TALENT: Target-aware Efficient Tuning for Referring Image Segmentation
Not on the map. Why?
Abstract (arXiv)
Referring image segmentation aims to segment specific targets based on a natural text expression. Recently, parameter-efficient tuning (PET) has emerged as a promising paradigm. However, existing PET-based methods often suffer from the fact that visual features can't emphasize the text-referred target instance but activate co-category yet unrelated objects. We analyze and quantify this problem, terming it the `non-target activation' (NTA) issue. To address this, we propose a novel framework, TALENT, which utilizes target-aware efficient tuning for PET-based RIS. Specifically, we first propose a Rectified Cost Aggregator (RCA) to efficiently aggregate text-referred features. Then, to calibrate `NTA' into accurate target activation, we adopt a Target-aware Learning Mechanism (TLM), including contextual pairwise consistency learning and target-centric contrastive learning. The former uses the sentence-level text feature to achieve a holistic understanding of the referent and constructs a text-referred affinity map to optimize the semantic association of visual features. The latter further enhances target localization to discover the distinct instance while suppressing associations with other unrelated ones. The two objectives work in concert and address `NTA' effectively. Extensive evaluations show that TALENT outperforms existing methods across various metrics (e.g., 2.5% mIoU gains on G-Ref val set). Our codes will be released at: https://github.com/Kimsure/TALENT.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 45 of its 59 references that are in the map. First posted on arXiv 1 Apr 2026.
Builds on
45 of 59 references.
References · 45
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2023Segment Anythingcited by 8,234
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2021Learning to Prompt for Vision-Language Modelscited by 2,281
- 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
- 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
- 2021Going deeper with Image Transformerscited by 764
33 more
- 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
- 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 460
- 2021CRIS: CLIP-Driven Referring Image Segmentationcited by 353
- 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 348
- 2016Segmentation from Natural Language Expressionscited by 257
- 2023GRES: Generalized Referring Expression Segmentationcited by 254
- 2016Modeling Context Between Objects for Referring Expression Understandingcited by 251
- 2021Vision-Language Transformer and Query Generation for Referring Segmentationcited by 240
- 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 219
- 2020Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentationcited by 204
- 2020Referring Image Segmentation via Cross-Modal Progressive Comprehensioncited by 131
- 2022Convolutional Bypasses Are Better Vision Transformer Adapterscited by 121
- 2021Cross-Modal Progressive Comprehension for Referring Segmentationcited by 102
- 2023Beyond One-to-One: Rethinking the Referring Image Segmentationcited by 68
- 2023Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentationcited by 61
- 2023Contrastive Grouping with Transformer for Referring Image Segmentationcited by 54
- 2024Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generationcited by 43
- 2025Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decodingcited by 43
- 2024ReMamber: Referring Image Segmentation with Mamba Twistercited by 38
- 2025StreamAgent: Towards Anticipatory Agents for Streaming Video Understandingcited by 33
- 2025MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversationcited by 29
- 2025Densely Connected Parameter-Efficient Tuning for Referring Image Segmentationcited by 26
- 2021Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Groundingcited by 21
- 2021Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learningcited by 20
- 2025Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraintscited by 17
- 2022Temporal Consistency Learning of inter-frames for Video Super-Resolutioncited by 16
- 2022Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learningcited by 14
- 2024CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentationcited by 10
- 2025Normal-Abnormal Guided Generalist Anomaly Detectioncited by 10
- 2022Position-Aware Contrastive Alignment for Referring Image Segmentationcited by 9
- 2025WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentationcited by 9
- 2024Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentationcited by 8
- 2024A Parameter-Efficient Tuning Framework for Language-guided Object Grounding and Robot Graspingcited by 6
Built on by
Citing papers per year: 2026: 1.
1 paper.