Search Results for author:
Found 25 papers, 12 papers with code
Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?
Evaluating Large Language Models (LLMs) is challenging due to their generative nature, necessitating precise evaluation methodologies.
Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
Vision-language models, such as CLIP, have shown promising Out-of-Distribution (OoD) generalization under various types of distribution shifts.
CRISPR: Ensemble Model
This is because most existing methods are trained on separate datasets with different genes and cells, which limits their generalizability.
Annotation-Free Group Robustness via Loss-Based Resampling
In order to provide group robustness without such annotations, we propose a new method, called loss-based feature re-weighting (LFR), in which we infer a grouping of the data by evaluating an ERM-pre-trained model on a small left-out split of the training data.
Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection
A promising solution to this problem is last-layer retraining, which involves retraining the linear classifier head on a small subset of data without spurious cues.
Blacksmith: Fast Adversarial Training of Vision Transformers via a Mixture of Single-step and Multi-step Methods
Despite the remarkable success achieved by deep learning algorithms in various domains, such as computer vision, they remain vulnerable to adversarial perturbations.
Seeking Next Layer Neurons' Attention for Error-Backpropagation-Like Training in a Multi-Agent Network Framework
Despite considerable theoretical progress in the training of neural networks viewed as a multi-agent system of neurons, particularly concerning biological plausibility and decentralized training, their applicability to real-world problems remains limited due to scalability issues.
Novel Pipeline for Diagnosing Acute Lymphoblastic Leukemia Sensitive to Related Biomarkers
We introduced a novel pipeline for diagnosing ALL that approximates the process used by hematologists, is sensitive to disease biomarkers, and achieves an accuracy of 96. 15%, an F1-score of 94. 24%, a sensitivity of 97. 56%, and a specificity of 90. 91% on ALL IDB 1.
KS-GNNExplainer: Global Model Interpretation Through Instance Explanations On Histopathology images
To follow this vision, we developed KS-GNNExplainer, the first instance-level graph neural network explainer that leverages current instance-level approaches in an effective manner to provide more informative and reliable explainable outputs, which are crucial for applied AI in the health domain.
A Data-Centric Approach for Improving Adversarial Training Through the Lens of Out-of-Distribution Detection
For this purpose, we first demonstrate that the existing model-based methods can be equivalent to applying smaller perturbation or optimization weights to the hard training examples.
InForecaster: Forecasting Influenza Hemagglutinin Mutations Through the Lens of Anomaly Detection
This helps the model to learn a shared unique representation between normal training samples as much as possible, which improves the discernibility and detectability of mutated samples from the unmutated ones at the test time.
Your Out-of-Distribution Detection Method is Not Robust!
Therefore, unlike OOD detection in the standard setting, access to OOD, as well as in-distribution, samples sounds necessary in the adversarial training setup.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
PIAT: Physics Informed Adversarial Training for Solving Partial Differential Equations
In this paper, we propose the physics informed adversarial training (PIAT) of neural networks for solving nonlinear differential equations (NDE).
OOD Augmentation May Be at Odds with Open-Set Recognition
Despite advances in image classification methods, detecting the samples not belonging to the training classes is still a challenging problem.
SwinCheX: Multi-label classification on chest X-ray images with transformers
Our model has been tested with several number of MLP layers for the head setting, each achieves a competitive AUC score on all classes.
Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection
Effectiveness of our method for both the near-distribution and standard novelty detection is assessed through extensive experiments on datasets in diverse applications such as medical images, object classification, and quality control.
Ranked #2 on
Anomaly Detection
on One-class CIFAR-10
(using extra training data)
A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
To date, several research domains tackle the problem of detecting unfamiliar samples, including anomaly detection, novelty detection, one-class learning, open set recognition, and out-of-distribution detection.
The Interplay between Distribution Parameters and the Accuracy-Robustness Tradeoff in Classification
Adversarial training tends to result in models that are less accurate on natural (unperturbed) examples compared to standard models.
Lagrangian Objective Function Leads to Improved Unforeseen Attack Generalization in Adversarial Training
However, it usually fails against other attacks, i. e. the model overfits to the training attack scheme.
ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training
Making deep neural networks robust to small adversarial noises has recently been sought in many applications.
Multiresolution Knowledge Distillation for Anomaly Detection
Unsupervised representation learning has proved to be a critical component of anomaly detection/localization in images.
Puzzle-AE: Novelty Detection in Images through Solving Puzzles
Puzzle-solving, as a pretext task of self-supervised learning (SSL) methods, has earlier proved its ability in learning semantically meaningful features.
Towards Deep Learning Models Resistant to Large Perturbations
Adversarial robustness has proven to be a required property of machine learning algorithms.
ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detection
To address this problem, we propose a novel AE that can learn more semantically meaningful features.
An Impossibility Result for High Dimensional Supervised Learning
We study high-dimensional asymptotic performance limits of binary supervised classification problems where the class conditional densities are Gaussian with unknown means and covariances and the number of signal dimensions scales faster than the number of labeled training samples.
