Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation

About

In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly favored for its effectiveness in large foundation models, as it streamlines transfer learning costs and optimizes hardware utilization. However, the current PET methods are mainly designed for single-modal optimization. While some pioneering studies have undertaken preliminary explorations, they still remain at the level of aligned encoders (e.g., CLIP) and lack exploration of misaligned encoders. These methods show sub-optimal performance with misaligned encoders, as they fail to effectively align the multimodal features during fine-tuning. In this paper, we introduce DETRIS, a parameter-efficient tuning framework designed to enhance low-rank visual feature propagation by establishing dense interconnections between each layer and all preceding layers, which enables effective cross-modal feature interaction and adaptation to misaligned encoders. We also suggest using text adapters to improve textual features. Our simple yet efficient approach greatly surpasses state-of-the-art methods with 0.9% to 1.8% backbone parameter updates, evaluated on challenging benchmarks. Our project is available at \url{https://github.com/jiaqihuang01/DETRIS}.

Jiaqi Huang, Zunnan Xu, Ting Liu, Yong Liu, Haonan Han, Kehong Yuan, Xiu Li• 2025

Related benchmarks

TaskDatasetResultRank
Referring Expression SegmentationRefCOCO (testA)
cIoU81.9
315
Referring Expression SegmentationRefCOCO+ (testA)
cIoU78.6
288
Referring Image SegmentationRefCOCO (val)
mIoU76
274
Referring Expression SegmentationRefCOCO+ (val)
cIoU75.2
272
Referring Image SegmentationRefCOCO+ (test-B)
mIoU70.2
267
Referring Expression SegmentationRefCOCO (val)
cIoU81
261
Referring Expression SegmentationRefCOCO (testB)
cIoU79
259
Referring Expression SegmentationRefCOCO+ (testB)
cIoU70.2
256
Referring Image SegmentationRefCOCO (test A)
mIoU81.9
245
Referring Image SegmentationRefCOCO+ (val)
mIoU68.9
194
Showing 10 of 30 rows

Other info

Code

Follow for update