Referring object detection and referring image segmentation are important tasks that require joint understanding of visual information and natural language. Yet there has been evidence that current benchmark datasets suffer from bias, and current state-of-the-art models cannot be easily evaluated on their intermediate reasoning process. To address these issues and complement similar efforts in visual question answering, we build CLEVR-Ref+, a synthetic diagnostic dataset for referring expression comprehension. The precise locations and attributes of the objects are readily available, and the referring expressions are automatically associated with functional programs. The synthetic nature allows control over dataset bias (through sampling strategy), and the modular programs enable intermediate reasoning ground truth without human annotators.In addition to evaluating several state-of-the-art models on CLEVR-Ref+, we also propose IEP-Ref, a module network approach that significantly outperforms other models on our dataset. In particular, we present two interesting and important findings using IEP-Ref:(1) the module trained to transform feature maps into segmentation masks can be attached to any intermediate module to reveal the entire reasoning process step-by-step; (2) even if all training data has at least one object referred, IEP-Ref can correctly predict no-foreground when presented with false-premise referring expressions. To the best of our knowledge, this is the first direct and quantitative proof that neural modules behave in the way they are intended. 1
Pseudopolyrotaxane was obtained through the grinding of a mixture of O‐trimethyl‐α‐cyclodextrin and polytetrahydrofuran in a mortar by solvent‐free synthesis, and it was fixed to stable polyrotaxane by a successive end‐capping reaction with a bulky isocyanate by solid‐state grinding in a mortar. Higher molecular weight polytetrahydrofurans (Mn > 1000) successfully produced corresponding polyrotaxanes in moderate yields and with moderate coverage ratios. O‐Trimethyl‐β‐cyclodextrin and poly(ethylene glycol) also formed corresponding pseudopolyrotaxanes and polyrotaxanes by the grinding method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.