Search Results for author:
Found 37 papers, 11 papers with code
Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition
Long-tailed image recognition is a computer vision problem considering a real-world class distribution rather than an artificial uniform.
Conflict-Aware Adversarial Training
Adversarial training is the most effective method to obtain adversarial robustness for deep neural networks by directly involving adversarial samples in the training procedure.
Creative and Context-Aware Translation of East Asian Idioms with GPT-4
As a type of figurative language, an East Asian idiom condenses rich cultural background into only a few characters.
Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling
Our theoretical analysis aligns with empirical observations of the generated images in the Chain of Diffusion.
NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions
We present NutriBench, the first publicly available natural language meal description nutrition benchmark.
Automated Adversarial Discovery for Safety Classifiers
We formalize the task of automated adversarial discovery for safety classifiers - to find new attacks along previously unseen harm dimensions that expose new weaknesses in the classifier.
A Minimalist Prompt for Zero-Shot Policy Learning
Transformer-based methods have exhibited significant generalization ability when prompted with target-domain demonstrations or example solutions during inference.
Fast Decision Boundary based Out-of-Distribution Detector
By regularizing the distances to decision boundaries based on feature deviation from the mean, we develop a hyperparameter-free, auxiliary model-free OOD detector.
Computational Efficiency
Out of Distribution (OOD) Detection
Initialization Matters for Adversarial Transfer Learning
Based on this, we propose Robust Linear Initialization (RoLI) for adversarial finetuning, which initializes the linear head with the weights obtained by adversarial linear probing to maximally inherit the robustness from pretraining.
Detecting Out-of-Distribution Through the Lens of Neural Collapse
By analyzing this trend, we discover that features of in-distribution (ID) samples cluster closer to the weight vectors compared to features of OOD samples.
Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective
State-of-the-art techniques for enhancing robustness of deep networks mostly rely on empirical risk minimization with suitable data augmentation.
Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning
As large language models (LLMs) are widely adopted, new safety issues and policies emerge, to which existing safety classifiers do not generalize well.
A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models
This paper aims to provide a comprehensive survey of cutting-edge research in prompt engineering on three types of vision-language models: multimodal-to-text generation models (e. g. Flamingo), image-text matching models (e. g.
Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting
Although offering improved data privacy protection, domain-specific small language models (SLMs) often underperform LLMs, emphasizing the need for methods that reduce this performance gap while alleviating privacy concerns.
Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals
We demonstrate that with a small amount of human-annotated counterfactual data (10%), we can generate a counterfactual augmentation dataset with learned labels, that provides an 18-20% improvement in robustness and a 14-21% reduction in errors on 6 out-of-domain datasets, comparable to that of a fully human-annotated counterfactual dataset for both sentiment classification and question paraphrase tasks.
Towards Robust Prompts on Vision-Language Models
With the advent of vision-language models (VLMs) that can perform in-context and prompt-based learning, how can we design prompting approaches that robustly generalize to distribution shift and can be used on novel classes outside the support set of the prompts?
Training Deep Boltzmann Networks with Sparse Ising Machines
These results demonstrate the potential of using Ising machines for traditionally hard-to-train deep generative Boltzmann networks, with further possible improvement in nanodevice-based realizations.
What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel
A wide breadth of research has devised data augmentation approaches that can improve both accuracy and generalization performance for neural networks.
Adjacent-Level Feature Cross-Fusion With 3-D CNN for Remote Sensing Image Change Detection
First, through the inner fusion property of 3D convolution, we design a new feature fusion way that can simultaneously extract and fuse the feature information from bi-temporal images.
Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers
Large pre-trained language models have shown remarkable performance over the past few years.
Are Vision Transformers Robust to Patch Perturbations?
However, when ViTs are attacked by an adversary, the attention mechanism can be easily fooled to focus more on the adversarially perturbed patches and cause a mistake.
Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
We show that patch-based negative augmentation consistently improves robustness of ViTs across a wide set of ImageNet based robustness benchmarks.
Are Vision Transformers Robust to Patch-wise Perturbations?
Based on extensive qualitative and quantitative experiments, we discover that ViT's stronger robustness to natural corrupted patches and higher vulnerability against adversarial patches are both caused by the attention mechanism.
A Multiscale Graph Convolutional Network for Change Detection in Homogeneous and Heterogeneous Remote Sensing Images
In this paper, a novel CD method based on the graph convolutional network (GCN) and multiscale object-based technique is proposed for both homogeneous and heterogeneous images.
What are effective labels for augmented data? Improving robustness with AutoLabel
Despite this, most existing work simply reuses the original label from the clean data, and the choice of label accompanying the augmented data is relatively less explored.
CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation
Experiments on real-world NLP datasets demonstrate that our method can generate more diverse and fluent adversarial texts, compared to many existing adversarial text generation approaches.
Improving Calibration through the Relationship with Adversarial Robustness
To this end, we propose Adversarial Robustness based Adaptive Label Smoothing (AR-AdaLS) that integrates the correlations of adversarial robustness and calibration into training by adaptively softening labels for an example based on how easily it can be attacked by an adversary.
Deflecting Adversarial Attacks
There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack.
Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
Then, we diagnose the adversarial examples for CapsNets and find that the success of the reconstructive attack is highly related to the visual similarity between the source and target class.
Evaluation Methodology for Attacks Against Confidence Thresholding Models
Current machine learning algorithms can be easily fooled by adversarial examples.
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Cross-Domain Collaborative Learning via Cluster Canonical Correlation Analysis and Random Walker for Hyperspectral Image Classification
To be specific, the proposed CDCL method is an iterative process of three main stages, i. e. twice of RW-based pseudolabeling and cross domain learning via C-CCA.
Tensor Alignment Based Domain Adaptation for Hyperspectral Image Classification
Then we consider the subspace invariance between two domains as projection matrices and original tensors are projected as core tensors with lower dimensions into the invariant tensor subspace by applying Tucker decomposition.
Autofocus Layer for Semantic Segmentation
We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing.
Ranked #5 on
Brain Tumor Segmentation
on BRATS-2015
Hierarchical Cellular Automata for Visual Saliency
The CCA can act as an efficient pixel-wise aggregation algorithm that can integrate state-of-the-art methods, resulting in even better results.
A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades.
Saliency Detection via Cellular Automata
In this paper, we introduce Cellular Automata--a dynamic evolution model to intuitively detect the salient object.
