Would having surface normals simplify the depth estimation of an image? Do visual tasks have a relationship, or are they unrelated? Common sense suggests that visual tasks are interdependent, implying the existence of structure among tasks. However, a proper model is needed for the structure to be actionable, e.g., to reduce the supervision required by utilizing task relationships. We therefore ask: which tasks transfer to an arbitrary target task, and how well? Or, how do we learn a set of tasks collectively, with less total supervision?
These are some of the questions that can be answered by a computational model of the vision tasks space, as proposed in this paper. We explore the task structure utilizing a sampled dictionary of 2D, 2.5D, 3D, and semantic tasks, and modeling their (1st and higher order) transfer behaviors in a latent space. The product can be viewed as a computational task taxonomy (Taskonomy) and a map of the task space. We study the consequences of this structure, e.g., the emerging task relationships, and exploit them to reduce supervision demand. For instance, we show that the total number of labeled datapoints needed to solve a set of 10 tasks can be reduced to 1/4 while keeping performance nearly the same by using features from multiple proxy tasks. Users can employ a provided Binary Integer Programming solver that leverages the taxonomy to find efficient supervision policies for their own use cases.
Process overview. The steps involved in creating the taxonomy.
The provided API uses our results to recommend a superior set of transfers. By using these transfers, we can get similar results close to a fully supervised network using substantially less data.
Example taxonomies. Generated from the API.
In order to evaluate the quality of the learned transfer functions, we ran the transfer networks on a random youtube video. Visit the Transfer Visualization page to analyze how well different sources transfer to a target, or how well a source transfers to different targets. Compare this to the task-specific networks as well as to baselines trained on ImageNet or trained on the same data as the transfer networks, but without transfer learning.
We provide a large and high-quality dataset of varied indoor scenes.
Complete pixel-level geometric information via aligned meshes.
Globally consistent camera poses. Complete camera intrinsics.
3x times big as ImageNet.
* If you are interested in using the full dataset (12 TB), then please contact the authors.
Zamir, Sax*, Shen*, Guibas, Malik, Savarese.
Taskonomy: Disentangling Task Transfer Learning.
Please cite the paper if you use the method, models, database, or API.