jodyngo

TMO

[WACV 2023] Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation

audio-streaming

lightweightSOD

motion-saliency-dynamic-mode-decomposition

PySODEvalToolkit

PySODEvalToolkit: A Python-based Evaluation Toolbox for Salient Object Detection and Camouflaged Object Detection

PyTorch-ONNX-TFLite

Conversion of PyTorch Models into TFLite

UAV-streaming

Conference-Acceptance-Rate

Acceptance rates for the major AI conferences

DADS

云边协同- collaborative inference📚Dynamic adaptive DNN surgery for inference acceleration on the edge

DDP

DeViT

PyTorch implementation of the paper: Decomposing Vision Transformers for Collaborative Inference in Edge Devices

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

DNN-Partition

DNN partition edge-cloud co-infer

EdgeCam

A Distributed Camera System for Inference Scheduling and Continuous Learning in Video Analytics

EdgeDI

Code for paper "Joint Architecture Design and Workload Partitioning for DNN Inference on Industrial IoT Clusters"

EdgeKE

Code for paper "EdgeKE: An On-Demand Deep Learning IoT System for Cognitive Big Data on Industrial Edge Devices"

EdgeLD

Code for paper "Locally Distributed Deep Learning Inference on Edge Device Clusters"

examples-1

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

FlexFlow

A distributed deep learning framework that supports flexible parallelization strategies.

Hybrid-Models-Efficient-Edge-Inference-by-Selective-Query

I-Split

Official implementation of the paper "I-Split: Deep Network Interpretability for Split Computing" accepted @ ICPR 2022.

LeNo

The official implementation of AAAI 2023 "LeNo: Adversarial Robust Salient Object Detection Networks with Learnable Noise"

Mimicking-packet-loss-at-the-edge-for-distributed-inference

Mimicking packet loss at the edge for distributed inference

MSE-CNN-Implementations

Code database with the implementation of MSE-CNN, from the paper "DeepQTMT: A Deep Learning Approach for Fast QTMT-based CU Partition of Intra-mode VVC".

Pipe-BD

[DATE'23] Pipe-BD: Pipelined Parallel Blockwise Distillation

sc2-benchmark-Supervised-Compression-for-Split-Computing

[TMLR] "SC2 Benchmark: Supervised Compression for Split Computing"

TOG

Real-time object detection is one of the key applications of deep neural networks (DNNs) for real-world mission-critical systems. While DNN-powered object detection systems celebrate many life-enriching opportunities, they also open doors for misuse and abuse. This project presents a suite of adversarial objectness gradient attacks, coined as TOG,

vista-net

Code for the paper "VistaNet: Visual Aspect Attention Network for Multimodal Sentiment Analysis", AAAI'19

visual-sentiment-analysis

Visual Sentiment Analysis

Visual-Sentiment-Analysis-for-Review-Images-with-Item-Oriented-and-User-Oriented-CNN

Code for the paper "Visual Sentiment Analysis for Review Images with Item-Oriented and User-Oriented CNN", ACM MM'17