Search Results for author:
Found 11 papers, 2 papers with code
GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge
Video analytics pipelines have steadily shifted to edge deployments to reduce bandwidth overheads and privacy violations, but in doing so, face an ever-growing resource tension.
Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers
Compressed models that are deployed on the edge servers for inference suffer from data drift, where the live video data diverges from the training data.
BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images
Unfortunately, this imbalance enables a visual recognition system to perform well on head classes but poorly on tail classes.
Ranked #52 on
Long-tail Learning
on ImageNet-LT
HyperSTAR: Task-Aware Hyperparameters for Deep Networks
To reduce HPO time, we present HyperSTAR (System for Task Aware Hyperparameter Recommendation), a task-aware method to warm-start HPO for deep neural networks.
Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning
In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors.
Conscious Inference for Object Detection
Current Convolutional Neural Network (CNN)-based object detection models adopt strictly feedforward inference to predict the final detection results.
Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification
We address the problem of person re-identification from commodity depth sensors.
Multi-View Feature Engineering and Learning
We frame the problem of local representation of imaging data as the computation of minimal sufficient statistics that are invariant to nuisance variability induced by viewpoint and illumination.
An Empirical Evaluation of Current Convolutional Architectures' Ability to Manage Nuisance Location and Scale Variability
We conduct an empirical study to test the ability of Convolutional Neural Networks (CNNs) to reduce the effects of nuisance transformations of the input data, such as location, scale and aspect ratio.
Boosting Convolutional Features for Robust Object Proposals
Modern detection algorithms like Regions with CNNs (Girshick et al., 2014) rely on Selective Search (Uijlings et al., 2013) to propose regions which with high probability represent objects, where in turn CNNs are deployed for classification.
Visual Scene Representations: Contrast, Scaling and Occlusion
We study the structure of representations, defined as approximations of minimal sufficient statistics that are maximal invariants to nuisance factors, for visual data subject to scaling and occlusion of line-of-sight.
