Search Results for author:
Found 18 papers, 13 papers with code
Learning Joint Visual Semantic Matching Embeddings for Language-guided Retrieval
Interactive image retrieval is an emerging research topic with the objective of integrating inputs from multiple modalities as query for retrieval, e. g., textual feedback from users to guide, modify or refine image retrieval.
Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment
In this work, we formulate a new knowledge distillation framework to transfer the knowledge from self-supervised pre-trained models to any other student network by a novel approach named Embedding Graph Alignment.
Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval
Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information.
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data.
BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
Moreover, many of the high-performing deep learning models that are already trained and deployed are non-Bayesian in nature and do not provide uncertainty estimates.
Attention Consistency on Visual Corruptions for Single-Source Domain Generalization
Generalizing visual recognition models trained on a single distribution to unseen input distributions (i. e. domains) requires making them robust to superfluous correlations in the training set.
Probabilistic Compositional Embeddings for Multimodal Image Retrieval
Without bells and whistles, we show that our probabilistic model formulation significantly outperforms existing related methods on multimodal image retrieval while generalizing well to query with different amounts of inputs given in arbitrary visual and (or) textual modalities.
Robustness via Uncertainty-aware Cycle Consistency
Unpaired image-to-image translation refers to learning inter-image-domain mapping without corresponding image pairs.
Uncertainty-Guided Progressive GANs for Medical Image Translation
However, the state-of-the-art GAN-based frameworks do not estimate the uncertainty in the predictions made by the network that is essential for making informed medical decisions and subsequent revision by medical experts and has recently been shown to improve the performance and interpretability of the model.
Where and When: Space-Time Attention for Audio-Visual Explanations
Recent advances in XAI provide explanations for models trained on still images.
Explainable artificial intelligence
Multimodal Deep Learning
Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
Having access to multi-modal cues (e. g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality.
Uncertainty-aware Generalized Adaptive CycleGAN
Unpaired image-to-image translation refers to learning inter-image-domain mapping in an unsupervised manner.
Image Search With Text Feedback by Visiolinguistic Attention Learning
In this work, we tackle this task by a novel Visiolinguistic Attention Learning (VAL) framework.
Ranked #8 on
Image Retrieval
on Fashion IQ
Instance-Guided Context Rendering for Cross-Domain Person Re-Identification
To tackle this limitation, we propose a novel Instance-Guided Context Rendering scheme, which transfers the source person identities into diverse target domain contexts to enable supervised re-id model learning in the unlabelled target domain.
Multiband gravitational-wave event rates and stellar physics
We use population synthesis simulations of isolated binary stars to explore some of the stellar physics that could be constrained with multiband events, and we show that specific formation pathways might be overrepresented in multiband events compared to ground-only detections.
High Energy Astrophysical Phenomena General Relativity and Quantum Cosmology
Semi-Supervised Deep Learning with Memory
We consider the semi-supervised multi-class classification problem of learning from sparse labelled and abundant unlabelled training data.
Deep Association Learning for Unsupervised Video Person Re-identification
In this work, to address the video person re-id task, we formulate a novel Deep Association Learning (DAL) scheme, the first end-to-end deep learning method using none of the identity labels in model initialisation and training.
Ranked #5 on
Person Re-Identification
on PRID2011
Optimizing LIGO with LISA forewarnings to improve black-hole spectroscopy
The early inspiral of massive stellar-mass black-hole binaries merging in LIGO's sensitivity band will be detectable at low frequencies by the upcoming space mission LISA.
General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena
