{"ID":2827068,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.17514","arxiv_id":"2512.17514","title":"Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection","abstract":"Current state-of-the-art approaches in Source-Free Object Detection (SFOD) typically rely on Mean-Teacher self-labeling. However, domain shift often reduces the detector's ability to maintain strong object-focused representations, causing high-confidence activations over background clutter. This weak object focus results in unreliable pseudo-labels from the detection head. While prior works mainly refine these pseudo-labels, they overlook the underlying need to strengthen the feature space itself. We propose FALCON-SFOD (Foundation-Aligned Learning with Clutter suppression and Noise robustness), a framework designed to enhance object-focused adaptation under domain shift. It consists of two complementary components. SPAR (Spatial Prior-Aware Regularization) leverages the generalization strength of vision foundation models to regularize the detector's feature space. Using class-agnostic binary masks derived from OV-SAM, SPAR promotes structured and foreground-focused activations by guiding the network toward object regions. IRPL (Imbalance-aware Noise Robust Pseudo-Labeling) complements SPAR by promoting balanced and noise-tolerant learning under severe foreground-background imbalance. Guided by a theoretical analysis that connects these designs to tighter localization and classification error bounds, FALCON-SFOD achieves competitive performance across SFOD benchmarks.","short_abstract":"Current state-of-the-art approaches in Source-Free Object Detection (SFOD) typically rely on Mean-Teacher self-labeling. However, domain shift often reduces the detector's ability to maintain strong object-focused representations, causing high-confidence activations over background clutter. This weak object focus resul...","url_abs":"https://arxiv.org/abs/2512.17514","url_pdf":"https://arxiv.org/pdf/2512.17514v3","authors":"[\"Sairam VCR\",\"Rishabh Lalla\",\"Aveen Dayal\",\"Tejal Kulkarni\",\"Anuj Lalla\",\"Vineeth N Balasubramanian\",\"Muhammad Haris Khan\"]","published":"2025-12-19T12:30:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}