Benchmark for Generic Product Detection: A Low Data Baseline for Dense Object Detection

@inproceedings{Varadarajan2019BenchmarkFG,
  title={Benchmark for Generic Product Detection: A Low Data Baseline for Dense Object Detection},
  author={Srikrishna Varadarajan and Sonaal Kant and Muktabh Mayank Srivastava},
  booktitle={International Conference on Image Analysis and Recognition},
  year={2019}
}
Object detection in densely packed scenes is a new area where standard object detectors fail to train well. Dense object detectors like RetinaNet trained on large and dense datasets show great performance. We train a standard object detector on a small, normally packed dataset with data augmentation techniques. This dataset is 265 times smaller than the standard dataset, in terms of number of annotations. This low data baseline achieves satisfactory results (mAP=0.56) at standard IoU of 0.5. We… 

Learning Gaussian Maps for Dense Object Detection

It is shown that, multi-task learning of gaussian maps along with classification and bounding box regression gives us a significant boost in accuracy over the baseline, and this method achieves the state of the art accuracy on the SKU110K dataset.

Semi-supervised Learning for Dense Object Detection in Retail Scenes

This work adapts a popular self supervised method called noisy student initially proposed for object classification to the task of dense object detection and shows that using unlabeled data with the noisy student training methodology can improve the state of the art on precise detection of objects in densely packed retail scenes.

Bag of Tricks for Retail Product Image Classification

A new neural network layer called Local-Concepts-Accumulation (LCA) layer is introduced which gives consistent gains across multiple datasets and enables us to increase the accuracy of fine tuned convnets for retail product image classification by a large margin.

Image Analysis and Recognition: 17th International Conference, ICIAR 2020, Póvoa de Varzim, Portugal, June 24–26, 2020, Proceedings, Part I

A method for workout repetition counting and validation based on a set of skeleton-based and deep semantic features that are obtained from a 2D human pose estimation network that is able to count valid repetitions with over 90% precision scores for 4 out of 5 considered exercises.

Machine Learning approaches to do size based reasoning on Retail Shelf objects to classify product variants

This work proposes methods to ascertain the size variant of the product as a downstream task to an object detector which extracts products from shelf and a classifier which determines product brand.

Designing an Efficient End-to-end Machine Learning Pipeline for Real-time Empty-shelf Detection

This work presents an elegant approach for designing an end-to-end machine learning (ML) pipeline for real-time empty shelf detection, and focuses on the importance of proper data collection, cleaning and correct data annotation before delving into modeling.

Linking physical objects to their digital twins via fiducial markers designed for invisibility to humans

This paper proposes to link digital assets created through building information modeling (BIM) with their physical counterparts using fiducial markers with patterns defined by cholesteric spherical reflectors (CSRs), selective retroreflectors produced using liquid crystal self-assembly.

Machine Learning based Automated Product Billing and Inventory

Due to the COVID-19 pandemic restrictions were imposed to stop the spread of the virus. As a result, the shopping malls, retail stores and grocery stores had to be shut down leading to significant

References

SHOWING 1-10 OF 17 REFERENCES

Precise Detection in Densely Packed Scenes

This work proposes a novel, deep-learning based method for precise object detection, designed for such challenging settings as packed retail environments, and shows the method to outperform existing state-of-the-art with substantial margins.

Microsoft COCO: Common Objects in Context

We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene

Recognizing Products: A Per-exemplar Multi-label Image Classification Approach

This paper presents an efficient approach for per-exemplar multi-label image classification, which targets the recognition and localization of products in retail store images, and provides a large novel dataset and labeling tools for products image search.

MVTec D2S: Densely Segmented Supermarket Dataset

We introduce the Densely Segmented Supermarket (D2S) dataset, a novel benchmark for instance-aware semantic segmentation in an industrial domain. It contains 21,000 high-resolution images with

An Analysis of Scale Invariance in Object Detection - SNIP

  • Bharat SinghL. Davis
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
A novel training scheme called Scale Normalization for Image Pyramids (SNIP) is presented which selectively back-propagates the gradients of object instances of different sizes as a function of the image scale.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.

Towards Identification of Packaged Products via Computer Vision: Convolutional Neural Networks for Object Detection and Image Classification in Retail Environments

It is demonstrated that even in realistic, fast-paced retail environments, image-based product identification provides an alternative to barcodes, especially for use-cases that do not require perfect 100% accuracy.

Fine-Grained Grocery Product Recognition by One-Shot Learning

A novel hybrid classification approach that combines feature-based matching and one-shot deep learning with a coarse-to-fine strategy to improve the accuracy of fine-grained grocery products recognition effectively is presented.

Albumentations: fast and flexible image augmentations

Albumentations is presented, a fast and flexible open source library for image augmentation with many various image transform operations available that is also an easy-to-use wrapper around other augmentation libraries.

Incremental Learning of Object Detectors without Catastrophic Forgetting

This work presents a method to learn object detectors incrementally, when neither the original training data nor annotations for the original classes in the new training set are available, and presents object detection results on the PASCAL VOC 2007 and COCO datasets.