Search Results for author:
Found 13 papers, 4 papers with code
Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation
We conducted a series of experiments to investigate whether and how distillation can be used to accelerate training using ResNet-50 trained on ImageNet and BERT trained on C4 with a masked language modeling objective and evaluated on GLUE, using common enterprise hardware (8x NVIDIA A100).
Learning Omnidirectional Flow in 360-degree Video via Siamese Representation
Optical flow estimation in omnidirectional videos faces two significant issues: the lack of benchmark datasets and the challenge of adapting perspective video-based methods to accommodate the omnidirectional nature.
Lipschitz Continuity Retained Binary Neural Network
Relying on the premise that the performance of a binary neural network can be largely restored with eliminated quantization error between full-precision weight vectors and their corresponding binary vectors, existing works of network binarization frequently adopt the idea of model robustness to reach the aforementioned objective.
Network Binarization via Contrastive Learning
Neural network binarization accelerates deep models by quantizing their weights and activations into 1-bit.
Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning
Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate the superiority of our novel Fourier analysis based MBP compared to other traditional MBP algorithms.
Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Neural Networks
Algorithmic bias is of increasing concern, both to the research community, and society at large.
Contrastive Mutual Information Maximization for Binary Neural Networks
Neural network binarization accelerates deep models by quantizing their weights and activations into 1-bit.
Lipschitz Continuity Guided Knowledge Distillation
Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones.
Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation
In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness.
Parallel Blockwise Knowledge Distillation for Deep Neural Network Compression
The experimental results running on an AMD server with four Geforce RTX 2080Ti GPUs show that our algorithm can achieve 3x speedup plus 19% energy savings on VGG distillation, and 3. 5x speedup plus 29% energy savings on ResNet distillation, both with negligible accuracy loss.
Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset
To bridge this gap, in this paper we propose a novel Egocentric (first-person) 360{\deg} Kinetic human activity video dataset (EgoK360).
Revisiting Optical Flow Estimation in 360 Videos
Second, we refine the network by training with augmented data in a supervised manner.
Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention
Recent works have shown that attention mechanism is beneficial to the fusion process.
