InterPruner: Interactive Structured Pruning via Taylor-Implicit Criterion and Language-Prior Modulator for Multimodal Object Detection

• URL: http://arxiv.org/abs/2608.10724v1
• Date: Tue, 11 Aug 2026 09:42:23 GMT
• Title: InterPruner: Interactive Structured Pruning via Taylor-Implicit Criterion and Language-Prior Modulator for Multimodal Object Detection
• Abstract summary: Multimodal object detection proves effective in remote sensing, especially the RGB-Infrared paradigm.<n>Existing pruning methods can reduce channel redundancy, but they are designed for unimodal backbones.<n>We propose InterPruner, the first interactive structured channel pruning framework for RGB-infrared object detectors.
• Score: 43.76234957204122
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal object detection proves effective in remote sensing, especially the RGB-Infrared paradigm. The parallel feature extractors provide rich multimodal information for robust detection, yet introduce substantial channel redundancy and computational overhead. Existing pruning methods can reduce channel redundancy, but they are designed for unimodal backbones, overlooking cross-modal interactions and dynamic scene-wise redundancy. In this paper, we propose InterPruner, the first interactive structured channel pruning framework for RGB-infrared object detectors. Specifically, we first derive a Taylor-Implicit Criterion(TIC) to quantify channel importance via high-order Taylor expansion and the implicit function theorem. Then, a Modality Interaction Redundancy Analyzer (MIRA) identifies redundant channels via mutual compensability assessment. Finally, a Scene-Prior Channel Anchor (SPCA) uses language priors as semantic anchors to measure channel-scene relevance for dynamic channel importance estimation. Cross-modality channel pruning for RGB-Infrared detection is yet unexplored. Extensive experiments on RGB-infrared object detection dataset demonstrate that InterPruner maintains high performance with negligible degradation. Specifically, it even achieves a 0.6% mAP increase on the FLIR dataset when pruning 50% of the channels. Code will be available on GitHub to facilitate future work.

Related papers

• Bridging the RGB-IR Gap: Consensus and Discrepancy Modeling for Text-Guided Multispectral Detection [45.62297680190076]
  We propose a semantic bridge fusion framework with bi-support modeling for multispectral object detection.<n>Specifically, text is used as a shared semantic bridge to align RGB and IR responses under a unified category condition.<n>We formulate RGB-IR interaction evidence into the regular consensus support and the complementary discrepancy support.
  arXiv  Detail & Related papers  (2026-04-13T09:41:01Z)
• Multispectral Detection Transformer with Infrared-Centric Feature Fusion [8.762314897895175]
  Infrared-Centric Fusion (IC-Fusion) is a lightweight and modality-aware sensor fusion method.<n>IC-Fusion prioritizes infrared features while effectively integrating complementary RGB semantic context.<n> Experiments on the FLIR and LLVIP benchmarks demonstrate the superior effectiveness and efficiency of our IR-centric fusion strategy.
  arXiv  Detail & Related papers  (2025-05-21T05:44:14Z)
• DCFG: Diverse Cross-Channel Fine-Grained Feature Learning and Progressive Fusion Siamese Tracker for Thermal Infrared Target Tracking [11.3097285242147]
  Cross-channel fine-grained feature learning network to suppress dominant target features.<n>Channel rearrangement mechanism to enhance efficient in-formation flow.<n> specialized cross-channel fine-grained loss function to guide feature groups toward distinct discriminative re-gions of the target.
  arXiv  Detail & Related papers  (2025-04-19T14:24:37Z)
• Multi-Domain Biometric Recognition using Body Embeddings [51.36007967653781]
  We show that body embeddings perform better than face embeddings in medium-wave infrared (MWIR) and long-wave infrared (LWIR) domains.<n>We leverage a vision transformer architecture to establish benchmark results on the IJB-MDF dataset.<n>We also show that finetuning a body model, pretrained exclusively on VIS data, with a simple combination of cross-entropy and triplet losses achieves state-of-the-art mAP scores.
  arXiv  Detail & Related papers  (2025-03-13T22:38:18Z)
• SCTransNet: Spatial-channel Cross Transformer Network for Infrared Small Target Detection [46.049401912285134]
  Infrared small target detection (IRSTD) has recently benefitted greatly from U-shaped neural models. Existing techniques struggle when the target has high similarities with the background. We present a Spatial-channel Cross Transformer Network (SCTransNet) that leverages spatial-channel cross transformer blocks.
  arXiv  Detail & Related papers  (2024-01-28T06:41:15Z)
• ABC: Attention with Bilinear Correlation for Infrared Small Target Detection [4.7379300868029395]
  CNN based deep learning methods are not effective at segmenting infrared small target (IRST) We propose a new model called attention with bilinear correlation (ABC) ABC is based on the transformer architecture and includes a convolution linear fusion transformer (CLFT) module with a novel attention mechanism for feature extraction and fusion.
  arXiv  Detail & Related papers  (2023-03-18T03:47:06Z)
• CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection [144.66411561224507]
  We present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement. Our network outperforms the state-of-the-art saliency detectors both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-10-06T11:59:19Z)
• Dual Swin-Transformer based Mutual Interactive Network for RGB-D Salient Object Detection [67.33924278729903]
  In this work, we propose Dual Swin-Transformer based Mutual Interactive Network. We adopt Swin-Transformer as the feature extractor for both RGB and depth modality to model the long-range dependencies in visual inputs. Comprehensive experiments on five standard RGB-D SOD benchmark datasets demonstrate the superiority of the proposed DTMINet method.
  arXiv  Detail & Related papers  (2022-06-07T08:35:41Z)
• Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds [155.388487263872]
  We propose a new infrared small-dim target detection method with the transformer. We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range. We also design a feature enhancement module to learn more features of small-dim targets.
  arXiv  Detail & Related papers  (2021-09-29T12:23:41Z)
• Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation [59.94819184452694]
  Depth information has proven to be a useful cue in the semantic segmentation of RGBD images for providing a geometric counterpart to the RGB representation. Most existing works simply assume that depth measurements are accurate and well-aligned with the RGB pixels and models the problem as a cross-modal feature fusion. In this paper, we propose a unified and efficient Crossmodality Guided to not only effectively recalibrate RGB feature responses, but also to distill accurate depth information via multiple stages and aggregate the two recalibrated representations alternatively.
  arXiv  Detail & Related papers  (2020-07-17T18:35:24Z)

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.