Search Results for author:
Found 11 papers, 5 papers with code
Sample-Efficient Behavior Cloning Using General Domain Knowledge
Behavior cloning has shown success in many sequential decision-making tasks by learning from expert demonstrations, yet they can be very sample inefficient and fail to generalize to unseen scenarios.
Faster Multi-GPU Training with PPLL: A Pipeline Parallelism Framework Leveraging Local Learning
To address this issue, we present PPLL (Pipeline Parallelism based on Local Learning), a novel framework that leverages local learning algorithms to enable effective parallel training across multiple GPUs.
LAKD-Activation Mapping Distillation Based on Local Learning
Existing knowledge distillation methods focus on designing different distillation targets to acquire knowledge from teacher models.
HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion
To overcome these limitations, we propose a novel model called HPFF that performs hierarchical locally supervised learning and patch-level feature computation on the auxiliary networks.
Momentum Auxiliary Network for Supervised Local Learning
Supervised local learning, which segments the network into multiple local blocks updated by independent auxiliary networks.
MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network
Specifically, MLAAN comprises Multilaminar Local Modules (MLM) and Leap Augmented Modules (LAM).
Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank
Local learning offers an alternative to traditional end-to-end back-propagation in deep neural networks, significantly reducing GPU memory usage.
SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation
Then we design a face editing module that modifies speech content and facial latent codes into a single latent space.
SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images
With the increasing demand for search and rescue, it is highly demanded to detect objects of interest in large-scale images captured by Unmanned Aerial Vehicles (UAVs), which is quite challenging due to extremely small scales of objects.
Watermark Faker: Towards Forgery of Digital Image Watermarking
Digital watermarking has been widely used to protect the copyright and integrity of multimedia data.
SQE: a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking
We present a novel self quality evaluation metric SQE for parameters optimization in the challenging yet critical multi-object tracking task.
