# Deformable Feature Alignment and Refinement for Moving Infrared Dim-small Target Detection

arXiv: https://arxiv.org/abs/2407.07289 · HTML: https://mlsanity.com/paper/2407.07289/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 70 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 21 of 21)

- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Asymmetric Contextual Modulation for Infrared Small Target Detection](https://mlsanity.com/paper/2009.14530/) (2020)
- [Dense Nested Attention Network for Infrared Small Target Detection](https://mlsanity.com/paper/2106.00487/) (2021)
- [UIU-Net: U-Net in U-Net for Infrared Small Object Detection](https://mlsanity.com/paper/2212.00968/) (2022)
- [Understanding Deformable Alignment in Video Super-Resolution](https://mlsanity.com/paper/2009.07265/) (2020)
- [Infrared Small Target Detection with Scale and Location Sensitivity](https://mlsanity.com/paper/2403.19366/) (2024)
- [SCTransNet: Spatial-channel Cross Transformer Network for Infrared Small Target Detection](https://mlsanity.com/paper/2401.15583/) (2024)
- [RPCANet: Deep Unfolding RPCA Based Infrared Small Target Detection](https://mlsanity.com/paper/2311.00917/) (2023)
- [Extended Feature Pyramid Network for Small Object Detection](https://mlsanity.com/paper/2003.07021/) (2020)
- [One-Stage Cascade Refinement Networks for Infrared Small Target Detection](https://mlsanity.com/paper/2212.08472/) (2022)
- [SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection](https://mlsanity.com/paper/2403.05416/) (2024)
- [Motion-aware Memory Network for Fast Video Salient Object Detection](https://mlsanity.com/paper/2208.00946/) (2022)
- [TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection](https://mlsanity.com/paper/2402.02046/) (2024)
- [Fast and Robust Small Infrared Target Detection Using Absolute Directional Mean Difference Algorithm](https://mlsanity.com/paper/1810.03173/) (2018)
- [Aggregation Signature for Small Object Tracking](https://mlsanity.com/paper/1910.10859/) (2019)
- [Feature-Aligned Video Raindrop Removal with Temporal Constraints](https://mlsanity.com/paper/2205.14574/) (2022)

## Abstract (arXiv)

The detection of moving infrared dim-small targets has been a challenging and prevalent research topic. The current state-of-the-art methods are mainly based on ConvLSTM to aggregate information from adjacent frames to facilitate the detection of the current frame. However, these methods implicitly utilize motion information only in the training stage and fail to explicitly explore motion compensation, resulting in poor performance in the case of a video sequence including large motion. In this paper, we propose a Deformable Feature Alignment and Refinement (DFAR) method based on deformable convolution to explicitly use motion context in both the training and inference stages. Specifically, a Temporal Deformable Alignment (TDA) module based on the designed Dilated Convolution Attention Fusion (DCAF) block is developed to explicitly align the adjacent frames with the current frame at the feature level. Then, the feature refinement module adaptively fuses the aligned features and further aggregates useful spatio-temporal information by means of the proposed Attention-guided Deformable Fusion (AGDF) block. In addition, to improve the alignment of adjacent frames with the current frame, we extend the traditional loss function by introducing a new motion compensation loss. Extensive experimental results demonstrate that the proposed DFAR method achieves the state-of-the-art performance on two benchmark datasets including DAUB and IRDST.