Abstract:Traditional image tagging and retrieval algorithms have limited value as a result of being trained with heavily curated datasets. These limitations are most evident when arbitrary search words are used that do not intersect with training set labels. Weak labels from user generated content (UGC) found in the wild (e.g., Google Photos, FlickR, etc.) have an almost unlimited number of unique words in the metadata tags. Prior work on word embeddings successfully leveraged unstructured text with large vocabularies,… Show more
“…Fast0Tag [14] projects an image by identifying a principal direction in the space and targeting that principal direction when learning to project the image. [15] uses noise contrastive estimation on a noisy web-scale dataset [16] to learn projection from image to word embeddings space. VSE++ [17] proposes a modified pairwise ranking loss weighted by violation caused by hard-negatives.…”
Learning a robust shared representation space is critical for effective multimedia retrieval, and is increasingly important as multimodal data grows in volume and diversity. The labeled datasets necessary for learning such a space are limited in size and also in coverage of semantic concepts. These limitations constrain performance: a shared representation learned on one dataset may not generalize well to another. We address this issue by building on the insight that, given limited data, it is easier to optimize the semantic structure of a space within a modality, than across modalities. We propose a two-stage shared representation learning framework with intra-modal optimization and subsequent cross-modal transfer learning of semantic structure that produces a robust shared representation space. We integrate multi-task learning into each step, making it possible to leverage multiple datasets, annotated with different concepts, as if they were one large dataset. Large-scale systematic experiments demonstrate improvements over previously reported state-ofthe-art methods on cross-modal retrieval tasks.
“…Fast0Tag [14] projects an image by identifying a principal direction in the space and targeting that principal direction when learning to project the image. [15] uses noise contrastive estimation on a noisy web-scale dataset [16] to learn projection from image to word embeddings space. VSE++ [17] proposes a modified pairwise ranking loss weighted by violation caused by hard-negatives.…”
Learning a robust shared representation space is critical for effective multimedia retrieval, and is increasingly important as multimodal data grows in volume and diversity. The labeled datasets necessary for learning such a space are limited in size and also in coverage of semantic concepts. These limitations constrain performance: a shared representation learned on one dataset may not generalize well to another. We address this issue by building on the insight that, given limited data, it is easier to optimize the semantic structure of a space within a modality, than across modalities. We propose a two-stage shared representation learning framework with intra-modal optimization and subsequent cross-modal transfer learning of semantic structure that produces a robust shared representation space. We integrate multi-task learning into each step, making it possible to leverage multiple datasets, annotated with different concepts, as if they were one large dataset. Large-scale systematic experiments demonstrate improvements over previously reported state-ofthe-art methods on cross-modal retrieval tasks.
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.