{
  "docId": "019dd923-5e88-73ef-bd5c-f812573a947a",
  "docSlug": "eea7524c557036f4",
  "documentTitle": "2020 Air Street Capital The State of AI Report 2020",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 48,
  "pageCount": 177,
  "prevPage": 47,
  "nextPage": 49,
  "slideType": "industry_trends",
  "function": "present_solution",
  "density": "balanced",
  "nDataPoints": 0,
  "notes": "The slide highlights the shift from traditional CNN-based architectures like Faster R-CNN to transformer-based approaches in computer vision.",
  "elementsJson": [
    "bullet_list",
    "process_diagram",
    "photo"
  ],
  "metadataConfidence": 0.95,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-f812573a947a/48",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a#slide-48",
  "components": [
    {
      "bbox": {
        "h": 0.08,
        "w": 0.9,
        "x": 0.05,
        "y": 0.22
      },
      "kind": "callout",
      "text": "A transformer-based object detection model matches the performance of the best object detection models while removing hand-coded prior knowledge and using half the compute budget.",
      "attrs": null,
      "subkind": "primary",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "2a7e432f-55d1-4046-952c-40b4f1348b19",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.4,
        "x": 0.55,
        "y": 0.52
      },
      "kind": "image",
      "text": "Visual examples of object detection and segmentation outputs.",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "a3a445a8-b04d-44af-be33-5f81c6f82bde",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.4,
        "x": 0.55,
        "y": 0.35
      },
      "kind": "image",
      "text": "DETR architecture diagram showing CNN, transformer encoder-decoder, and bipartite matching loss.",
      "attrs": null,
      "subkind": "infographic",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "158d2943-cf62-45a9-afe6-603e3a032a3b",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.5,
        "w": 0.45,
        "x": 0.05,
        "y": 0.32
      },
      "kind": "list",
      "text": "Popular models like Faster R-CNN require various means of hand-encoding prior knowledge into the architecture in order to make predictions relative to some initial guesses. A new framework, DEtection TRansformer (DETR), uses 2D images features from a CNN, flattens them into a sequence, and uses transformers to model pairwise interactions between the features. DETR is trained end-to-end with a loss function that matches predicted and ground-truth objects. The model is simpler because it drops multiple hand-designed priors and its attention decoder helps with interpretability.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "55cc2207-b900-4bd0-b16e-2737b91b3518",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.7,
        "x": 0.05,
        "y": 0.13
      },
      "kind": "title",
      "text": "Attention turns to computer vision tasks like object detection and segmentation",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "9d762031-4875-44fa-bdb1-a89c96390d59",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-0fd5-7148-8ece-e758c599d693",
      "evidence": "Title: attention turning to vision tasks.",
      "confidence": 80
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 129,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e34-ed2a8f38a754",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Research, Talent, Industry sections inventory what happened in AI in 2020.",
      "position": 1,
      "confidence": 60,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 129,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e34-fc384f439bba",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Research, Talent and Industry sections build momentum of AI progress.",
      "position": 2,
      "confidence": 40,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 57,
      "from": 47,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3c-f820616b6fcc",
      "evidence": "Wimbledon synth video, object detection, depth, AutoML-Zero examples in sequence.",
      "position": 5,
      "objective": "Catalog computer vision and generative model advances",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 70,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}