paper-with-me

홈 › Papers

Zero-shot Object-Level OOD Detection with Context-Aware Inpainting

2024-02-05 · Quang-Huy Nguyen, Jin Peng Zhou, Zhenzhen Liu, Khanh-Huyen Bui, Kilian Q. Weinberger, Dung D. Le

Machine learning algorithms are increasingly provided as black-box cloud services or pre-trained models, without access to their training data. This motivates the problem of zero-shot out-of-distribution (OOD) detection. Concretely, we aim to detect OOD objects that do not belong to the classifier's label set but are erroneously classified as in-distribution (ID) objects. Our approach, RONIN, uses an off-the-shelf diffusion model to replace detected objects with inpainting. RONIN conditions the inpainting process with the predicted ID label, drawing the input object closer to the in-distribution domain. As a result, the reconstructed object is very close to the original in the ID cases and far in the OOD cases, allowing RONIN to effectively distinguish ID and OOD samples. Throughout extensive experiments, we demonstrate that RONIN achieves competitive results compared to previous approaches across several datasets, both in zero-shot and non-zero-shot settings.

📄 PDF Abstract BibTeX arXiv:2402.03292

Code (0)

등록된 구현이 없습니다.

Tasks

Out of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection

2025-03-28 · Bin Zhang, Xiaoyang Qu, Guokuan Li, Jiguang Wan 외

As object detectors are increasingly deployed as black-box cloud services or pre-trained models with restricted access to the original training data, the challenge of zero-shot object-level out-of-distribution (OOD) dete…

ObjectOut of Distribution (OOD) Detection

Context-Aware Zero-Shot Recognition

2019-04-19 · Ruotian Luo, Ning Zhang, Bohyung Han, Linjie Yang

We present a novel problem setting in zero-shot learning, zero-shot object recognition and detection in the context. Contrary to the traditional zero-shot learning methods, which simply infers unseen categories by transf…

Object RecognitionZero-Shot Learning

From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation

2020-09-25 · Zhangxuan Gu, Siyuan Zhou, Li Niu, Zihan Zhao 외

Zero-shot learning has been actively studied for image classification task to relieve the burden of annotating image labels. Interestingly, semantic segmentation task requires more labor-intensive pixel-wise annotation, …

image-classificationImage ClassificationSegmentationSemantic Segmentation+2

Question Answering Infused Pre-training of General-Purpose Contextualized Representations

2021-06-15 · Findings (ACL) 2022 5 · Robin Jia, Mike Lewis, Luke Zettlemoyer

We propose a pre-training objective based on question answering (QA) for learning general-purpose contextual representations, motivated by the intuition that the representation of a phrase in a passage should encode all …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Question Answering+1

Question Answering Infused Pre-training of General-Purpose Contextualized Representations

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We propose a pre-training objective based on question answering (QA) for learning general-purpose contextual representations, motivated by the intuition that the representation of a phrase in a passage should encode all …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Question Answering+1