HI-MoE: Hierarchical Instance-Conditioned Mixture-of-Experts for Object Detection

• URL: http://arxiv.org/abs/2604.04908v1
• Date: Mon, 06 Apr 2026 17:52:58 GMT
• Title: HI-MoE: Hierarchical Instance-Conditioned Mixture-of-Experts for Object Detection
• Abstract summary: Mixture-of-Experts (MoE) architectures enable conditional computation by activating only a subset of model parameters for each input.<n>We propose Hierarchical Instance-Conditioned Mixture-of-Experts (HI-MoE), a DETR-style detection architecture that performs routing in two stages.<n>We present the method, ablations, and current limitations in a form intended to support further experimental validation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixture-of-Experts (MoE) architectures enable conditional computation by activating only a subset of model parameters for each input. Although sparse routing has been highly effective in language models and has also shown promise in vision, most vision MoE methods operate at the image or patch level. This granularity is poorly aligned with object detection, where the fundamental unit of reasoning is an object query corresponding to a candidate instance. We propose Hierarchical Instance-Conditioned Mixture-of-Experts (HI-MoE), a DETR-style detection architecture that performs routing in two stages: a lightweight scene router first selects a scene-consistent expert subset, and an instance router then assigns each object query to a small number of experts within that subset. This design aims to preserve sparse computation while better matching the heterogeneous, instance-centric structure of detection. In the current draft, experiments are concentrated on COCO with preliminary specialization analysis on LVIS. Under these settings, HI-MoE improves over a dense DINO baseline and over simpler token-level or instance-only routing variants, with especially strong gains on small objects. We also provide an initial visualization of expert specialization patterns. We present the method, ablations, and current limitations in a form intended to support further experimental validation.

Related papers

• Hierarchical Fine-Grained Aerial Object Detection [41.39072956799442]
  We present ExpertDet, a scheme that incorporates expert-informed cues to enhance fine-grained aerial object detection.<n>Specifically, we design Vision-aware Masked Attribute Modeling (VMAM), which aligns semantics with visual structures.<n>We also propose Hierarchical Visual Instance Promotion (HierVIP), which builds a visual prototype tree based on hierarchical relations.
  arXiv  Detail & Related papers  (2026-06-15T09:20:16Z)
• Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection [29.69451620133701]
  Human-Object Interaction (HOI) detection aims to localize human-object pairs and classify their interactions from a single image.<n>Recent approaches have leveraged Vision-Language Models (VLMs) to introduce semantic priors, significantly improving HOI detection performance.<n>We propose the Instance-centric Context Mining Network (InCoM-Net) to integrate rich semantic knowledge extracted from VLM with instance-specific features produced by an object detector.
  arXiv  Detail & Related papers  (2026-04-02T14:01:58Z)
• A Multimodal Depth-Aware Method For Embodied Reference Understanding [56.30142869506262]
  Embodied Reference Understanding requires identifying a target object in a visual scene based on both language instructions and pointing cues.<n>We propose a novel ERU framework that jointly leverages data augmentation, depth-map modality, and a depth-aware decision module.
  arXiv  Detail & Related papers  (2025-10-09T14:32:21Z)
• Align Your Query: Representation Alignment for Multimodality Medical Object Detection [55.86070915426998]
  We propose a detector-agnostic framework to align representations with modality context.<n>We integrate modality tokens into the detection process via Multimodality Context Attention.<n>The proposed approach consistently improves AP with minimal overhead and no architectural modifications.
  arXiv  Detail & Related papers  (2025-10-03T07:49:21Z)
• Learning to Borrow Features for Improved Detection of Small Objects in Single-Shot Detectors [0.0]
  We propose a novel framework that enables small object representations to "borrow" discriminative features from larger, semantically richer instances within the same class.<n>Our approach significantly boosts small object detection accuracy over baseline methods, offering a promising direction for robust object detection in complex visual environments.
  arXiv  Detail & Related papers  (2025-04-30T01:18:33Z)
• MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction [75.93907511203317]
  We propose MGMapNet (Multi-Granularity Map Network) to model map element with a multi-granularity representation. The proposed MGMapNet achieves state-of-the-art performance, surpassing MapTRv2 by 5.3 mAP on nuScenes and 4.4 mAP on Argoverse2 respectively.
  arXiv  Detail & Related papers  (2024-10-10T09:05:23Z)
• Weakly Supervised Open-Vocabulary Object Detection [31.605276665964787]
  We propose a novel weakly supervised open-vocabulary object detection framework, namely WSOVOD, to extend traditional WSOD. To achieve this, we explore three vital strategies, including dataset-level feature adaptation, image-level salient object localization, and region-level vision-language alignment.
  arXiv  Detail & Related papers  (2023-12-19T18:59:53Z)
• TIDE: Test Time Few Shot Object Detection [11.036762620105383]
  Few-shot object detection (FSOD) aims to extract semantic knowledge from limited object instances of novel categories within a target domain. Recent advances in FSOD focus on fine-tuning the base model based on a few objects via meta-learning or data augmentation. We formalize a novel FSOD task, referred to as Test TIme Few Shot DEtection (TIDE), where the model is un-tuned in the configuration procedure.
  arXiv  Detail & Related papers  (2023-11-30T09:00:44Z)
• I^3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors [64.93963042395976]
  Implicit Instance-Invariant Network (I3Net) is tailored for adapting one-stage detectors. I3Net implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers. Experiments reveal that I3Net exceeds the state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2021-03-25T11:14:36Z)
• End-to-End Object Detection with Transformers [88.06357745922716]
  We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss.
  arXiv  Detail & Related papers  (2020-05-26T17:06:38Z)
• One-Shot Object Detection without Fine-Tuning [62.39210447209698]
  We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module. We also propose novel training strategies that effectively improve detection performance. Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
  arXiv  Detail & Related papers  (2020-05-08T01:59:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.