# CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

arXiv: https://arxiv.org/abs/1604.02426 · HTML: https://mlsanity.com/paper/1604.02426/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2016.

## Built on by (most cited first, 30 of 58)

- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity](https://mlsanity.com/paper/2203.08101/) (2022)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features](https://mlsanity.com/paper/2108.02927/) (2021)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (2022)
- [Visual Grounding with Transformers](https://mlsanity.com/paper/2105.04281/) (2021)
- [Interpretable Semantic Photo Geolocation](https://mlsanity.com/paper/2104.14995/) (2021)
- [Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition](https://mlsanity.com/paper/2407.02422/) (2024)
- [HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer](https://mlsanity.com/paper/2305.03595/) (2023)
- [Composed Video Retrieval via Enriched Context and Discriminative Embeddings](https://mlsanity.com/paper/2403.16997/) (2024)
- [DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding](https://mlsanity.com/paper/2211.15516/) (2022)
- [Reassessing the Limitations of CNN Methods for Camera Pose Regression](https://mlsanity.com/paper/2108.07260/) (2021)
- [Semantic Reinforced Attention Learning for Visual Place Recognition](https://mlsanity.com/paper/2108.08443/) (2021)
- [Robust and Decomposable Average Precision for Image Retrieval](https://mlsanity.com/paper/2110.01445/) (2021)
- [Boosting vision transformers for image retrieval](https://mlsanity.com/paper/2210.11909/) (2022)
- [Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey](https://mlsanity.com/paper/2206.08304/) (2022)
- [All the attention you need: Global-local, spatial-channel attention for image retrieval](https://mlsanity.com/paper/2107.08000/) (2021)
- [InsCLR: Improving Instance Retrieval with Self-Supervision](https://mlsanity.com/paper/2112.01390/) (2021)
- [FeDXL: Provable Federated Learning for Deep X-Risk Optimization](https://mlsanity.com/paper/2210.14396/) (2022)
- [FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory](https://mlsanity.com/paper/2308.10170/) (2023)
- [Optimization of Rank Losses for Image Retrieval](https://mlsanity.com/paper/2309.08250/) (2023)
- [GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps](https://mlsanity.com/paper/2109.00951/) (2021)
- [Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.15575/) (2023)
- [Hierarchical Average Precision Training for Pertinent Image Retrieval](https://mlsanity.com/paper/2207.04873/) (2022)
- [A Critical Analysis of Image-based Camera Pose Estimation Techniques](https://mlsanity.com/paper/2201.05816/) (2022)
- [Visual Correspondence Hallucination](https://mlsanity.com/paper/2106.09711/) (2021)
- [4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions](https://mlsanity.com/paper/2301.01147/) (2022)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positive and hard negative examples enhance the final performance in particular object retrieval with compact codes.