Research map / Detection and segmentation / Open-set and few-shot detection

Stabilizing Few-Shot Object Detection with Language-Conditioned Probabilistic Prototypes

NeurIPS 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a language-conditioned probabilistic prototype approach to stabilize prototype-based few-shot object detection in extreme low-shot regimes.

Problem

Prototype-based few-shot object detection is unstable in extreme low-shot regimes, attributed to semantically unanchored query initialization causing high-variance cold-start behavior (abstract is truncated).

Approach

Anchors query initialization with language-conditioned semantics and models prototypes probabilistically to reduce variance; details unavailable because the abstract is truncated.

Closest papers by meaning

• Fine-Grained Prototypes Distillation for Few-Shot Object Detection (AAAI 2024 · similarity 0.90)
• Revisiting Few-Shot Object Detection with Vision-Language Models (NeurIPS 2024 · similarity 0.90)
• SCAN: Cross Domain Object Detection with Semantic Conditioned Adaptation (AAAI 2022 · similarity 0.89)
• Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models (NeurIPS 2025 · similarity 0.87)
• Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages (CVPR 2025 · similarity 0.87)
• Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.87)