paper-with-me

Papers Slice Discovery

“Slice Discovery” 태그가 달린 논문 10편 · 필터 해제

VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis

2025-05-06 · Xinyuan Yan, Xiwei Xuan, Jorge Piazentin Ono, Jiajing Guo 외

Real-world machine learning models require rigorous evaluation before deployment, especially in safety-critical domains like autonomous driving and surveillance. The evaluation of machine learning models often focuses on…

Autonomous Drivingobject-detectionObject DetectionSlice Discovery

Error Slice Discovery via Manifold Compactness

2025-01-31 · Han Yu, Jiashuo Liu, Hao Zou, Renzhe Xu 외

Despite the great performance of deep learning models in many areas, they still make mistakes and underperform on certain subsets of data, i.e. error slices. Given a trained model, it is important to identify its semanti…

Slice Discovery

DebugAgent: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging

2025-01-28 · Muxi Chen, Chenchen Zhao, Qiang Xu

Despite the significant success of deep learning models in computer vision, they often exhibit systematic failures on specific data subsets, known as error slices. Identifying and mitigating these error slices is crucial…

image-classificationImage Classificationobject-detectionObject Detection+2

LADDER: Language Driven Slice Discovery and Error Rectification

2024-07-31 · Shantanu Ghosh, Rayan Syed, Chenyu Wang, Clare B. Poynton 외

Error slice discovery is crucial to diagnose and mitigate model errors. Current clustering or discrete attribute-based slice discovery methods face key limitations: 1) clustering results in incoherent slices, while assig…

AttributeClusteringImage ClassificationLanguage Modelling+2

Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods

2024-06-17 · Vincent Olesen, Nina Weng, Aasa Feragen, Eike Petersen

Machine learning models have achieved high overall accuracy in medical image analysis. However, performance disparities on specific patient groups pose challenges to their clinical utility, safety, and fairness. This can…

FairnessMedical Image AnalysisSlice Discovery

LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model

2024-05-03 · Yulin Luo, Ruichuan An, Bocheng Zou, Yiming Tang 외

The distribution of subpopulations is an important property hidden within a dataset. Uncovering and analyzing the subpopulation distribution within datasets provides a comprehensive understanding of the datasets, standin…

Image CaptioningInstruction FollowingLanguage ModelingLanguage Modelling+3

Error Discovery by Clustering Influence Embeddings

2023-12-07 · NeurIPS 2023 11 · Fulton Wang, Julius Adebayo, Sarah Tan, Diego Garcia-Olano 외

We present a method for identifying groups of test examples -- slices -- on which a model under-performs, a task now known as slice discovery. We formalize coherence -- a requirement that erroneous predictions, within a …

ClusteringSlice Discovery

VLSlice: Interactive Vision-and-Language Slice Discovery

2023-09-13 · ICCV 2023 1 · Eric Slyman, Minsuk Kahng, Stefan Lee

Recent work in vision-and-language demonstrates that large-scale pretraining can learn generalizable models that are efficiently transferable to downstream tasks. While this may improve dataset-scale aggregate metrics, a…

Slice Discovery

Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms

2023-06-13 · Nari Johnson, Ángel Alexander Cabrera, Gregory Plumb, Ameet Talwalkar

Machine learning (ML) models that achieve high average accuracy can still underperform on semantically coherent subsets ("slices") of data. This behavior can have significant societal consequences for the safety or bias …

object-detectionObject DetectionSlice Discovery

Domino: Discovering Systematic Errors with Cross-Modal Embeddings

2022-03-24 · ICLR 2022 4 · Sabri Eyuboglu, Maya Varma, Khaled Saab, Jean-Benoit Delbrouck 외

Machine learning models that achieve high overall accuracy often make systematic errors on important subsets (or slices) of data. Identifying underperforming slices is particularly challenging when working with high-dime…

Representation LearningSlice DiscoveryTime Series Analysis
1–10 / 10