# Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations

arXiv: https://arxiv.org/abs/2306.02092 · HTML: https://mlsanity.com/paper/2306.02092/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 73 references that are in the map.
- First posted on arXiv 3 Jun 2023.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Composing Text and Image for Image Retrieval - An Empirical Odyssey](https://mlsanity.com/paper/1812.07119/) (2018)
- [Deep Co-Training for Semi-Supervised Image Recognition](https://mlsanity.com/paper/1803.05984/) (2018)
- [Dual-Path Convolutional Image-Text Embeddings with Instance Loss](https://mlsanity.com/paper/1711.05535/) (2017)
- [Automatic Spatially-aware Fashion Concept Discovery](https://mlsanity.com/paper/1708.01311/) (2017)
- [Cross-Batch Memory for Embedding Learning](https://mlsanity.com/paper/1912.06798/) (2019)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity](https://mlsanity.com/paper/2203.08101/) (2022)
- [A Discriminatively Learned CNN Embedding for Person Re-identification](https://mlsanity.com/paper/1611.05666/) (2016)
- [Deep Co-Training for Semi-Supervised Image Segmentation](https://mlsanity.com/paper/1903.11233/) (2019)
- [Unsupervised Scene Adaptation with Memory Regularization in vivo](https://mlsanity.com/paper/1912.11164/) (2019)
- [On Semantic Similarity in Video Retrieval](https://mlsanity.com/paper/2103.10095/) (2021)
- [Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization](https://mlsanity.com/paper/2211.07394/) (2022)
- [Multimodal Residual Learning for Visual QA](https://mlsanity.com/paper/1606.01455/) (2016)
- [FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks](https://mlsanity.com/paper/2303.02483/) (2023)
- [SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification](https://mlsanity.com/paper/1807.00537/) (2018)
- [Progressive Learning for Image Retrieval with Hybrid-Modality Queries](https://mlsanity.com/paper/2204.11212/) (2022)

## Built on by (most cited first, 14 of 14)

- [CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval](https://mlsanity.com/paper/2405.19149/) (2024)
- [Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.19386/) (2026)
- [A Comprehensive Survey on Composed Image Retrieval](https://mlsanity.com/paper/2502.18495/) (2025)
- [ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.20358/) (2026)
- [COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations](https://mlsanity.com/paper/2606.04604/) (2026)
- [Scale Up Composed Image Retrieval Learning via Modification Text Generation](https://mlsanity.com/paper/2504.05316/) (2025)
- [LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval](https://mlsanity.com/paper/2601.14706/) (2026)
- [A Survey of Multimodal Composite Editing and Retrieval](https://mlsanity.com/paper/2409.05405/) (2024)
- [DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval](https://mlsanity.com/paper/2505.17796/) (2025)
- [Self-distilled Dynamic Fusion Network for Language-based Fashion Retrieval](https://mlsanity.com/paper/2405.15451/) (2024)
- [CLIP-SENet: CLIP-based Semantic Enhancement Network for Vehicle Re-identification](https://mlsanity.com/paper/2502.16815/) (2025)
- [Composed Multi-modal Retrieval: A Survey of Approaches and Applications](https://mlsanity.com/paper/2503.01334/) (2025)
- [Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2602.00813/) (2026)
- [VietFashion: Benchmarking Sketch-Text Composed Image Retrieval for Cultural Outfits](https://mlsanity.com/paper/2606.13427/) (2026)

## Abstract (arXiv)

Composed image retrieval extends content-based image retrieval systems by enabling users to search using reference images and captions that describe their intention. Despite great progress in developing image-text compositors to extract discriminative visual-linguistic features, we identify a hitherto overlooked issue, triplet ambiguity, which impedes robust feature extraction. Triplet ambiguity refers to a type of semantic ambiguity that arises between the reference image, the relative caption, and the target image. It is mainly due to the limited representation of the annotated text, resulting in many noisy triplets where multiple visually dissimilar candidate images can be matched to an identical reference pair (i.e., a reference image + a relative caption). To address this challenge, we propose the Consensus Network (Css-Net), inspired by the psychological concept that groups outperform individuals. Css-Net comprises two core components: (1) a consensus module with four diverse compositors, each generating distinct image-text embeddings, fostering complementary feature extraction and mitigating dependence on any single, potentially biased compositor; (2) a Kullback-Leibler divergence loss that encourages learning of inter-compositor interactions to promote consensual outputs. During evaluation, the decisions of the four compositors are combined through a weighting scheme, enhancing overall agreement. On benchmark datasets, particularly FashionIQ, Css-Net demonstrates marked improvements. Notably, it achieves significant recall gains, with a 2.77% increase in R@10 and 6.67% boost in R@50, underscoring its competitiveness in addressing the fundamental limitations of existing methods.