Search Results for author:
Found 13 papers, 1 papers with code
Efficient approximation of Earth Mover's Distance Based on Nearest Neighbor Search
Earth Mover's Distance (EMD) is an important similarity measure between two distributions, used in computer vision and many other application domains.
Data-Driven Deep Supervision for Skin Lesion Classification
Specifically, we analyze the convolutional network's behavior (field-of-view) to find the location of deep supervision for improved feature extraction.
Associative Memory Based Experience Replay for Deep Reinforcement Learning
AMPER replaces the widely-used time-costly tree-traversal-based priority sampling in PER while preserving the learning performance.
Data-Driven Deep Supervision for Medical Image Segmentation
In this paper, we study medical image segmentation by focusing on robust data-specific feature extraction to achieve improved dense prediction.
Experimentally realized memristive memory augmented neural network
Memory augmented neural network has been proposed to achieve the goal, but the memory module has to be stored in an off-chip memory due to its size.
Image Complexity Guided Network Compression for Biomedical Image Segmentation
Finally, the mapping is used to determine the convolutional layer-wise multiplicative factor for generating a compressed network.
Objective-Dependent Uncertainty Driven Retinal Vessel Segmentation
In this paper, we study retinal vessel segmentation by incorporating tiny vessel segmentation into our framework for the overall accurate vessel segmentation.
In-Memory Nearest Neighbor Search with FeFET Multi-Bit Content-Addressable Memories
Moreover, this approach achieves accuracies comparable to floating-point precision implementations in software for NN classification and one/few-shot learning tasks.
Nonvolatile Spintronic Memory Cells for Neural Networks
A new spintronic nonvolatile memory cell analogous to 1T DRAM with non-destructive read is proposed.
Application-level Studies of Cellular Neural Network-based Hardware Accelerators
While it is well-known that CeNNs can be well-suited for spatio-temporal information processing, few (if any) studies have quantified the energy/delay/accuracy of a CeNN-friendly algorithm and compared the CeNN-based approach to the best von Neumann algorithm at the application level.
CC-Net: Image Complexity Guided Network Compression for Biomedical Image Segmentation
Convolutional neural networks (CNNs) for biomedical image analysis are often of very large size, resulting in high memory requirement and high latency of operations.
A mixed signal architecture for convolutional neural networks
Deep neural network (DNN) accelerators with improved energy and delay are desirable for meeting the requirements of hardware targeted for IoT and edge computing systems.
DAC-SDC Low Power Object Detection Challenge for UAV Applications
The 55th Design Automation Conference (DAC) held its first System Design Contest (SDC) in 2018.
