Lexlip: Lexicon-bottlenecked language-image pre-training for large-scale image-text sparse retrieval
Image-text retrieval (ITR) aims to retrieve images or texts that match a query originating from
the other modality. The conventional dense retrieval paradigm relies on encoding images …
the other modality. The conventional dense retrieval paradigm relies on encoding images …
CROMA: Remote sensing representations with contrastive radar-optical masked autoencoders
A vital and rapidly growing application, remote sensing offers vast yet sparsely labeled,
spatially aligned multimodal data; this makes self-supervised learning algorithms invaluable …
spatially aligned multimodal data; this makes self-supervised learning algorithms invaluable …
Balance act: Mitigating hubness in cross-modal retrieval with query and gallery banks
In this work, we present a post-processing solution to address the hubness problem in cross-
modal retrieval, a phenomenon where a small number of gallery data points are frequently …
modal retrieval, a phenomenon where a small number of gallery data points are frequently …
LexLIP: lexicon-bottlenecked language-image pre-training for large-scale image-text retrieval
Image-text retrieval (ITR) is a task to retrieve the relevant images/texts, given the query from
another modality. The conventional dense retrieval paradigm relies on encoding images …
another modality. The conventional dense retrieval paradigm relies on encoding images …
CSDNet: Contrastive Similarity Distillation Network for Multi-lingual Image-Text Retrieval
Cross-modal image-text retrieval is a crucial task in the field of vision and language, aimed
at retrieving the relevant samples from one modality as per the given user expressed in …
at retrieving the relevant samples from one modality as per the given user expressed in …
Self-supervised Pretraining of Vision Transformers for Earth Observation
A Fuller - 2023 - repository.library.carleton.ca
Remote sensing offers vast yet sparsely labeled multimodal data but lacks foundation
models that can be leveraged across societally impactful applications. In this thesis, I …
models that can be leveraged across societally impactful applications. In this thesis, I …