Zero-shot Object-Level OOD Detection with Context-Aware Inpainting
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Out of Distribution (OOD) DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection
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) DetectionContext-Aware Zero-Shot Recognition
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 LearningFrom Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation
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+2Question Answering Infused Pre-training of General-Purpose Contextualized Representations
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+1Question Answering Infused Pre-training of General-Purpose Contextualized Representations
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