Roadmap

Afraid your computer vision project will turn into an endless stream of failed experiments?

Are you unsure whether you’re focusing on the best model types for your application?
Or whether you’re overcomplicating the algorithm?
Do you have data challenges like noisy labels or small training sets?
Do you need to build credibility with your investors?

Get to market faster with less wasted time on unsuccessful approaches

Follow best practices for your unique challenges
Focus on clear priorities for your team
Understand and communicate technical details to investors and end users

Get a comprehensive roadmap incorporating best practices for your imagery

Results:

Increased clarity on the scope of work
Decreased uncertainty for the implementation phase that follows
Decreased likelihood of going in circles or wasting time on unsuccessful approaches
Confidence that you’re incorporating the latest and greatest tools and techniques
Save time and money by identifying existing toolkits instead of implementing from scratch
Increased likelihood of success

Option 1: Roadmap Complete $18,000

Get a complete roadmap in less than one month

Using my proven process, I’ll assess your planned project. I’ll focus on your current datasets, target task, and desired outcomes. I’ll outline my findings in a report that will provide a strategic plan for advancing your computer vision project and ensuring that it can support your goals.

You’ll start by filling out a questionnaire with some background information about your project. We’ll dive deeper into this in our kickoff meeting, examining the desired outcomes for your project and availability of data.

By our second meeting, I’ll have some possible solutions to present to you. We’ll talk through which will be most suitable for your application. Subsequent meetings will refine the strategy for data and annotation requirements, model development, and validation until we’ve settled on the best option for you. We’ll review the roadmap in our final session.

A six week check-in call is also included in case you have any follow up questions as your team begins implementing the roadmap.

You will receive a strategic roadmap detailing each of the components below:

Images and annotations: challenges, preprocessing, and cleaning requirements

Expectations from existing tools and research: software and research literature review

Modeling: architecture and training

Validation: metrics, generalizability, and error analysis

Option 2: Roadmap Guide $6,000

Two months of asynchronous feedback as your team develops your roadmap

Does your team already have a general project plan but need guidance on fleshing it out?

Share a Google Doc with your in-progress roadmap and I’ll provide on-going feedback as your team continues to fill in the gaps.

Option 3: Roadmap Teardown – One Time $2,000

Question your assumptions and poke holes in your plan – a one-time roadmap review

Share a Google Doc with your computer vision modeling roadmap and I’ll provide questions and comments on any weak areas that I see.

Have you identified all the challenges in your data?

Was your literature search thorough enough?

Will the metrics you’ve selected accurately assess the successes and failures of your model?

Identifying these and other obstacles before you begin development will save you so much time down the road.

Ready to get started?

Are you ready to set your project on the path to success? Apply for a computer vision modeling Roadmap by clicking the button below.

Apply Now

Don’t just take my word for it…

Heather has accelerated the development of our machine learning projects by challenging the status quo and introducing the team to new approaches. She helped us get out of the echo chamber and brought an outside perspective with very relevant alternative approaches that would have taken a lot longer to do on our own.

-- Joe Sturonas, Ancera, VP of Systems Development

Pixel Scientia provides valuable insights for Gestalt's image analysis product development. Heather has deep understanding of digital pathology and machine learning and their application to whole slide images. Her in-depth review of the current state of the art research has enabled Gestalt to rapidly focus our machine learning efforts on approaches that are yielding value for our pathologists and their patients.

-- Brian Napora, Gestalt Diagnostics, VP of Sales & Product Management

The roadmap we worked on together is very well written with clear descriptions regarding the tasks we wanted to tackle, the algorithms that could be applied to each one of the tasks, and the data/annotation requirements.

-- Ebrahim Hazrati, Agendia, Senior Deep Learning Engineer

Still have questions?

What happens after I apply?

I’ll schedule a short call to confirm that this package is suitable for your project. Then I’ll send over a short contract. Once you submit your payment, you’ll receive an email with a link to a questionnaire. At the end of the questionnaire you’ll be able to schedule our kickoff.

Will you sign an NDA before we start?

The contract for this Modeling Roadmap will include confidentiality and non-disclosure provisions.

We already have a great ML team. Why do we need you?"

Maybe you don’t need me. If your team is spending most of their time keeping up with the state-of-the-art and can outline a clear roadmap, you might not.

But if your team is spending most of their time training models, that’s where I come in. It is my job to stay at the forefront of the field, specifically at the intersection of machine learning and computer vision. Through literature reviews and observations across multiple projects, I develop best practices for applying ML to pathology and remote sensing images and tactics for adapting new advances.

You and your team know your data and specific application better than I ever will. In developing the Modeling Roadmap, I build upon your team’s expertise and combine it with my knowledge of the field to get you on the path to a successful ML solution.

Our project is different from other applications. Is this a problem?

No. All projects in this space are different. This is why I focus specifically on pathology and remote sensing so that I can dig into research that’s relevant to the field. I will be sure to assess the closest related publications. There may be some differences between these and your application, but it is essential for setting expectations for your project.

We’ve already started implementing a solution, do we still need a roadmap?

A roadmap likely isn’t the best choice since you’ve already started your project. But if you find yourself in a jam, you might look into my Diagnostic services.

Some challenges don’t arise until later on in a project. Like discovering that your model doesn’t generalize to images from a different scanner or lab. Or analyzing your results for potential biases. These are great reasons to seek advice on a project that’s already in progress but are best-suited to a different offering.

What’s next after the roadmap? Can you help us with implementation?

After completing this roadmap, we have a few options. Your team could go off and implement the algorithms outlined independently. However, my clients have found that their projects are completed more efficiently with continuous guidance. You can sign up for my monthly Advisory service and receive advice as your team handles the implementation.

Still not sure if this is the right package for you?

Schedule a free Discovery Call, and I’ll help you determine if this is a good fit.