Search Results for author:
Found 13 papers, 0 papers with code
Training-efficient density quantum machine learning
Quantum machine learning requires powerful, flexible and efficiently trainable models to be successful in solving challenging problems.
Improving Generalization via Meta-Learning on Hard Samples
In particular, we show that using hard-to-classify instances in the validation set has both a theoretical connection to, and strong empirical evidence of generalization.
Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images
The key ideas presented in this paper are (i) Recovering accurate camera parameters via a robust pipeline from unposed day-to-day images is equally crucial in neural novel view synthesis problem; (ii) It is rather more practical to model object's content at different resolutions since dramatic camera motion is highly likely in day-to-day unposed images.
Efficiently Robustify Pre-trained Models
A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset.
Enhanced Stable View Synthesis
Extensive evaluation of our approach on the popular benchmark dataset, such as Tanks and Temples, shows substantial improvement in view synthesis results compared to the prior art.
Selective classification using a robust meta-learning approach
Predictive uncertainty-a model's self awareness regarding its accuracy on an input-is key for both building robust models via training interventions and for test-time applications such as selective classification.
Instance-Conditional Timescales of Decay for Non-Stationary Learning
Second, we learn an auxiliary scorer model that recovers the appropriate mixture of timescales as a function of the instance itself.
Robustifying the Multi-Scale Representation of Neural Radiance Fields
Although recently proposed Mip-NeRF could handle multi-scale imaging problems with NeRF, it cannot handle camera pose estimation error.
YouMVOS: An Actor-Centric Multi-Shot Video Object Segmentation Dataset
Many video understanding tasks require analyzing multi-shot videos, but existing datasets for video object segmentation (VOS) only consider single-shot videos.
Graph neural network initialisation of quantum approximate optimisation
In this work, we focus on the quantum approximate optimisation algorithm (QAOA) for solving the MaxCut problem.
MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation
The auxiliary task helps in capturing the relevant scale-related information to improve the performance of the main task.
From Fully Supervised to Zero Shot Settings for Twitter Hashtag Recommendation
To overcome this limitation, we propose a Zero Shot Learning (ZSL) paradigm for predicting unseen hashtag labels by learning the relationship between the semantic space of tweets and the embedding space of hashtag labels.
Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network
The SIFT descriptor layer captures the orientation and the spatial relationship of the features extracted by convolutional layer.
