Search Results for author:
Found 22 papers, 12 papers with code
VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment
Extensive experiments on a wide range of vision- and vision-language downstream tasks demonstrate the effectiveness of VoLTA on fine-grained applications without compromising the coarse-grained downstream performance, often outperforming methods using significantly more caption and box annotations.
MSA-GCN:Multiscale Adaptive Graph Convolution Network for Gait Emotion Recognition
Most of the existing methods recognize emotions by focusing on local actions over time.
Masked Siamese ConvNets
Self-supervised learning has shown superior performances over supervised methods on various vision benchmarks.
Positive Unlabeled Contrastive Learning
We extend this paradigm to the classical positive unlabeled (PU) setting, where the task is to learn a binary classifier given only a few labeled positive samples, and (often) a large amount of unlabeled samples (which could be positive or negative).
Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials
Topological materials present unconventional electronic properties that make them attractive for both basic science and next-generation technological applications.
Equivariant Contrastive Learning
In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge.
Understanding Dimensional Collapse in Contrastive Self-supervised Learning
It has been shown that non-contrastive methods suffer from a lesser collapse problem of a different nature: dimensional collapse, whereby the embedding vectors end up spanning a lower-dimensional subspace instead of the entire available embedding space.
Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations
In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge.
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
This causes the embedding vectors of distorted versions of a sample to be similar, while minimizing the redundancy between the components of these vectors.
Ranked #11 on
Image Classification
on Places205
Data-Informed Global Sparseness in Attention Mechanisms for Deep Neural Networks
The attention mechanism is a key component of the neural revolution in Natural Language Processing (NLP).
Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications
To address this issue, we propose a novel vector-vector-matrix architecture (VVMA), which greatly reduces the latency at inference time for NMT.
Implicit Rank-Minimizing Autoencoder
An important component of autoencoders is the method by which the information capacity of the latent representation is minimized or limited.
Contextualizing Enhances Gradient Based Meta Learning
We propose the implementation of contextualizers, which are generalizable prototypes that adapt to given examples and play a larger role in classification for gradient-based models.
Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery
We find that the EQL-based architecture can extrapolate quite well outside of the training data set compared to a standard neural network-based architecture, paving the way for deep learning to be applied in scientific exploration and discovery.
Perceptual representations of structural information in images: application to quality assessment of synthesized view in FTV scenario
As the immersive multimedia techniques like Free-viewpoint TV (FTV) develop at an astonishing rate, user's demand for high-quality immersive contents increases dramatically.
Rotational Unit of Memory: A Novel Representation Unit for RNNs with Scalable Applications
Stacking long short-term memory (LSTM) cells or gated recurrent units (GRUs) as part of a recurrent neural network (RNN) has become a standard approach to solving a number of tasks ranging from language modeling to text summarization.
WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices
We present a logarithmic-scale efficient convolutional neural network architecture for edge devices, named WaveletNet.
Migrating Knowledge between Physical Scenarios based on Artificial Neural Networks
First, we demonstrate that in predicting the transmission from multilayer photonic film, the relative error rate is reduced by 46. 8% (26. 5%) when the source data comes from 10-layer (8-layer) films and the target data comes from 8-layer (10-layer) films.
Rotational Unit of Memory
We evaluate our model on synthetic memorization, question answering and language modeling tasks.
Ranked #5 on
Question Answering
on bAbi
(Accuracy (trained on 1k) metric)
Nanophotonic Particle Simulation and Inverse Design Using Artificial Neural Networks
We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles.
Computational Physics Applied Physics Optics
Gated Orthogonal Recurrent Units: On Learning to Forget
We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory.
Ranked #7 on
Question Answering
on bAbi
(Accuracy (trained on 1k) metric)
Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
Using unitary (instead of general) matrices in artificial neural networks (ANNs) is a promising way to solve the gradient explosion/vanishing problem, as well as to enable ANNs to learn long-term correlations in the data.
