Search papers, labs, and topics across Lattice.
This paper introduces Sparsely Annotated Open-World Object Detection (SA-OWOD), a novel task that addresses the simultaneous challenges of sparse supervision and the presence of unknown object categories in real-world object detection. The authors propose a Dual-Perspective Object Discovery (DPOD) framework, which integrates a Known Target Recovery Module (KTRM) to enhance supervision for known instances and a Dual-Disagreement Target Generator (DDTG) to identify reliable unknown candidates. Experimental results show that DPOD significantly outperforms existing methods, particularly in accurately detecting unknown objects, thereby stabilizing decision boundaries in ambiguous scenarios.
Misclassification between known and unknown objects can be effectively mitigated using a unified framework that leverages dual perspectives on object discovery.
Real-world object detection operates under ambiguous supervision, where unlabeled regions may correspond to missing annotations of known objects or genuinely unknown categories. These challenges have been addressed separately in Sparsely Annotated Object Detection (SAOD) and Open-World Object Detection (OWOD). In practice, their co-occurrence remains an open problem. To address this problem, we introduce Sparsely Annotated Open-World Object Detection (SA-OWOD), a new task that jointly considers sparse supervision and the presence of unseen categories. We propose Dual-Perspective Object Discovery (DPOD), a unified framework that jointly models unlabeled known and unknown instances via two complementary mechanisms. The Known Target Recovery Module (KTRM) recovers supervision for unlabeled known instances and explicitly regularizes the feature space to separate known and unknown representations. Complementarily, the Dual-Disagreement Target Generator (DDTG) identifies reliable unknown candidates through cross-view semantic inconsistency. By integrating these modules, DPOD resolves contradictory supervision signals caused by ambiguous unlabeled regions. As a result, it prevents misclassification between known and unknown objects and stabilizes the decision boundaries. Experimental results on sparsely annotated open-world benchmarks demonstrate that the proposed method outperforms existing open-world detection methods, particularly in detecting unknown objects.
