# HASSOD: Hierarchical Adaptive Self-Supervised Object Detection Source: [HASSOD: Hierarchical Adaptive Self-Supervised Object Detection]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:40:03.317Z Authors: Shengcao Cao, Dhiraj Joshi, Liang-Yan Gui, Yu-Xiong Wang Published: 2024-02-05T18:59:41.000Z ## Abstract The human visual perception system demonstrates exceptional capabilities in learning without explicit supervision and understanding the part-to-whole composition of objects. Drawing inspiration from these two abilities, we propose Hierarchical Adaptive Self-Supervised Object Detection (HASSOD), a novel approach that learns to detect objects and understand their compositions without human supervision. HASSOD employs a hierarchical adaptive clustering strategy to group regions into object masks based on self-supervised visual representations, adaptively determining the number of objects per image. Furthermore, HASSOD identifies the hierarchical levels of objects in terms of composition, by analyzing coverage relations between masks and constructing tree structures. This additional self-supervised learning task leads to improved detection performance and enhanced interpretability. Lastly, we abandon the inefficient multi-round self-training process utilized in prior methods and instead adapt the Mean Teacher framework from semi-supervised learning, which leads to a smoother and more efficient training process. Through extensive experiments on prevalent image datasets, we demonstrate the superiority of HASSOD over existing methods, thereby advancing the state of the art in self-supervised object detection. Notably, we improve Mask AR from 20.2 to 22.5 on LVIS, and from 17.0 to 26.0 on SA-1B. Project page: https://HASSOD-NeurIPS23.github.io. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on SA-1B](): Object Detection; SA-1B; AR (Average Recall): 29. - [Instance Segmentation on SA-1B](): Instance Segmentation; SA-1B; AR (Small): 12.9. - [Instance Segmentation on Waymo](): Instance Segmentation; Waymo; AP50: 3.9. - [Instance Segmentation on LVIS](): Instance Segmentation; LVIS; mAP (Mask): 4.2. - [Object Detection on LVIS](): Object Detection; LVIS; APr: not recorded. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()