# Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval

arXiv: https://arxiv.org/abs/2409.13513 · HTML: https://mlsanity.com/paper/2409.13513/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Automatic Spatially-aware Fashion Concept Discovery](https://mlsanity.com/paper/1708.01311/) (2017)
- [DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images](https://mlsanity.com/paper/1901.07973/) (2019)
- [AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations](https://mlsanity.com/paper/1905.00292/) (2019)
- [An Inverse Scaling Law for CLIP Training](https://mlsanity.com/paper/2305.07017/) (2023)
- [Products-10K: A Large-scale Product Recognition Dataset](https://mlsanity.com/paper/2008.10545/) (2020)
- [The Met Dataset: Instance-level Recognition for Artworks](https://mlsanity.com/paper/2202.01747/) (2022)
- [Medical Image Retrieval using Deep Convolutional Neural Network](https://mlsanity.com/paper/1703.08472/) (2017)
- [Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations](https://mlsanity.com/paper/2309.01858/) (2023)
- [RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification](https://mlsanity.com/paper/2006.12634/) (2020)
- [Visual Search at Alibaba](https://mlsanity.com/paper/2102.04674/) (2021)
- [GPR1200: A Benchmark for General-Purpose Content-Based Image Retrieval](https://mlsanity.com/paper/2111.13122/) (2021)
- [1st Place Solution in Google Universal Images Embedding](https://mlsanity.com/paper/2210.08473/) (2022)
- [AirFace: Lightweight and Efficient Model for Face Recognition](https://mlsanity.com/paper/1907.12256/) (2019)

## Built on by (most cited first, 1 of 1)

- [Illuminating Visual Identity in Universal Multimodal Embeddings](https://mlsanity.com/paper/2608.01794/) (2026)

## Abstract (arXiv)

Current image retrieval systems often face domain specificity and generalization issues. This study aims to overcome these limitations by developing a computationally efficient training framework for a universal feature extractor that provides strong semantic image representations across various domains. To this end, we curated a multi-domain training dataset, called M4D-35k, which allows for resource-efficient training. Additionally, we conduct an extensive evaluation and comparison of various state-of-the-art visual-semantic foundation models and margin-based metric learning loss functions regarding their suitability for efficient universal feature extraction. Despite constrained computational resources, we achieve near state-of-the-art results on the Google Universal Image Embedding Challenge, with a mMP@5 of 0.721. This places our method at the second rank on the leaderboard, just 0.7 percentage points behind the best performing method. However, our model has 32% fewer overall parameters and 289 times fewer trainable parameters. Compared to methods with similar computational requirements, we outperform the previous state of the art by 3.3 percentage points. We release our code and M4D-35k training set annotations at https://github.com/morrisfl/UniFEx.