Update README.md

## Problem definition

The convention standard for object detection uses a bounding box to represent each individual object instance. 

However, it is not practical in the industry-relevant applications in the context of warehouses due to severe occlusions among groups of instances of the same categories.

For example, as shown in [Fig. 1(g)](https://isrc.iscas.ac.cn/gitlab/research/locount-dataset/-/tree/master/Images/dataset-comparison.jpg), it is extremely difficult to annotate the stacked dinner plates even by a well-trained annotator. 

For example, as shown in Fig. 1(g), it is extremely difficult to annotate the stacked dinner plates even by a well-trained annotator. 

Meanwhile, it is almost impossible for object detectors to detect all stacked dinner plates accurately, even for the state-of-the-art detectors.

Thus, it is necessary to rethink the definition of object detection in such scenarios.

More than 1.9 million object instances in 140 categories (including *Jacket*, *Shoes*, *Oven*, etc.) are annotated. 

![Table 1: Summary of existing object detection benchmarks in retail stores. “C” indicates the image classification task, “S”

indicates the single-class object detection task, and “M” indicates the multi-class object detection task.](https://isrc.iscas.ac.cn/gitlab/research/locount-dataset/-/tree/master/Images/dataset-summary.png)

indicates the single-class object detection task, and “M” indicates the multi-class object detection task.](Images/dataset-summary.png)

To facilitate data usage, we divide the dataset into two subsets, i.e., *training* and *testing* sets, including 34,022 images for training and 16,372 images for testing.

The dataset includes 9 big subclasses, i.e., Baby Stuffs (e.g., *Baby Diapers* and *Baby Slippers*), Drinks (e.g., *Juice* and *Ginger Tea*), Food Stuff (e.g., *Dried Fish* and *Cake*), Daily Chemicals (e.g., *Soap* and *Shampoo*), Clothing (e.g., *Jacket* and *Adult hats*), 

The counting accuracy threshold for the positive/negative sample generation is determined by the architecture design of CLCNet, which is described as follows.

![Figure 3: The architecture of our CLCNet for the Locount task. The cubes indicate the output feature maps from the convolutional layers or RoIAlign operation.

The numbers in the brackets indicate the range of counting number in each stage.](https://isrc.iscas.ac.cn/gitlab/research/locount-dataset/-/blob/master/Images/framework.png)

The numbers in the brackets indicate the range of counting number in each stage.](Images/framework.png)

We use the same architecture and configuration as Cascade R-CNN for the box-regression and box-classification layers. For the instance counting layer, 

a direct strategy is to use a FC layer to regress a floating point number, indicating the number of instances, called *count-regression strategy*. 

We conduct several experiments of the state-of-the-art object detectors and the proposed CLCNet method on the proposed dataset, to demonstrate the effectiveness of CLCNet, Table 2 and Fig. 4.

![Table 2: Comparison results of the algorithms on the proposed dataset. Detection results of all comparison methods on the

proposed dataset. The mark lc on the upper right corner indicates that its value is computed by the proposed metrics](https://isrc.iscas.ac.cn/gitlab/research/locount-dataset/-/blob/master/Images/Experiment-results.png)

proposed dataset. The mark lc on the upper right corner indicates that its value is computed by the proposed metrics](Images/Experiment-results.png)

![Figure 4: Qualitative results of the proposed CLCNet method on the Locount dataset.](https://isrc.iscas.ac.cn/gitlab/research/locount-dataset/-/blob/master/Images/show-results.jpg)

![Figure 4: Qualitative results of the proposed CLCNet method on the Locount dataset.](Images/show-results.jpg)

## Citation

If you find this dataset useful for your research, please cite