mlsanityData to 7 Oct 2026

PTQ4RIS: Post-Training Quantization for Referring Image Segmentation

arXiv 2409.17020 ↗First posted 25 Sep 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Referring Image Segmentation (RIS), aims to segment the object referred by a given sentence in an image by understanding both visual and linguistic information. However, existing RIS methods tend to explore top-performance models, disregarding considerations for practical applications on resources-limited edge devices. This oversight poses a significant challenge for on-device RIS inference. To this end, we propose an effective and efficient post-training quantization framework termed PTQ4RIS. Specifically, we first conduct an in-depth analysis of the root causes of performance degradation in RIS model quantization and propose dual-region quantization (DRQ) and reorder-based outlier-retained quantization (RORQ) to address the quantization difficulties in visual and text encoders. Extensive experiments on three benchmarks with different bits settings (from 8 to 4 bits) demonstrates its superior performance. Importantly, we are the first PTQ method specifically designed for the RIS task, highlighting the feasibility of PTQ in RIS applications. Code and video are available at {https://github.com/gugu511yy/PTQ4RIS}.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 48 of its 57 references that are in the map. First posted on arXiv 25 Sep 2024.

Builds on

48 of 57 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  7. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
  8. 2016Modeling Context in Referring Expressionscited by 1,054
  9. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 897
  10. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  11. 2019Learned Step Size Quantizationcited by 604
  12. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
36 more
  1. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  2. 2021A White Paper on Neural Network Quantizationcited by 453
  3. 2018MAttNet: Modular Attention Network for Referring Expression Comprehensioncited by 427
  4. 2021CRIS: CLIP-Driven Referring Image Segmentationcited by 353
  5. 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 347
  6. 2015LSTM: A Search Space Odysseycited by 315
  7. 2021Post-Training Quantization for Vision Transformercited by 274
  8. 2019Cross-Modal Self-Attention Network for Referring Image Segmentationcited by 263
  9. 2016Segmentation from Natural Language Expressionscited by 257
  10. 2021I-BERT: Integer-only BERT Quantizationcited by 250
  11. 2021Vision-Language Transformer and Query Generation for Referring Segmentationcited by 239
  12. 2022Interactive Language: Talking to Robots in Real Timecited by 217
  13. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 185
  14. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
  15. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 173
  16. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  17. 2023PolyFormer: Referring Image Segmentation as Sequential Polygon Generationcited by 147
  18. 2022SeqTR: A Simple yet Universal Network for Visual Groundingcited by 138
  19. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 134
  20. 2020Referring Image Segmentation via Cross-Modal Progressive Comprehensioncited by 131
  21. 2017Recurrent Multimodal Interaction for Referring Image Segmentationcited by 125
  22. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 117
  23. 2022ReSTR: Convolution-free Referring Image Segmentation Using Transformerscited by 112
  24. 2020Linguistic Structure Guided Context Modeling for Referring Image Segmentationcited by 102
  25. 2019Loss Aware Post-training Quantizationcited by 94
  26. 2022Instruction-driven history-aware policies for robotic manipulationscited by 93
  27. 2020A Survey on Instance Segmentation: State of the artcited by 85
  28. 2022PD-Quant: Post-Training Quantization based on Prediction Difference Metriccited by 73
  29. 2022BiBERT: Accurate Fully Binarized BERTcited by 70
  30. 2023Towards Accurate Post-Training Quantization for Vision Transformercited by 70
  31. 2023Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentationcited by 61
  32. 2023Contrastive Grouping with Transformer for Referring Image Segmentationcited by 54
  33. 2024A Survey on Transformer Compressioncited by 44
  34. 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detectioncited by 29
  35. 2022CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentationcited by 28
  36. 2023Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentationcited by 16

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantizationcited by 35
  2. 2025Multimodal Referring Segmentation: A Surveycited by 22
  3. 2025Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Trackingcited by 4
  4. 2025TFANet: Three-Stage Image-Text Feature Alignment Network for Robust Referring Image Segmentationcited by 0