83 citations · 734 across the 57 of their papers we have counts for
12 papers · 1 filter
TrIMS: Transparent and Isolated Model Sharing for Low Latency Deep LearningInference in Function as a Service Environments
Abdul Dakkak, Cheng Li, Simon Garcia de Gonzalo +2
Deep neural networks (DNNs) have become core computation components within low latency Function as a Service (FaaS) prediction pipelines: including image recognition, object detect…
Frustrated with Replicating Claims of a Shared Model? A Solution
Abdul Dakkak, Cheng Li, Jinjun Xiong +1
Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that model owners and evaluators are hard-pressed analyzing and studying them. Th…
Accelerating Reduction and Scan Using Tensor Core Units
Abdul Dakkak, Cheng Li, Isaac Gelado +2
Driven by deep learning, there has been a surge of specialized processors for matrix multiplication, referred to as TensorCore Units (TCUs). These TCUs are capable of performing ma…
A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization
Bowen Cheng, Yunchao Wei, Jiahui Yu +5
While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in…
Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection
Khoi-Nguyen C. Mac, Dhiraj Joshi, Raymond A. Yeh +3
Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach in…
Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
Bowen Cheng, Yunchao Wei, Rogerio Feris +4
In this paper, we analyze failure cases of state-of-the-art detectors and observe that most hard false positives result from classification instead of localization and they have a…
SCOPE: C3SR Systems Characterization and Benchmarking Framework
Carl Pearson, Abdul Dakkak, Cheng Li +3
This report presents the design of the Scope infrastructure for extensible and portable benchmarking. Improvements in high- performance computing systems rely on coordination acros…
TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
Yunchao Wei, Zhiqiang Shen, Bowen Cheng +4
This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C)…
Interpretable and Globally Optimal Prediction for Textual Grounding using Image Concepts
Raymond A. Yeh, Jinjun Xiong, Wen-mei W. Hwu +2
Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining. Existing algorithms generally formulate the task as selection…
Face Recognition with Hybrid Efficient Convolution Algorithms on FPGAs
Chuanhao Zhuge, Xinheng Liu, Xiaofan Zhang +3
Deep Convolutional Neural Networks have become a Swiss knife in solving critical artificial intelligence tasks. However, deploying deep CNN models for latency-critical tasks remain…
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN
Bowen Cheng, Yunchao Wei, Honghui Shi +3
Recent region-based object detectors are usually built with separate classification and localization branches on top of shared feature extraction networks. In this paper, we analyz…
On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks
Yukun Ding, Jinglan Liu, Jinjun Xiong +1
Compression is a key step to deploy large neural networks on resource-constrained platforms. As a popular compression technique, quantization constrains the number of distinct weig…