Official implementation of NeurIPS 2021 paper "One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective"

Overview

OrthoHash

ArXiv (pdf)

Official pytorch implementation of the paper: "One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective"

NeurIPS 2021

Released on September 29, 2021

Description

This paper proposes a novel deep hashing model with only a single learning objective which is a simplification from most state of the art papers generally use lots of losses and regularizer. Specifically, it maximizes the cosine similarity between the continuous codes and their corresponding binary orthogonal codes to ensure both the discriminative capability of hash codes and the quantization error minimization. Besides, it adopts a Batch Normalization layer to ensure code balance and leverages the Label Smoothing strategy to modify the Cross-Entropy loss to tackle multi-labels classification. Extensive experiments show that the proposed method achieves better performance compared with the state-of-the-art multi-loss hashing methods on several benchmark datasets.

How to run

Training

python main.py --codebook-method B --ds cifar10 --margin 0.3 --seed 59495

Run python main.py --help to check what hyperparameters to run with. All the hyperparameters are the default parameters to get the performance in the paper.

The above command should obtain mAP of 0.824 at best for CIFAR-10.

Testing

python val.py -l /path/to/logdir

Dataset

Category-level Retrieval (ImageNet, NUS-WIDE, MS-COCO)

You may refer to this repo (https://github.com/swuxyj/DeepHash-pytorch) to download the datasets. I was using the same dataset format as HashNet. See utils/datasets.py to understand how to save the data folder.

Dataset sample: https://raw.githubusercontent.com/swuxyj/DeepHash-pytorch/master/data/imagenet/test.txt

For CIFAR-10, the code will auto generate a dataset at the first run. See utils/datasets.py.

Instance-level Retrieval (GLDv2, ROxf, RPar)

This code base is a simplified version and we did not include everything yet. We will release a version that will include the dataset we have generated and also the corresponding evaluation metrics, stay tune.

Performance Tuning (Some Tricks)

I have found some tricks to further improve the mAP score.

Avoid Overfitting

As set by the previous protocols, the dataset is small in size (e.g., 13k training images for ImageNet100) and hence overfitting can easily happen during the training.

An appropriate learning rate for backbone

We set a 10x lower learning rate for the backbone to avoid overfitting.

Cosine Margin

An appropriate higher cosine margin should be able to get higher performance as it slow down the overfitting.

Data Augmentation

We did not tune the data augmentation, but we believe that appropriate data augmentation can obtain a little bit of improvement in mAP.

Database Shuffling

If you shuffle the order of database before calculate_mAP, you might get 1~2% improvement in mAP.

It is because many items with same hamming distance will not be sorted properly, hence it will affect the mAP calculation.

Codebook Method

Run with --codebook-method O might help to improve mAP by 1~2%. The improvement is explained in our paper.

Feedback

Suggestions and opinions on this work (both positive and negative) are greatly welcomed. Please contact the authors by sending an email to jiuntian at gmail.com or kamwoh at gmail.com or cs.chan at um.edu.my.

Related Work

  1. Deep Polarized Network (DPN) - (https://github.com/kamwoh/DPN)

Notes

  1. You may get slightly different performance as compared with the paper, the random seed sometime affect the performance a lot, but should be very close.
  2. I re-run the training (64-bit ImageNet100) with this simplified version can obtain 0.709~0.710 on average (paper: 0.711).

License and Copyright

The project is open source under BSD-3 license (see the LICENSE file).

©2021 Universiti Malaya.

Owner
Ng Kam Woh
- Deep Learning Beginner
Ng Kam Woh
Deep learning based hand gesture recognition using LSTM and MediaPipie.

Hand Gesture Recognition Deep learning based hand gesture recognition using LSTM and MediaPipie. Demo video using PingPong Robot Files Pretrained mode

Brad 24 Nov 11, 2022
Official implementation of Self-supervised Image-to-text and Text-to-image Synthesis

Self-supervised Image-to-text and Text-to-image Synthesis This is the official implementation of Self-supervised Image-to-text and Text-to-image Synth

6 Jul 31, 2022
A Python type explainer!

typesplainer A Python typehint explainer! Available as a cli, as a website, as a vscode extension, as a vim extension Usage First, install the package

Typesplainer 79 Dec 01, 2022
Code for ACL 2019 Paper: "COMET: Commonsense Transformers for Automatic Knowledge Graph Construction"

To run a generation experiment (either conceptnet or atomic), follow these instructions: First Steps First clone, the repo: git clone https://github.c

Antoine Bosselut 575 Jan 01, 2023
Official PyTorch implementation of StyleGAN3

Modified StyleGAN3 Repo Changes Made tied to python 3.7 syntax .jpgs instead of .pngs for training sample seeds to recreate the 1024 training grid wit

Derrick Schultz (he/him) 83 Dec 15, 2022
Hand tracking demo for DIY Smart Glasses with a remote computer doing the work

CameraStream This is a demonstration that streams the image from smartglasses to a pc, does the hand recognition on the remote pc and streams the proc

Teemu Laurila 20 Oct 13, 2022
Predict the latency time of the deep learning models

Deep Neural Network Prediction Step 1. Genernate random parameters and Run them sequentially : $ python3 collect_data.py -gp -ep -pp -pl pooling -num

QAQ 1 Nov 12, 2021
An algorithm that handles large-scale aerial photo co-registration, based on SURF, RANSAC and PyTorch autograd.

An algorithm that handles large-scale aerial photo co-registration, based on SURF, RANSAC and PyTorch autograd.

Luna Yue Huang 41 Oct 29, 2022
Improving Convolutional Networks via Attention Transfer (ICLR 2017)

Attention Transfer PyTorch code for "Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Tran

Sergey Zagoruyko 1.4k Dec 23, 2022
Revisiting Self-Training for Few-Shot Learning of Language Model.

SFLM This is the implementation of the paper Revisiting Self-Training for Few-Shot Learning of Language Model. SFLM is short for self-training for few

15 Nov 19, 2022
library for nonlinear optimization, wrapping many algorithms for global and local, constrained or unconstrained, optimization

NLopt is a library for nonlinear local and global optimization, for functions with and without gradient information. It is designed as a simple, unifi

Steven G. Johnson 1.4k Dec 25, 2022
The repository for freeCodeCamp's YouTube course, Algorithmic Trading in Python

Algorithmic Trading in Python This repository Course Outline Section 1: Algorithmic Trading Fundamentals What is Algorithmic Trading? The Differences

Nick McCullum 1.8k Jan 02, 2023
Latent Network Models to Account for Noisy, Multiply-Reported Social Network Data

VIMuRe Latent Network Models to Account for Noisy, Multiply-Reported Social Network Data. If you use this code please cite this article (preprint). De

6 Dec 15, 2022
ICNet for Real-Time Semantic Segmentation on High-Resolution Images, ECCV2018

ICNet for Real-Time Semantic Segmentation on High-Resolution Images by Hengshuang Zhao, Xiaojuan Qi, Xiaoyong Shen, Jianping Shi, Jiaya Jia, details a

Hengshuang Zhao 594 Dec 31, 2022
Prototypical Networks for Few shot Learning in PyTorch

Prototypical Networks for Few shot Learning in PyTorch Simple alternative Implementation of Prototypical Networks for Few Shot Learning (paper, code)

Orobix 835 Jan 08, 2023
Session-aware Item-combination Recommendation with Transformer Network

Session-aware Item-combination Recommendation with Transformer Network 2nd place (0.39224) code and report for IEEE BigData Cup 2021 Track1 Report EDA

Tzu-Heng Lin 6 Mar 10, 2022
Chainer Implementation of Semantic Segmentation using Adversarial Networks

Semantic Segmentation using Adversarial Networks Requirements Chainer (1.23.0) Differences Use of FCN-VGG16 instead of Dilated8 as Segmentor. Caution

Taiki Oyama 99 Jun 28, 2022
Code for Overinterpretation paper Overinterpretation reveals image classification model pathologies

Overinterpretation This repository contains the code for the paper: Overinterpretation reveals image classification model pathologies Authors: Brandon

Gifford Lab, MIT CSAIL 17 Dec 10, 2022
Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [2021]

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations This repo contains the Pytorch implementation of our paper: Revisit

Wouter Van Gansbeke 80 Nov 20, 2022
Convolutional Neural Networks

Darknet Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation. D

Joseph Redmon 23.7k Jan 05, 2023