Changelog

Update 2020-09-07

Changes:

  • Various performance improvements
  • Minor changes in the UI

Release of New Version 2020-08-17

View press release

Added free features:

  • Functionality to download offline models (30-day trial)
  • Possibility to use a pre-trained object detection model

Added paid features:

  • Paid licenses for offline models
  • Functionality to train object detection models
  • Possibility to share projects
  • Possibility to track labeling time of all users in a project
  • Functionality to filter images by people who have labeled or reviewed those images
  • Functionality to edit user roles and permissions
  • Possibility to have a dedicated image similarity search service

Update 2020-07-08

Added:

  • Possibility to upload color bitmaps (one bitmap per image)
  • Possibility to download/upload black and white bitmaps (one bitmap per object)
  • A color picker for object labels

Changed:

  • When a new object label is selected or created on canvas, the object list automatically scrolls to that object
  • Large file downloads are now prepared in the background
  • Added option to change brush size in the smart labeling tool
  • Brush preview is always displayed, even while drawing an object

Update 2020-06-09

Added:

  • Smart labeling tool for segmentation. Using this smart labeling tool users can quickly label images for segmentation by marking foreground and background in a selected area.
  • Functionality to convert bitmaps to polygons
  • Labeling time reporting. Users can now track how much time they have spent labeling day by day using our platform.
  • Download manager. Users can see their previous downloads and re-download them if necessary.
  • Possibility to label images in image similarity search result screen
  • Possibility to delete a specific label from all selected images at once
  • Possibility to delete all labels from all selected images at once
  • Possibility to hide all labeling objects

Changed

  • Now after labeling image for classification or exiting from labeling screen, the page is not reloaded, so users stay on the same page as they were before
  • Using pre-trained models does not require to specify project ID anymore

Update 2020-05-04

Added:

  • Three new pre-trained models that are ready-to-use without any additional training:
    • General classification – this model tells what is seen inside an image in general
    • Places recognition – this model tries to recognize the place where picture was taken
    • NSFW classification – this model can be used for content moderation purposes to filter out any images that contain nudity
  • Labeled objects now can have “attributes”. These attributes can be used to further describe the object. For example, object “table” can have attributes such as “white”, “round”, “four legs”, etc.
  • Images now have “seen” or “unseen” status. If a user opens an image for labeling, its status is automatically set as “seen”. In addition user can mark specific images as “seen” or “unseen” by simply selecting them and using right click context menu. Later the user can filter images that he has seen or not seen. This feature was implemented to help to track the labeling progress.

Changed:

  • Some minor changes image labeling interface (sorting labels newest-oldest, possibility to have empty label name field by default, etc.)

Update 2020-03-30

Added:

  • A completely redesigned labeling tool that includes bounding box, polygon, polyline, points and bitmap labeling using a brush tool
  • Functionality to mark keypoints for bounding box and polygon objects
  • Possibility to save keypoints template that includes names of the keypoints
  • Functionality to convert bounding boxes and polygons to bitmap (“rasterize”)
  • Possibility to see label names next to objects
  • Possibility to change the order of object list by dragging them
  • Possibility to select which type labels are downloaded
  • Possibility to filter images based on labels that are of other type than classification (such as polygons, bounding boxes, points and others)

Changed:

  • Now object detection and segmentation labeling are done within the same window
  • Some of the fields in the downloaded .json file with labels have changed. For some time we will support both the old and the new formats

Removed:

  • Fixed vertex count setting for polygon labeling
  • Continous polygon drawing mode
  • Full screen mode

Update 2020-01-27

Added:

  • Object name is shown next to the bounding box or polygon
  • Image labels are now downloaded as a .zip file and works faster
  • Now we report both label-wise and image-wise accuracy in multi-label classification
  • Possibility to upload classification labels from .json file (rather than .csv)
  • Possibility to rotate image counter-clockwise

Update 2019-11-20

Added:

  • Possibility to download image similarity search results
  • Improved object detection/segmentation labeling interface:
    • Bounding boxes and polygons that are being edited are highlighted in an image and in the list on the right panel
    • Active vertices are highlighted
    • A new vertex which is about to be added on an edge is visualized
    • After finishing labeling a bouding box or a polygon its name field is automatically activated
    • Occluded objects are marked by a dashed line
    • New shortcuts for labeling ('O' - mark object as occluded, 'V' turn on/off visibility of an object)
  • Added a search field by image filename
  • A new button to select all images in the current page
  • Five new video tutorials (training a model on one class, image similarity search, labeling images for object detection, labeling images for segmentation, labeling settings)

Changed:

  • Removed “Move” and “Edit” modes in image labeling (everything is done in a single mode now)
  • Restructured image similarity search results window
  • Slightly changed REST api output format
  • User projects with duplicated names were renamed
  • Download labels function now downloads classification labels in .csv file in addition to all types of labels in .json file
  • When a user exits labeling, the current page stays where the last image was and the last image is highlighted

Update 2019-09-20

Added:

  • New shortcuts for labeling ('Z' to fit image to screen, 'Ctrl or Shift + mouse wheel' to scroll image left/right or up/down)

Changed:

  • A minimum value of optimized score threshold for multi-label classification is now 5%
  • Downloaded image labels for object detection, segmentation and classification are now all in one .json file
  • Reordered context menu of right mouse button

Update 2019-08-30

Added:

  • Functionality to perform image similarity search via web interface and REST api
  • Possibility to see how many images will be allocated to train and validation sets
  • Functionality to rotate image
  • Functionality to sort images by name or upload time
  • Possibility to select images from several different pages
  • New shortcuts: press ctrl+1, ctrl+2, etc. to select object label
  • New shortcut: delete images with [delete] key
  • Possibility to pre-process images for classification and similarity search during image upload

Changed:

  • Restructured project selection and editing menu
  • Removed boundary groups from object detection labeling (now each bounding box is stand-alone)

Update 2019-06-26

Added:

  • Functionality to upload object detection and segmentation labels from a .json file
  • Functionality to select and move polygons by mouse click during labeling
  • Full screen mode for image labeling
  • Icons to mark images labeled for object detection and segmentation
  • Possibility to exclude labels from training in the training screen
  • Possibility for changing line width for labeling
  • Functionality to filter images by labels using “and” and “or” filters
  • Functionality to upload images by selecting a whole folder

Changed:

  • Removed “save” button from settings menu (now settings are saved automatically)
  • Now images in “show predictions” screen are shown in original aspect ratio
  • Restructured upper menu

Updates 2018-11-18 – 2019-06-26

Added:

  • Possibility to upload classification labels as a .csv file
  • Possibility to download classification predictions as a .csv file, .json file or images grouped into folders by predicted labeling
  • Download object detection and segmentation labels as a .json file
  • Upload images as a .zip file with a possibility to label them based on folder structure
  • Possibility to select which exact images will be used for validation
  • Possibility to set “default” label on all selected images
  • Possibility to have a fixed bounding box ratio
  • Possibility to have a fixed number of points in a polygon
  • Possibility to skip images that are already labeled
  • Possibility to switch between images using arrows or “A” and “D” shortcuts

Changed:

  • Labels without the minimum required number of images are automatically excluded from training
  • Improved bounding box and segmentation labeling tools

SentiSight.ai first release 2018-11-18

View press release

Added:

  • Functionality to train single-label and multi-label classification models
  • Functionality to label images for classification, object detection and segmentation
  • Functionality to view predictions on train and validation sets and analyze model’s performance
  • Functionality to filter images by type and labels
  • REST api service