PyTorch code and models for ScaLR image-to-lidar distillation method

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

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

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

A distributed deep learning framework that supports flexible parallelization strategies.

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

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".

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

DNN partition edge-cloud co-infer

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

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

Visual Sentiment Analysis

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

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

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

Acceptance rates for the major AI conferences

Mimicking packet loss at the edge for distributed inference

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

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

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

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-enri…

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