5 papers
Test-time Vocabulary Adaptation for Language-driven Object Detection
Mingxuan Liu, Tyler L. Hayes, Massimiliano Mancini +3
Open-vocabulary object detection models allow users to freely specify a class vocabulary in natural language at test time, guiding the detection of desired objects. However, vocabu…
What could go wrong? Discovering and describing failure modes in computer vision
Gabriela Csurka, Tyler L. Hayes, Diane Larlus +1
Deep learning models are effective, yet brittle. Even carefully trained, their behavior tends to be hard to predict when confronted with out-of-distribution samples. In this work,…
Placing Objects in Context via Inpainting for Out-of-distribution Segmentation
Pau de Jorge, Riccardo Volpi, Puneet K. Dokania +2
When deploying a semantic segmentation model into the real world, it will inevitably encounter semantic classes that were not seen during training. To ensure a safe deployment of s…
SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection
Mingxuan Liu, Tyler L. Hayes, Elisa Ricci +2
Open-vocabulary object detection (OvOD) has transformed detection into a language-guided task, empowering users to freely define their class vocabularies of interest during inferen…
PANDAS: Prototype-based Novel Class Discovery and Detection
Tyler L. Hayes, César R. de Souza, Namil Kim +3
Object detectors are typically trained once and for all on a fixed set of classes. However, this closed-world assumption is unrealistic in practice, as new classes will inevitably…