Retrieving images with objects that are semantically similar to objects of interest (OOI) in a query image has many practical use cases. A few examples include fixing failures like false negatives/positives of a learned model or mitigating class imbalance in a dataset. The targeted selection task requires finding the relevant data from a large-scale pool of unlabeled data. Manual mining at this scale is infeasible. Further, the OOI are often small and occupy less than 1% of image area, are occluded, and co-exist with many semantically different objects in cluttered scenes. Existing semantic image retrieval methods often focus on mining for larger sized geographical landmarks, and/or require extra labeled data, such as images/image-pairs with similar objects, for mining images with generic objects. We propose a fast and robust template matching algorithm in the DNN feature space, that retrieves semantically similar images at the object-level from a large unlabeled pool of data. We project the region(s) around the OOI in the query image to the DNN feature space for use as the template. This enables our method to focus on the semantics of the OOI without requiring extra labeled data. In the context of autonomous driving, we evaluate our system for targeted selection by using failure cases of object detectors as OOI. We demonstrate its efficacy on a large unlabeled dataset with 2.2M images and show high recall in mining for images with small-sized OOI. We compare our method against a well-known semantic image retrieval method, which also does not require extra labeled data. Lastly, we show that our method is flexible and retrieves images with one or more semantically different co-occurring OOI seamlessly.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Object-Level Targeted Selection via Deep Template Matching


    Contributors:


    Publication date :

    2022-06-05


    Size :

    547364 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Feature Selection for Reliable Tracking Using Template Matching

    Kaneko, T. / Hori, O. / IEEE | British Library Conference Proceedings | 2003


    Object recognition by multiresolutional template matching [2606-29]

    Prasad, L. / Rao, R. L. / SPIE | British Library Conference Proceedings | 1995


    Using template matching for object recognition in infrared video sequences

    Pham, Quy Ich / Jalovecky, Rudolf / Polasek, Martin | IEEE | 2015


    Using Template Matching Technique for Object Detection in Infrared Images

    Pham, I. Q. / Polášek, M. | British Library Conference Proceedings | 2014