paper-with-me

Papers

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, analyzing performance around hand-crafted subgroups targeting specific bias dimensions reveals systemic undesirable behaviors. However, this subgroup analysis is frequently stalled by annotation efforts, which require extensive time and resources to collect the necessary data. Prior art attempts to automatically discover subgroups to circumvent these constraints but typically leverages model behavior on existing task-specific annotations and rapidly degrades on more complex inputs beyond "tabular" data, none of which study vision-and-language models. This paper presents VLSlice, an interactive system enabling user-guided discovery of coherent representation-level subgroups with consistent visiolinguistic behavior, denoted as vision-and-language slices, from unlabeled image sets. We show that VLSlice enables users to quickly generate diverse high-coherency slices in a user study (n=22) and release the tool publicly.

📄 PDF Abstract BibTeX arXiv:2309.06703

Code (1)

slymane/vlslice 공식 구현 pytorch

Tasks

Slice Discovery

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

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

GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks

2025-12-31 · Wei Zhang, Chaoqun Wang, Zixuan Guan, Sam Kao 외 arxiv

Systematic failures of vision models on semantically coherent subsets, known as error slices, reveal limitations in robustness and evaluation. Existing slice discovery approaches largely model slices as clusters in repre…

Object Detection

Active Slice Discovery in Large Language Models

2025-11-24 · Minhui Zhang, Prahar Ijner, Yoav Wald, Elliot Creager arxiv

Large Language Models (LLMs) often exhibit systematic errors on specific subsets of data, known as error slices. For instance, a slice can correspond to a certain demographic, where a model does poorly in identifying tox…

Active Learning

What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs

2026-06-01 · Abhishek Aich, Sparsh Garg, Vijay Kumar BG, Turgun Yusuf Kashgari 외 arxiv

Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs), yet verification remains sparse: many slices are missing, making empirical f…

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