Search Results for author:
Found 21 papers, 7 papers with code
On Modulating the Gradient for Meta-Learning
Inspired by optimization techniques, we propose a novel meta-learning algorithm with gradient modulation to encourage fast-adaptation of neural networks in the absence of abundant data.
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
Beyond crowdsourcing, our initiative goes one step further in the exploration of the automatic collection of culturally relevant images through crawling and image generation.
CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation
Binaural audio generation (BAG) aims to convert monaural audio to stereo audio using visual prompts, requiring a deep understanding of spatial and semantic information.
Mining Your Own Secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models
Personalized text-to-image diffusion models have grown popular for their ability to efficiently acquire a new concept from user-defined text descriptions and a few images.
A randomized simulation trial evaluating ABiMed, a clinical decision support system for medication reviews and polypharmacy management
We recorded the problems identified by the pharmacists, the interventions proposed, the response time, the perceived usability and the comments.
Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks
Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability.
ABiMed: An intelligent and visual clinical decision support system for medication reviews and polypharmacy management
Conclusions: The association of guidelines implementation with visual presentation of knowledge is a promising approach for managing polypharmacy.
On Manipulating Scene Text in the Wild with Diffusion Models
In experiments, we thoroughly assess and compare our proposed method against state-of-the-arts on various scene text datasets, then provide extensive ablation studies for each granularity to analyze our performance gain.
Optical Character Recognition
Optical Character Recognition (OCR)
+1
FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing
In this paper, for the first time, we introduce optical flow into the attention module in the diffusion model's U-Net to address the inconsistency issue for text-to-video editing.
Subspace Distillation for Continual Learning
To mitigate forgetting prior knowledge, we propose a novel knowledge distillation technique that takes into the account the manifold structure of the latent/output space of a neural network in learning novel tasks.
On Generalizing Beyond Domains in Cross-Domain Continual Learning
Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task.
Dialog+ in Broadcasting: First Field Tests Using Deep-Learning-Based Dialogue Enhancement
To address this, Fraunhofer IIS has developed a deep-learning solution called Dialog+, capable of enabling speech level personalization also for content with only the final audio tracks available.
Meta-Learning for Multi-Label Few-Shot Classification
Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address.
Towards a Robust Differentiable Architecture Search under Label Noise
Our empirical evaluations show that the noise injecting operation does not degrade the performance of the NAS algorithm if the data is indeed clean.
On Learning the Geodesic Path for Incremental Learning
This in practice is done by minimizing the dissimilarity between current and previous responses of the network one way or another.
Reinforced Attention for Few-Shot Learning and Beyond
Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images.
Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces
In this paper, we propose addressing this problem using a mixture of subspaces.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
Adaptive Subspaces for Few-Shot Learning
In this paper, we provide a framework for few-shot learning by introducing dynamic classifiers that are constructed from few samples.
Ranked #15 on
Few-Shot Image Classification
on CIFAR-FS 5-way (1-shot)
Projective Subspace Networks For Few-Shot Learning
Generalization from limited examples, usually studied under the umbrella of meta-learning, equips learning techniques with the ability to adapt quickly in dynamical environments and proves to be an essential aspect of lifelong learning.
Reflection Removal for In-Vehicle Black Box Videos
In this paper, we propose a novel method to remove the reflection on the windscreen in the in-vehicle black box videos.
A generic system for critiquing physicians' prescriptions: usability, satisfaction and lessons learnt
Clinical decision support systems have been developed to help physicians to take clinical guidelines into account during consultations.
