Official implementation for the paper: Multi-label Classification with Partial Annotations using Class-aware Selective Loss

Overview

PWC

Multi-label Classification with Partial Annotations using Class-aware Selective Loss


Paper | Pretrained models

Official PyTorch Implementation

Emanuel Ben-Baruch, Tal Ridnik, Itamar Friedman, Avi Ben-Cohen, Nadav Zamir, Asaf Noy, Lihi Zelnik-Manor
DAMO Academy, Alibaba Group

Abstract

Large-scale multi-label classification datasets are commonly, and perhaps inevitably, partially annotated. That is, only a small subset of labels are annotated per sample. Different methods for handling the missing labels induce different properties on the model and impact its accuracy. In this work, we analyze the partial labeling problem, then propose a solution based on two key ideas. First, un-annotated labels should be treated selectively according to two probability quantities: the class distribution in the overall dataset and the specific label likelihood for a given data sample. We propose to estimate the class distribution using a dedicated temporary model, and we show its improved efficiency over a naive estimation computed using the dataset's partial annotations. Second, during the training of the target model, we emphasize the contribution of annotated labels over originally un-annotated labels by using a dedicated asymmetric loss. Experiments conducted on three partially labeled datasets, OpenImages, LVIS, and simulated-COCO, demonstrate the effectiveness of our approach. Specifically, with our novel selective approach, we achieve state-of-the-art results on OpenImages dataset. Code will be made available.

Class-aware Selective Approach

An overview of our approach is summarized in the following figure:

Loss Implementation

Our loss consists of a selective approach for adjusting the training mode for each class individualy and a partial asymmetric loss.

An implementation of the Class-aware Selective Loss (CSL) can be found here.

  • class PartialSelectiveLoss(nn.Module)

Pretrained Models

We provide models pretrained on the OpenImages datasset with different modes and architectures:

Model Architecture Link mAP
Ignore TResNet-M link 85.38
Negative TResNet-M link 85.85
Selective (CSL) TResNet-M link 86.72
Selective (CSL) TResNet-L link 87.34

Inference Code (Demo)

We provide inference code, that demonstrate how to load the model, pre-process an image and do inference. Example run of OpenImages model (after downloading the relevant model):

python infer.py  \
--dataset_type=OpenImages \
--model_name=tresnet_m \
--model_path=./models_local/mtresnet_opim_86.72.pth \
--pic_path=./pics/10162266293_c7634cbda9_o.jpg \
--input_size=448

Result Examples

Training Code

Training code is provided in (train.py). Also, code for simulating partial annotation for the MS-COCO dataset is available (here). In particular, two "partial" simulation schemes are implemented: fix-per-class(FPC) and random-per-sample (RPS).

  • FPC: For each class, we randomly sample a fixed number of positive annotations and the same number of negative annotations. The rest of the annotations are dropped.
  • RPA: We omit each annotation with probability p.

Pretrained weights using the ImageNet-21k dataset can be found here: link
Pretrained weights using the ImageNet-1k dataset can be found here: link

Example of training with RPS simulation:

--data=/mnt/datasets/COCO/COCO_2014
--model-path=models/pretrain/mtresnet_21k
--gamma_pos=0
--gamma_neg=4
--gamma_unann=4
--simulate_partial_type=rps
--simulate_partial_param=0.5
--partial_loss_mode=selective
--likelihood_topk=5
--prior_threshold=0.5
--prior_path=./outputs/priors/prior_fpc_1000.csv

Example of training with FPC simulation:

--data=/mnt/datasets/COCO/COCO_2014
--model-path=models/pretrain/mtresnet_21k
--gamma_pos=0
--gamma_neg=4
--gamma_unann=4
--simulate_partial_type=fpc
--simulate_partial_param=1000
--partial_loss_mode=selective
--likelihood_topk=5
--prior_threshold=0.5
--prior_path=./outputs/priors/prior_fpc_1000.csv

Typical Training Results

FPC (1,000) simulation scheme:

Model mAP
Ignore, CE 76.46
Negative, CE 81.24
Negative, ASL (4,1) 81.64
CSL - Selective, P-ASL(4,3,1) 83.44

RPS (0.5) simulation scheme:

Model mAP
Ignore, CE 84.90
Negative, CE 81.21
Negative, ASL (4,1) 81.91
CSL- Selective, P-ASL(4,1,1) 85.21

Estimating the Class Distribution

The training code contains also the procedure for estimting the class distribution from the data. Our approach enables to rank the classes based on training a temporary model usinig the Ignore mode. link

Top 10 classes:

Method Top 10 ranked classes
Original 'person', 'chair', 'car', 'dining table', 'cup', 'bottle', 'bowl', 'handbag', 'truck', 'backpack'
Estiimate (Ignore mode) 'person', 'chair', 'handbag', 'cup', 'bench', 'bottle', 'backpack', 'car', 'cell phone', 'potted plant'
Estimate (Negative mode) 'kite' 'truck' 'carrot' 'baseball glove' 'tennis racket' 'remote' 'cat' 'tie' 'horse' 'boat'

Citation

@misc{benbaruch2021multilabel,
      title={Multi-label Classification with Partial Annotations using Class-aware Selective Loss}, 
      author={Emanuel Ben-Baruch and Tal Ridnik and Itamar Friedman and Avi Ben-Cohen and Nadav Zamir and Asaf Noy and Lihi Zelnik-Manor},
      year={2021},
      eprint={2110.10955},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Acknowledgements

Several images from OpenImages dataset are used in this project. ֿ
Some components of this code implementation are adapted from the repository https://github.com/Alibaba-MIIL/ASL.

The tl;dr on a few notable transformer/language model papers + other papers (alignment, memorization, etc).

The tl;dr on a few notable transformer/language model papers + other papers (alignment, memorization, etc).

Will Thompson 166 Jan 04, 2023
The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"

The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"

Sun Yi 201 Nov 21, 2022
UT-Sarulab MOS prediction system using SSL models

UTMOS: UTokyo-SaruLab MOS Prediction System Official implementation of "UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022" submitted to INTERSP

sarulab-speech 58 Nov 22, 2022
Train CNNs for the fruits360 data set in NTOU CS「Machine Vision」class.

CNNs fruits360 Train CNNs for the fruits360 data set in NTOU CS「Machine Vision」class. CNN on a pretrained model Build a CNN on a pretrained model, Res

Ricky Chuang 1 Mar 07, 2022
My 1st place solution at Kaggle Hotel-ID 2021

1st place solution at Kaggle Hotel-ID My 1st place solution at Kaggle Hotel-ID to Combat Human Trafficking 2021. https://www.kaggle.com/c/hotel-id-202

Kohei Ozaki 18 Aug 19, 2022
Pytorch implementations of the paper Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients

LSF-SAC Pytorch implementations of the paper Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy G

Hanhan 2 Aug 14, 2022
PyTorch implementation of spectral graph ConvNets, NIPS’16

Graph ConvNets in PyTorch October 15, 2017 Xavier Bresson http://www.ntu.edu.sg/home/xbresson https://github.com/xbresson https://twitter.com/xbresson

Xavier Bresson 287 Jan 04, 2023
Simple STAC Catalogs discovery tool.

STAC Catalog Discovery Simple STAC discovery tool. Just paste the STAC Catalog link and press Enter. Details STAC Discovery tool enables discovering d

Mykola Kozyr 21 Oct 19, 2022
.NET bindings for the Pytorch engine

TorchSharp TorchSharp is a .NET library that provides access to the library that powers PyTorch. It is a work in progress, but already provides a .NET

Matteo Interlandi 17 Aug 30, 2021
[ICCV 2021 Oral] Just Ask: Learning to Answer Questions from Millions of Narrated Videos

Just Ask: Learning to Answer Questions from Millions of Narrated Videos Webpage • Demo • Paper This repository provides the code for our paper, includ

Antoine Yang 87 Jan 05, 2023
NeurIPS 2021, self-supervised 6D pose on category level

SE(3)-eSCOPE video | paper | website Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimation Xiaolong Li, Yijia Weng,

Xiaolong 63 Nov 22, 2022
Improving Query Representations for DenseRetrieval with Pseudo Relevance Feedback:A Reproducibility Study.

APR The repo for the paper Improving Query Representations for DenseRetrieval with Pseudo Relevance Feedback:A Reproducibility Study. Environment setu

ielab 8 Nov 26, 2022
We simulate traveling back in time with a modern camera to rephotograph famous historical subjects.

[SIGGRAPH Asia 2021] Time-Travel Rephotography [Project Website] Many historical people were only ever captured by old, faded, black and white photos,

298 Jan 02, 2023
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

Annoy Annoy (Approximate Nearest Neighbors Oh Yeah) is a C++ library with Python bindings to search for points in space that are close to a given quer

Spotify 10.6k Jan 04, 2023
This is the source code of the 1st place solution for segmentation task (with Dice 90.32%) in 2021 CCF BDCI challenge.

1st place solution in CCF BDCI 2021 ULSEG challenge This is the source code of the 1st place solution for ultrasound image angioma segmentation task (

Chenxu Peng 30 Nov 22, 2022
Official PyTorch Implementation of Rank & Sort Loss [ICCV2021]

Rank & Sort Loss for Object Detection and Instance Segmentation The official implementation of Rank & Sort Loss. Our implementation is based on mmdete

Kemal Oksuz 229 Dec 20, 2022
A 3D sparse LBM solver implemented using Taichi

taichi_LBM3D Background Taichi_LBM3D is a 3D lattice Boltzmann solver with Multi-Relaxation-Time collision scheme and sparse storage structure impleme

Jianhui Yang 121 Jan 06, 2023
Directed Greybox Fuzzing with AFL

AFLGo: Directed Greybox Fuzzing AFLGo is an extension of American Fuzzy Lop (AFL). Given a set of target locations (e.g., folder/file.c:582), AFLGo ge

380 Nov 24, 2022
PyTorch implementation for our AAAI 2022 Paper "Graph-wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning"

deepGCFX PyTorch implementation for our AAAI 2022 Paper "Graph-wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning" Pr

Thilini Cooray 4 Aug 11, 2022
A PyTorch implementation of Radio Transformer Networks from the paper "An Introduction to Deep Learning for the Physical Layer".

An Introduction to Deep Learning for the Physical Layer An usable PyTorch implementation of the noisy autoencoder infrastructure in the paper "An Intr

Gram.AI 120 Nov 21, 2022