# Fine-Grained Dynamic Head for Object Detection

arXiv: https://arxiv.org/abs/2012.03519 · HTML: https://mlsanity.com/paper/2012.03519/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2020.

## Built on by (most cited first, 16 of 16)

- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images](https://mlsanity.com/paper/2303.14488/) (2023)
- [Meta-Adapter: An Online Few-shot Learner for Vision-Language Model](https://mlsanity.com/paper/2311.03774/) (2023)
- [DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection](https://mlsanity.com/paper/2207.10909/) (2022)
- [Dynamic Grained Encoder for Vision Transformers](https://mlsanity.com/paper/2301.03831/) (2023)
- [IQDet: Instance-wise Quality Distribution Sampling for Object Detection](https://mlsanity.com/paper/2104.06936/) (2021)
- [DyFADet: Dynamic Feature Aggregation for Temporal Action Detection](https://mlsanity.com/paper/2407.03197/) (2024)
- [Improving Video Instance Segmentation via Temporal Pyramid Routing](https://mlsanity.com/paper/2107.13155/) (2021)
- [GrootVL: Tree Topology is All You Need in State Space Model](https://mlsanity.com/paper/2406.02395/) (2024)
- [BoxSnake: Polygonal Instance Segmentation with Box Supervision](https://mlsanity.com/paper/2303.11630/) (2023)
- [FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors](https://mlsanity.com/paper/2303.08319/) (2023)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [AFter: Attention-based Fusion Router for RGBT Tracking](https://mlsanity.com/paper/2405.02717/) (2024)
- [Semantic-aware Modular Capsule Routing for Visual Question Answering](https://mlsanity.com/paper/2207.10404/) (2022)
- [The Untapped Potential of Off-the-Shelf Convolutional Neural Networks](https://mlsanity.com/paper/2103.09891/) (2021)

## Abstract (arXiv)

The Feature Pyramid Network (FPN) presents a remarkable approach to alleviate the scale variance in object representation by performing instance-level assignments. Nevertheless, this strategy ignores the distinct characteristics of different sub-regions in an instance. To this end, we propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance, which further releases the ability of multi-scale feature representation. Moreover, we design a spatial gate with the new activation function to reduce computational complexity dramatically through spatially sparse convolutions. Extensive experiments demonstrate the effectiveness and efficiency of the proposed method on several state-of-the-art detection benchmarks. Code is available at https://github.com/StevenGrove/DynamicHead.