TY - JOUR AU - Karlinsky, Leonid AU - Shtok, Joseph AU - Alfassy, Amit AU - Lichtenstein, Moshe AU - Harary, Sivan AU - Schwartz, Eli AU - Doveh, Sivan AU - Sattigeri, Prasanna AU - Feris, Rogerio AU - Bronstein, Alex AU - Giryes, Raja PY - 2021/05/18 Y2 - 2024/03/28 TI - StarNet: towards Weakly Supervised Few-Shot Object Detection JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 2 SE - AAAI Technical Track on Computer Vision I DO - 10.1609/aaai.v35i2.16268 UR - https://ojs.aaai.org/index.php/AAAI/article/view/16268 SP - 1743-1753 AB - Few-shot detection and classification have advanced significantly in recent years. Yet, detection approaches require strong annotation (bounding boxes) both for pre-training and for adaptation to novel classes, and classification approaches rarely provide localization of objects in the scene. In this paper, we introduce StarNet - a few-shot model featuring an end-to-end differentiable non-parametric star-model detection and classification head. Through this head, the backbone is meta-trained using only image-level labels to produce good features for jointly localizing and classifying previously unseen categories of few-shot test tasks using a star-model that geometrically matches between the query and support images (to find corresponding object instances). Being a few-shot detector, StarNet does not require any bounding box annotations, neither during pre-training nor for novel classes adaptation. It can thus be applied to the previously unexplored and challenging task of Weakly Supervised Few-Shot Object Detection (WS-FSOD), where it attains significant improvements over the baselines. In addition, StarNet shows significant gains on few-shot classification benchmarks that are less cropped around the objects (where object localization is key). ER -