Search Results for author:
Found 22 papers, 13 papers with code
Rewrite the Stars
Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design.
Don't Judge by the Look: Towards Motion Coherent Video Representation
Current training pipelines in object recognition neglect Hue Jittering when doing data augmentation as it not only brings appearance changes that are detrimental to classification, but also the implementation is inefficient in practice.
Latent Graph Inference with Limited Supervision
We begin by defining the pivotal nodes as $k$-hop starved nodes, which can be identified based on a given adjacency matrix.
Frame Flexible Network
To fix this issue, we propose a general framework, named Frame Flexible Network (FFN), which not only enables the model to be evaluated at different frames to adjust its computation, but also reduces the memory costs of storing multiple models significantly.
Making Reconstruction-based Method Great Again for Video Anomaly Detection
With the same perturbation magnitude, the testing reconstruction error of the normal frames lowers more than that of the abnormal frames, which contributes to mitigating the overfitting problem of reconstruction.
Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning
The state of neural network pruning has been noticed to be unclear and even confusing for a while, largely due to "a lack of standardized benchmarks and metrics" [3].
Look More but Care Less in Video Recognition
To tackle this problem, we propose Ample and Focal Network (AFNet), which is composed of two branches to utilize more frames but with less computation.
Parameter-Efficient Masking Networks
We validate the potential of PEMN learning masks on random weights with limited unique values and test its effectiveness for a new compression paradigm based on different network architectures.
Dual Lottery Ticket Hypothesis
In this work, we regard the winning ticket from LTH as the subnetwork which is in trainable condition and its performance as our benchmark, then go from a complementary direction to articulate the Dual Lottery Ticket Hypothesis (DLTH): Randomly selected subnetworks from a randomly initialized dense network can be transformed into a trainable condition and achieve admirable performance compared with LTH -- random tickets in a given lottery pool can be transformed into winning tickets.
SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation
Next we add adversarial perturbation to the transformed features to decrease their softmax scores of the predicted labels and design anomaly scores based on the predictive uncertainties of the classifier on these perturbed features.
Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble
Current Sign Language Recognition (SLR) methods usually extract features via deep neural networks and suffer overfitting due to limited and noisy data.
Rethinking Again the Value of Network Pruning -- A Dynamical Isometry Perspective
Several recent works questioned the value of inheriting weight in structured neural network pruning because they empirically found training from scratch can match or even outperform finetuning a pruned model.
Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
This paper is meant to explain it through the lens of dynamical isometry [42].
Skeleton Aware Multi-modal Sign Language Recognition
Sign language is commonly used by deaf or speech impaired people to communicate but requires significant effort to master.
Ranked #2 on
Sign Language Recognition
on WLASL-2000
Recent Advances on Neural Network Pruning at Initialization
Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network.
SuperFront: From Low-resolution to High-resolution Frontal Face Synthesis
Even as impressive milestones are achieved in synthesizing faces, the importance of preserving identity is needed in practice and should not be overlooked.
Collaborative Attention Mechanism for Multi-View Action Recognition
Extensive experiments on four action datasets illustrate the proposed CAM achieves better results for each view and also boosts multi-view performance.
Correlative Channel-Aware Fusion for Multi-View Time Series Classification
Multi-view time series classification (MVTSC) aims to improve the performance by fusing the distinctive temporal information from multiple views.
Tuning-Free Disentanglement via Projection
In representation learning and non-linear dimension reduction, there is a huge interest to learn the 'disentangled' latent variables, where each sub-coordinate almost uniquely controls a facet of the observed data.
Elastic Neural Networks for Classification
In this work we propose a framework for improving the performance of any deep neural network that may suffer from vanishing gradients.
Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision
We propose a new framework for image classification with deep neural networks.
