Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Knowledge and Logical Reasoning in the Era of Data-driven Learning

Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models

Yunhao Ge · Jie Ren · Jiaping Zhao · Kaifeng Chen · Andrew Gallagher · Laurent Itti · Balaji Lakshminarayanan


Abstract:

We focus on the challenge of out-of-distribution (OOD) detection in deep learning models, a crucial aspect in ensuring reliability. Despite considerable effort, the problem remains significantly challenging in deep learning models due to their propensity to output over-confident predictions for OOD inputs. We propose a novel one-class open-set OOD detector that leverages text-image pre-trained models in a zero-shot fashion and incorporates various descriptions of in-domain and OOD. Our approach is designed to detect anything not in-domain and offers the flexibility to detect a wide variety of OOD, defined via fine- or coarse-grained labels, or even in natural language. We evaluate our approach on challenging benchmarks including large-scale datasets containing fine-grained, semantically similar classes, distributionally shifted images, and multi-object images containing a mixture of in-domain and OOD objects. Our method shows superior performance over previous methods on all benchmarks.

Chat is not available.