Code for our work "Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection".
Code will be released upon publication.
Here we provide the generated salency maps for our method in Google Drive: Pseudo labels (Stage 1) and Saliency maps (Stage 2), or download from Baidu Disk [g6xb].
Torchserve Dashboard Torchserve Dashboard using Streamlit Related blog post Usage Additional Requirement: torchserve (recommended:v0.5.2) Simply run:
Zero-DCE and Zero-DCE++(Lite architechture for Mobile and edge Devices) Papers Abstract The paper presents a novel method, Zero-Reference Deep Curve E
Multitask Learning Strengthens Adversarial Robustness
APP: Anytime Progressive Pruning Diganta Misra1,2,3, Bharat Runwal2,4, Tianlong Chen5, Zhangyang Wang5, Irina Rish1,3 1 Mila - Quebec AI Institute,2 L
Please use stacknn-core instead! StackNN This project implements differentiable stacks and queues in PyTorch. The data structures are implemented in s
Instance-level Image Retrieval using Reranking Transformers Fuwen Tan, Jiangbo Yuan, Vicente Ordonez, ICCV 2021. Abstract Instance-level image retriev
PE-former: Pose Estimation Transformer Vision transformer architectures perform very well for image classification tasks. Efforts to solve more challe
Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai
SfMLearner Pytorch version This codebase implements the system described in the paper: Unsupervised Learning of Depth and Ego-Motion from Video Tinghu
Torchlight 2 Lan Game Server Tool A message forwarding tool for Torchlight 2 lan
LexSubGen Lexical Substitution Framework This repository contains the code to reproduce the results from the paper: Arefyev Nikolay, Sheludko Boris, P
3DETR: An End-to-End Transformer Model for 3D Object Detection PyTorch implementation and models for 3DETR. 3DETR (3D DEtection TRansformer) is a simp
ContextNet ContextNet has CNN-RNN-transducer architecture and features a fully convolutional encoder that incorporates global context information into
DirectQuote - A Dataset for Direct Quotation Extraction and Attribution in News Articles DirectQuote is a corpus containing 19,760 paragraphs and 10,3
rscolorq Rust port of Derrick Coetzee's scolorq, based on the 1998 paper "On spatial quantization of color images" by Jan Puzicha, Markus Held, Jens K
Graph Convolutional Networks for Temporal Action Localization This repo holds the codes and models for the PGCN framework presented on ICCV 2019 Graph
Convolutional MLP ConvMLP: Hierarchical Convolutional MLPs for Vision Preprint link: ConvMLP: Hierarchical Convolutional MLPs for Vision By Jiachen Li
Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose Release Notes The official PyTorch implementation of Neural View S
vae-textures This is an experiment with using variational autoencoders (VAEs) to perform mesh parameterization. This was also my first project using J
Dual-Level Collaborative Transformer for Image Captioning This repository contains the reference code for the paper Dual-Level Collaborative Transform
103 Dec 10, 2022
15 Dec 10, 2022
15 Jun 10, 2022
12 Nov 22, 2022
141 Oct 06, 2022
87 Jan 03, 2023
23 Oct 17, 2022
2.8k Jan 08, 2023
909 Dec 22, 2022
3 Nov 01, 2022
37 Sep 15, 2022
487 Dec 31, 2022
24 Nov 24, 2022
9 Sep 23, 2022
37 Dec 22, 2022
318 Dec 06, 2022
143 Jan 03, 2023
20 Oct 09, 2022
41 May 24, 2022
160 Dec 11, 2022