perception tasks.
Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts
In this paper, we discover that there exist cases with distribution shifts unobservable in the time domain while observable in the spectral domain, and propose to study distribution shifts on dynamic graphs in the spectral domain for the first time.
Understanding the Weakness of Large Language Model Agents within a Complex Android Environment
These challenges motivate AndroidArena, an environment and benchmark designed to evaluate LLM agents on a modern operating system.
Text Image Inpainting via Global Structure-Guided Diffusion Models
Leveraging the global structure of the text as a prior, the proposed GSDM develops an efficient diffusion model to recover clean texts.
One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications
The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors.
PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolution
Scene text image super-resolution (STISR) aims at simultaneously increasing the resolution and readability of low-resolution scene text images, thus boosting the performance of the downstream recognition task.
DoubleAUG: Single-domain Generalized Object Detector in Urban via Color Perturbation and Dual-style Memory
In this paper, we aim to solve the single-domain generalizable object detection task in urban scenarios, meaning that a model trained on images from one weather condition should be able to perform well on images from any other weather conditions.
Model Inversion Attack via Dynamic Memory Learning
Model Inversion (MI) attacks aim to recover the private training data from the target model, which has raised security concerns about the deployment of DNNs in practice.
Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging
In this paper, we conduct a comprehensive study of over 10 fast adversarial training methods in terms of adversarial robustness and training costs.
Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training
Developing a practically-robust automatic speech recognition (ASR) is challenging since the model should not only maintain the original performance on clean samples, but also achieve consistent efficacy under small volume perturbations and large domain shifts.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts
To give a more comprehensive robustness assessment, we introduce COCO-O(ut-of-distribution), a test dataset based on COCO with 6 types of natural distribution shifts.
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework
In our experiments, we conduct a robustness evaluation of RoBERTa models to demonstrate the effectiveness of our evaluation framework, and further show the rationality of each component in the framework.
Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning
Large language models (LLMs) have recently shown great potential for in-context learning, where LLMs learn a new task simply by conditioning on a few input-label pairs (prompts).
Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection
In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD).
FairRec: Fairness Testing for Deep Recommender Systems
Given the testing report, by adopting a simple re-ranking mitigation strategy on these identified disadvantaged groups, we show that the fairness of DRSs can be significantly improved.
ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing
We also evaluate some robust models including both adversarially trained models and other robust trained models and find that some models show worse robustness against attribute changes than vanilla models.
PIAT: Parameter Interpolation based Adversarial Training for Image Classification
Besides, we suggest to use the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the clean and adversarial examples.
To Make Yourself Invisible with Adversarial Semantic Contours
In this paper, we propose Adversarial Semantic Contour (ASC), an MAP estimate of a Bayesian formulation of sparse attack with a deceived prior of object contour.
Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain
To address this issue, we proposed a novel method of Augmenting data with Adversarial examples via a Wavelet module (AdvWavAug), an on-manifold adversarial data augmentation technique that is simple to implement.
A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking
In our benchmark, we evaluate the robustness of 55 typical deep learning models on ImageNet with diverse architectures (e. g., CNNs, Transformers) and learning algorithms (e. g., normal supervised training, pre-training, adversarial training) under numerous adversarial attacks and out-of-distribution (OOD) datasets.
Improving Scene Text Image Super-resolution via Dual Prior Modulation Network
Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images, and the resulting images will significantly affect the performance of downstream tasks.
Open-Vocabulary Object Detection With an Open Corpus
For the classification task, we introduce an open corpus classifier by reconstructing original classifier with similar words in text space.
Rethinking Out-of-Distribution Detection From a Human-Centric Perspective
Additionally, our experiments demonstrate that model selection is non-trivial for OOD detection and should be considered as an integral of the proposed method, which differs from the claim in existing works that proposed methods are universal across different models.
Context-Aware Robust Fine-Tuning
Contrastive Language-Image Pre-trained (CLIP) models have zero-shot ability of classifying an image belonging to "[CLASS]" by using similarity between the image and the prompt sentence "a [CONTEXT] of [CLASS]".
Ranked #1 on
Domain Generalization
on VLCS
Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models
Conditioned diffusion models have demonstrated state-of-the-art text-to-image synthesis capacity.
Ranked #1 on
Story Visualization
on Pororo
RoChBert: Towards Robust BERT Fine-tuning for Chinese
Despite of the superb performance on a wide range of tasks, pre-trained language models (e. g., BERT) have been proved vulnerable to adversarial texts.
Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation
Capturing emotions within a conversation plays an essential role in modern dialogue systems.
Ranked #3 on
Emotion Recognition in Conversation
on EmoryNLP
Boosting Out-of-distribution Detection with Typical Features
Out-of-distribution (OOD) detection is a critical task for ensuring the reliability and safety of deep neural networks in real-world scenarios.
Enhance the Visual Representation via Discrete Adversarial Training
For borrowing the advantage from NLP-style AT, we propose Discrete Adversarial Training (DAT).
Ranked #1 on
Domain Generalization
on Stylized-ImageNet
Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition
Finally, we propose a weakly supervised object localization-based approach to extract multi-scale local features, to form a multi-view pipeline.
D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention
DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing.
Multi-View Fusion Transformer for Sensor-Based Human Activity Recognition
In this paper, to extract a better feature for advancing the performance, we propose a novel method, namely multi-view fusion transformer (MVFT) along with a novel attention mechanism.
Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains
Notably, our methods outperform state-of-the-art approaches by up to 7. 71\% (towards coarse-grained domains) and 25. 91\% (towards fine-grained domains) on average.
An Automated Question-Answering Framework Based on Evolution Algorithm
Our framework is based on an innovative evolution algorithm, which is stable and suitable for multiple dataset scenario.
Unrestricted Adversarial Attacks on ImageNet Competition
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
Adversarial Attacks on ML Defense Models Competition
Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years.
DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework
In multimodal tasks, we find that the importance of text and image modal information is different for different input cases, and for this motivation, we propose a high-performance and highly general Dual-Router Dynamic Framework (DRDF), consisting of Dual-Router, MWF-Layer, experts and expert fusion unit.
RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition
We propose the recurrent attention multi-scale transformer (RAMS-Trans), which uses the transformer's self-attention to recursively learn discriminative region attention in a multi-scale manner.
Ranked #7 on
Fine-Grained Image Classification
on Stanford Dogs
Fine-Grained Image Classification
Fine-Grained Image Recognition
Towards Robust Vision Transformer
By using and combining robust components as building blocks of ViTs, we propose Robust Vision Transformer (RVT), which is a new vision transformer and has superior performance with strong robustness.
Ranked #24 on
Domain Generalization
on ImageNet-C
QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval
Comprehensive experiments show that the proposed attack achieves a high attack success rate with few queries against the image retrieval systems under the black-box setting.
Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain
The remarkable success in face forgery techniques has received considerable attention in computer vision due to security concerns.
Enhancing Model Robustness By Incorporating Adversarial Knowledge Into Semantic Representation
Extensive experiments on two real-world tasks show that AdvGraph exhibits better performance compared with previous work: (i) effective - it significantly strengthens the model robustness even under the adaptive attacks setting without negative impact on model performance over legitimate input; (ii) generic - its key component, i. e., the representation of connotative adversarial knowledge is task-agnostic, which can be reused in any Chinese-based NLP models without retraining; and (iii) efficient - it is a light-weight defense with sub-linear computational complexity, which can guarantee the efficiency required in practical scenarios.
Cut out the annotator, keep the cutout: better segmentation with weak supervision
We propose a framework that fuses limited label learning and weak supervision for segmentation tasks, enabling users to train high-performing segmentation CNNs with very few hand-labeled training points.
The Open Brands Dataset: Unified brand detection and recognition at scale
To the best of our knowledge, it is the largest dataset for brand detection and recognition with rich annotations.
Composite Adversarial Attacks
Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness.
Landmark detection in Cardiac Magnetic Resonance Imaging Using A Convolutional Neural Network
Conclusions: This study developed, validated and deployed a CNN solution for robust landmark detection in both long and short-axis CMR images for cine, LGE and T1 mapping sequences, with the accuracy comparable to the inter-operator variation.
Sharp Multiple Instance Learning for DeepFake Video Detection
A sharp MIL (S-MIL) is proposed which builds direct mapping from instance embeddings to bag prediction, rather than from instance embeddings to instance prediction and then to bag prediction in traditional MIL.
MIRA: Leveraging Multi-Intention Co-click Information in Web-scale Document Retrieval using Deep Neural Networks
The common framework is to train two encoding models based on neural embedding which learn the distributed representations of queries and documents separately and match them in the latent semantic space.
SpanMlt: A Span-based Multi-Task Learning Framework for Pair-wise Aspect and Opinion Terms Extraction
To this end, this paper proposes an end-to-end method to solve the task of Pair-wise Aspect and Opinion Terms Extraction (PAOTE).
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
GAP++: Learning to generate target-conditioned adversarial examples
Different from previous single-target attack models, our model can conduct target-conditioned attacks by learning the relations of attack target and the semantics in image.
Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling
Localizing thoracic diseases on chest X-ray plays a critical role in clinical practices such as diagnosis and treatment planning.
Towards Face Encryption by Generating Adversarial Identity Masks
As billions of personal data being shared through social media and network, the data privacy and security have drawn an increasing attention.
Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network
This paper strives to learn fine-grained fashion similarity.
Deeper Insights into Weight Sharing in Neural Architecture Search
With the success of deep neural networks, Neural Architecture Search (NAS) as a way of automatic model design has attracted wide attention.
Semantic Regularization: Improve Few-shot Image Classification by Reducing Meta Shift
This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their own support set.
Self-supervised Adversarial Training
Recent work has demonstrated that neural networks are vulnerable to adversarial examples.
Learning To Characterize Adversarial Subspaces
To detect these adversarial examples, previous methods use artificially designed metrics to characterize the properties of \textit{adversarial subspaces} where adversarial examples lie.
AdvKnn: Adversarial Attacks On K-Nearest Neighbor Classifiers With Approximate Gradients
Deep neural networks have been shown to be vulnerable to adversarial examples---maliciously crafted examples that can trigger the target model to misbehave by adding imperceptible perturbations.
Self-Supervised Learning For Few-Shot Image Classification
In this paper, we proposed to train a more generalized embedding network with self-supervised learning (SSL) which can provide robust representation for downstream tasks by learning from the data itself.
Ranked #4 on
Few-Shot Image Classification
on Mini-ImageNet - 1-Shot Learning
(using extra training data)
Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
This solution was integrated on the MR scanner, enabling 'one-click' analysis and reporting of myocardial blood flow.
Automated Detection of Left Ventricle in Arterial Input Function Images for Inline Perfusion Mapping using Deep Learning: A study of 15,000 Patients
The 3CS model successfully detect LV for 99. 98% of all test cases (1 failed out of 5, 721 cases).
DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition
Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem.
Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network
However, the video length is usually long, and there are hierarchical relationships between frames across events in the video, the performance of RNN based models are decreased.
Ranked #1 on
Video Classification
on YouTube-8M
Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks
The task of Language-Based Image Editing (LBIE) aims at generating a target image by editing the source image based on the given language description.
Deep Features Analysis with Attention Networks
Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc.
Ranking Responses Oriented to Conversational Relevance in Chat-bots
For automatic chatting systems, it is indeed a great challenge to reply the given query considering the conversation history, rather than based on the query only.
Logistic Boosting Regression for Label Distribution Learning
In order to learn this general model family, this paper uses a method called Logistic Boosting Regression (LogitBoost) which can be seen as an additive weighted function regression from the statistical viewpoint.
LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks
In this paper, we introduce "LOGO-Net", a large-scale logo image database for logo detection and brand recognition from real-world product images.
