Multiple Instance Filtering
We propose a robust filtering approach based on semi-supervised and multiple instance learning (MIL). We assume that the posterior density would be unimodal if not for the effect of outliers that we do not wish to explicitly model. Therefore, we seek for a point estimate at the outset, rather than a generic approximation of the entire posterior. Our approach can be thought of as a combination of standard finite-dimensional filtering (Extended Kalman Filter, or Unscented Filter) with multiple instance learning, whereby the initial condition comes with a putative set of inlier measurements. We show how both the state (regression) and the inlier set (classification) can be estimated iteratively and causally by processing only the current measurement. We illustrate our approach on visual tracking problems whereby the object of interest (target) moves and evolves as a result of occlusions and deformations, and partial knowledge of the target is given in the form of a bounding box (training set).
Code (0)
등록된 구현이 없습니다.
Tasks
Multiple Instance LearningVisual TrackingSimilar Papers 제목 키워드 기반
An Extensive Evaluation of Filtering Misclassified Instances in Supervised Classification Tasks
Removing or filtering outliers and mislabeled instances prior to training a learning algorithm has been shown to increase classification accuracy. A popular approach for handling outliers and mislabeled instances is to r…
General ClassificationEfficient Evaluation of Large Language Models via Collaborative Filtering
With the development of Large Language Models (LLMs), numerous benchmarks have been proposed to measure and compare the capabilities of different LLMs. However, evaluating LLMs is costly due to the large number of test i…
Collaborative FilteringRecommendation SystemsA Comparative Evaluation of Curriculum Learning with Filtering and Boosting
Not all instances in a data set are equally beneficial for inferring a model of the data. Some instances (such as outliers) are detrimental to inferring a model of the data. Several machine learning techniques treat inst…
General ClassificationInstanceFlow: Visualizing the Evolution of Classifier Confusion on the Instance Level
Classification is one of the most important supervised machine learning tasks. During the training of a classification model, the training instances are fed to the model multiple times (during multiple epochs) in order t…
ClassificationGeneral ClassificationLearnable Instance Attention Filtering for Adaptive Detector Distillation
As deep vision models grow increasingly complex to achieve higher performance, deployment efficiency has become a critical concern. Knowledge distillation (KD) mitigates this issue by transferring knowledge from large te…
Knowledge Distillation