Task Programming: Learning Data Efficient Behavior Representations

• URL: http://arxiv.org/abs/2011.13917v2
• Date: Mon, 29 Mar 2021 17:59:47 GMT
• Title: Task Programming: Learning Data Efficient Behavior Representations
• Authors: Jennifer J. Sun, Ann Kennedy, Eric Zhan, David J. Anderson, Yisong Yue, Pietro Perona
• Abstract summary: We present TREBA: a method to learn annotation-sample efficient trajectory embedding for behavior analysis. The tasks in our method can be efficiently engineered by domain experts through a process we call "task programming" We present experimental results in three datasets across two domains: mice and fruit flies.
• Score: 44.244695150594815
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Specialized domain knowledge is often necessary to accurately annotate training sets for in-depth analysis, but can be burdensome and time-consuming to acquire from domain experts. This issue arises prominently in automated behavior analysis, in which agent movements or actions of interest are detected from video tracking data. To reduce annotation effort, we present TREBA: a method to learn annotation-sample efficient trajectory embedding for behavior analysis, based on multi-task self-supervised learning. The tasks in our method can be efficiently engineered by domain experts through a process we call "task programming", which uses programs to explicitly encode structured knowledge from domain experts. Total domain expert effort can be reduced by exchanging data annotation time for the construction of a small number of programmed tasks. We evaluate this trade-off using data from behavioral neuroscience, in which specialized domain knowledge is used to identify behaviors. We present experimental results in three datasets across two domains: mice and fruit flies. Using embeddings from TREBA, we reduce annotation burden by up to a factor of 10 without compromising accuracy compared to state-of-the-art features. Our results thus suggest that task programming and self-supervision can be an effective way to reduce annotation effort for domain experts.

Related papers

• Geospatial Trajectory Generation via Efficient Abduction: Deployment for Independent Testing [1.8877926393541125]
  We show that we can abduce movement trajectories efficiently through an informed (i.e., A*) search. We also report on our own experiments showing that we not only provide exact results but also scale to very large scenarios.
  arXiv  Detail & Related papers  (2024-07-08T23:11:47Z)
• Prompt-Based Spatio-Temporal Graph Transfer Learning [22.855189872649376]
  We propose a prompt-based framework capable of adapting to multi-diverse tasks in a data-scarce domain. We employ learnable prompts to achieve domain and task transfer in a two-stage pipeline. Our experiments demonstrate that STGP outperforms state-of-the-art baselines in three tasks-forecasting, kriging, and extrapolation-achieving an improvement of up to 10.7%.
  arXiv  Detail & Related papers  (2024-05-21T02:06:40Z)
• Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning [85.66907881270785]
  We propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training. In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk. In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training.
  arXiv  Detail & Related papers  (2024-01-07T18:12:20Z)
• Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding [52.723297744257536]
  Pre-trained language models (LMs) have shown effectiveness in scientific literature understanding tasks. We propose a multi-task contrastive learning framework, SciMult, to facilitate common knowledge sharing across different literature understanding tasks.
  arXiv  Detail & Related papers  (2023-05-23T16:47:22Z)
• Knowledge Combination to Learn Rotated Detection Without Rotated Annotation [53.439096583978504]
  Rotated bounding boxes drastically reduce output ambiguity of elongated objects. Despite the effectiveness, rotated detectors are not widely employed. We propose a framework that allows the model to predict precise rotated boxes.
  arXiv  Detail & Related papers  (2023-04-05T03:07:36Z)
• Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks [8.320969283401233]
  We show that the standard, naive approach to exploration can manifest as a suboptimal local maximum. We present Learning from Guided Play (LfGP), a framework in which we leverage expert demonstrations of multiple exploratory, auxiliary tasks.
  arXiv  Detail & Related papers  (2022-12-30T20:38:54Z)
• I Know Therefore I Score: Label-Free Crafting of Scoring Functions using Constraints Based on Domain Expertise [6.26476800426345]
  We introduce a label-free practical approach to learn a scoring function from multi-dimensional numerical data. The approach incorporates insights and business rules from domain experts in the form of easily observable and specifiable constraints. We convert such constraints into loss functions that are optimized simultaneously while learning the scoring function.
  arXiv  Detail & Related papers  (2022-03-18T17:51:20Z)
• Streaming Self-Training via Domain-Agnostic Unlabeled Images [62.57647373581592]
  We present streaming self-training (SST) that aims to democratize the process of learning visual recognition models. Key to SST are two crucial observations: (1) domain-agnostic unlabeled images enable us to learn better models with a few labeled examples without any additional knowledge or supervision; and (2) learning is a continuous process and can be done by constructing a schedule of learning updates.
  arXiv  Detail & Related papers  (2021-04-07T17:58:39Z)
• Adversarial Imitation Learning with Trajectorial Augmentation and Correction [61.924411952657756]
  We introduce a novel augmentation method which preserves the success of the augmented trajectories. We develop an adversarial data augmented imitation architecture to train an imitation agent using synthetic experts. Experiments show that our data augmentation strategy can improve accuracy and convergence time of adversarial imitation.
  arXiv  Detail & Related papers  (2021-03-25T14:49:32Z)
• Domain-Robust Visual Imitation Learning with Mutual Information Constraints [0.0]
  We introduce a new algorithm called Disentangling Generative Adversarial Imitation Learning (DisentanGAIL) Our algorithm enables autonomous agents to learn directly from high dimensional observations of an expert performing a task.
  arXiv  Detail & Related papers  (2021-03-08T21:18:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.