# SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval

arXiv: https://arxiv.org/abs/2209.13833 · HTML: https://mlsanity.com/paper/2209.13833/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 55 references that are in the map.
- First posted on arXiv 28 Sep 2022.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [A Survey on Learning to Hash](https://mlsanity.com/paper/1606.00185/) (2016)
- [Feature Learning based Deep Supervised Hashing with Pairwise Labels](https://mlsanity.com/paper/1511.03855/) (2015)
- [SOLAR: Second-Order Loss and Attention for Image Retrieval](https://mlsanity.com/paper/2001.08972/) (2020)
- [Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval](https://mlsanity.com/paper/1604.04994/) (2016)
- [One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective](https://mlsanity.com/paper/2109.14449/) (2021)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [Asymmetric Deep Supervised Hashing](https://mlsanity.com/paper/1707.08325/) (2017)
- [Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks](https://mlsanity.com/paper/1504.08289/) (2015)
- [ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval](https://mlsanity.com/paper/2008.01369/) (2020)
- [Deep Saliency Hashing](https://mlsanity.com/paper/1807.01459/) (2018)
- [The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification](https://mlsanity.com/paper/1411.7466/) (2014)
- [Category-Based Deep CCA for Fine-Grained Venue Discovery from Multimodal Data](https://mlsanity.com/paper/1805.02997/) (2018)
- [Hashing with Binary Matrix Pursuit](https://mlsanity.com/paper/1808.01990/) (2018)
- [PHPQ: Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval](https://mlsanity.com/paper/2109.05206/) (2021)

## Built on by (most cited first, 11 of 11)

- [From Region to Patch: Attribute-Aware Foreground-Background Contrastive Learning for Fine-Grained Fashion Retrieval](https://mlsanity.com/paper/2305.10260/) (2023)
- [Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval](https://mlsanity.com/paper/2311.06067/) (2023)
- [Feature-Suppressed Contrast for Self-Supervised Food Pre-training](https://mlsanity.com/paper/2308.03272/) (2023)
- [Cascading Hierarchical Networks with Multi-task Balanced Loss for Fine-grained hashing](https://mlsanity.com/paper/2303.11274/) (2023)
- [Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization](https://mlsanity.com/paper/2401.08860/) (2024)
- [ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery](https://mlsanity.com/paper/2406.08457/) (2024)
- [Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels](https://mlsanity.com/paper/2502.19816/) (2025)
- [Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization](https://mlsanity.com/paper/2509.17049/) (2025)
- [Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition](https://mlsanity.com/paper/2504.09215/) (2025)
- [RFHNet: Relational and Frequency-Aware Hashing Network for Large-Scale Fine-Grained Food Image Retrieval](https://mlsanity.com/paper/2607.06148/) (2026)
- [Controlling Embedding Spaces with Text-Conditioned Transformations](https://mlsanity.com/paper/2607.22919/) (2026)

## Abstract (arXiv)

In this paper, we propose Suppression-Enhancing Mask based attention and Interactive Channel transformatiON (SEMICON) to learn binary hash codes for dealing with large-scale fine-grained image retrieval tasks. In SEMICON, we first develop a suppression-enhancing mask (SEM) based attention to dynamically localize discriminative image regions. More importantly, different from existing attention mechanism simply erasing previous discriminative regions, our SEM is developed to restrain such regions and then discover other complementary regions by considering the relation between activated regions in a stage-by-stage fashion. In each stage, the interactive channel transformation (ICON) module is afterwards designed to exploit correlations across channels of attended activation tensors. Since channels could generally correspond to the parts of fine-grained objects, the part correlation can be also modeled accordingly, which further improves fine-grained retrieval accuracy. Moreover, to be computational economy, ICON is realized by an efficient two-step process. Finally, the hash learning of our SEMICON consists of both global- and local-level branches for better representing fine-grained objects and then generating binary hash codes explicitly corresponding to multiple levels. Experiments on five benchmark fine-grained datasets show our superiority over competing methods.