mlsanityData to 7 Oct 2026

Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval

arXiv 2204.13913 ↗First posted 29 Apr 2022cs.CV cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Current text-image approaches (e.g., CLIP) typically adopt dual-encoder architecture using pre-trained vision-language representation. However, these models still pose non-trivial memory requirements and substantial incremental indexing time, which makes them less practical on mobile devices. In this paper, we present an effective two-stage framework to compress large pre-trained dual-encoder for lightweight text-image retrieval. The resulting model is smaller (39% of the original), faster (1.6x/2.9x for processing image/text respectively), yet performs on par with or better than the original full model on Flickr30K and MSCOCO benchmarks. We also open-source an accompanying realistic mobile image search application.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 19 of its 20 references that are in the map. First posted on arXiv 29 Apr 2022.

Builds on

19 of 20 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  8. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  9. 2015VQA: Visual Question Answeringcited by 2,489
  10. 2017Billion-scale similarity search with GPUscited by 2,477
  11. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  12. 2017Decoupled Weight Decay Regularizationcited by 1,722
7 more
  1. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  2. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
  3. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,213
  4. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
  5. 2021ImageNet-21K Pretraining for the Massescited by 607
  6. 2018A Corpus for Reasoning About Natural Language Grounded in Photographscited by 457
  7. 2019UNITER: UNiversal Image-TExt Representation Learningcited by 225

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1.

4 papers.

  1. 2023ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrievalcited by 3
  2. 2023MOSAIC: Multi-Object Segmented Arbitrary Stylization Using CLIPcited by 2
  3. 2024The Use of Multimodal Large Language Models to Detect Objects from Thermal Images: Transportation Applicationscited by 2
  4. 2023MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrievalcited by 1