# IntRec: Intent-based Retrieval with Contrastive Refinement

arXiv: https://arxiv.org/abs/2602.17639 · HTML: https://mlsanity.com/paper/2602.17639/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Reviving Iterative Training with Mask Guidance for Interactive Segmentation](https://mlsanity.com/paper/2102.06583/) (2021)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [An Open and Comprehensive Pipeline for Unified Object Grounding and Detection](https://mlsanity.com/paper/2401.02361/) (2024)
- [Multi-Modal Classifiers for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.05493/) (2023)
- [CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2310.16667/) (2023)
- [LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors](https://mlsanity.com/paper/2402.04630/) (2024)
- [OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion](https://mlsanity.com/paper/2407.07844/) (2024)
- [DesCo: Learning Object Recognition with Rich Language Descriptions](https://mlsanity.com/paper/2306.14060/) (2023)
- [Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection](https://mlsanity.com/paper/2406.00510/) (2024)
- [Open-Vocabulary Object Detection via Language Hierarchy](https://mlsanity.com/paper/2410.20371/) (2024)
- [Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2503.11005/) (2025)
- [Region-centric Image-Language Pretraining for Open-Vocabulary Detection](https://mlsanity.com/paper/2310.00161/) (2023)
- [Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization](https://mlsanity.com/paper/2403.09433/) (2024)
- [OVMR: Open-Vocabulary Recognition with Multi-Modal References](https://mlsanity.com/paper/2406.04675/) (2024)
- [SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection](https://mlsanity.com/paper/2503.00414/) (2025)
- [Open-Vocabulary Object Detection via Neighboring Region Attention Alignment](https://mlsanity.com/paper/2405.08593/) (2024)

## Abstract (arXiv)

Retrieving user-specified objects from complex scenes remains a challenging task, especially when queries are ambiguous or involve multiple similar objects. Existing open-vocabulary detectors operate in a one-shot manner, lacking the ability to refine predictions based on user feedback. To address this, we propose IntRec, an interactive object retrieval framework that refines predictions based on user feedback. At its core is an Intent State (IS) that maintains dual memory sets for positive anchors (confirmed cues) and negative constraints (rejected hypotheses). A contrastive alignment function ranks candidate objects by maximizing similarity to positive cues while penalizing rejected ones, enabling fine-grained disambiguation in cluttered scenes. Our interactive framework provides substantial improvements in retrieval accuracy without additional supervision. On LVIS, IntRec achieves 35.4 AP, outperforming OVMR, CoDet, and CAKE by +2.3, +3.7, and +0.5, respectively. On the challenging LVIS-Ambiguous benchmark, it improves performance by +7.9 AP over its one-shot baseline after a single corrective feedback, with less than 30 ms of added latency per interaction.