# Learning Similarity Conditions Without Explicit Supervision

arXiv: https://arxiv.org/abs/1908.08589 · HTML: https://mlsanity.com/paper/1908.08589/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2019.

## Built on by (most cited first, 30 of 36)

- [Kaleido-BERT: Vision-Language Pre-training on Fashion Domain](https://mlsanity.com/paper/2103.16110/) (2021)
- [No Representation Rules Them All in Category Discovery](https://mlsanity.com/paper/2311.17055/) (2023)
- [GeneCIS: A Benchmark for General Conditional Image Similarity](https://mlsanity.com/paper/2306.07969/) (2023)
- [FashionViL: Fashion-Focused Vision-and-Language Representation Learning](https://mlsanity.com/paper/2207.08150/) (2022)
- [OutfitTransformer: Learning Outfit Representations for Fashion Recommendation](https://mlsanity.com/paper/2204.04812/) (2022)
- [ERM++: An Improved Baseline for Domain Generalization](https://mlsanity.com/paper/2304.01973/) (2023)
- [Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning](https://mlsanity.com/paper/2104.02429/) (2021)
- [Effectively Leveraging Attributes for Visual Similarity](https://mlsanity.com/paper/2105.01695/) (2021)
- [Improved Diversity-Promoting Collaborative Metric Learning for Recommendation](https://mlsanity.com/paper/2409.01012/) (2024)
- [Semi-Supervised Visual Representation Learning for Fashion Compatibility](https://mlsanity.com/paper/2109.08052/) (2021)
- [Learning Weakly-Supervised Contrastive Representations](https://mlsanity.com/paper/2202.06670/) (2022)
- [UIGR: Unified Interactive Garment Retrieval](https://mlsanity.com/paper/2204.03111/) (2022)
- [Contextualizing Meta-Learning via Learning to Decompose](https://mlsanity.com/paper/2106.08112/) (2021)
- [Improving Deep Metric Learning by Divide and Conquer](https://mlsanity.com/paper/2109.04003/) (2021)
- [Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry](https://mlsanity.com/paper/2111.00905/) (2021)
- [Identifying Ambiguous Similarity Conditions via Semantic Matching](https://mlsanity.com/paper/2204.04053/) (2022)
- [SAT: Self-adaptive training for fashion compatibility prediction](https://mlsanity.com/paper/2206.12622/) (2022)
- [Transformer-based Graph Neural Networks for Outfit Generation](https://mlsanity.com/paper/2304.08098/) (2023)
- [Data-Side Efficiencies for Lightweight Convolutional Neural Networks](https://mlsanity.com/paper/2308.13057/) (2023)
- [Multi-modal Extreme Classification](https://mlsanity.com/paper/2309.04961/) (2023)
- [The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric](https://mlsanity.com/paper/2607.18237/) (2026)
- [Anchoring to Exemplars for Training Mixture-of-Expert Cell Embeddings](https://mlsanity.com/paper/2112.03208/) (2021)
- [FashionM3: Multimodal, Multitask, and Multiround Fashion Assistant based on Unified Vision-Language Model](https://mlsanity.com/paper/2504.17826/) (2025)
- [TATTOO: Training-free AesTheTic-aware Outfit recOmmendation](https://mlsanity.com/paper/2509.23242/) (2025)
- [Visual Knowledge Tracing](https://mlsanity.com/paper/2207.10157/) (2022)
- [VICTOR: Visual Incompatibility Detection with Transformers and Fashion-specific contrastive pre-training](https://mlsanity.com/paper/2207.13458/) (2022)
- [Lost Your Style? Navigating with Semantic-Level Approach for Text-to-Outfit Retrieval](https://mlsanity.com/paper/2311.02122/) (2023)
- [Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models](https://mlsanity.com/paper/2512.21860/) (2025)
- [Inductive learning for product assortment graph completion](https://mlsanity.com/paper/2110.01677/) (2021)
- [Recommendation of Compatible Outfits Conditioned on Style](https://mlsanity.com/paper/2203.16161/) (2022)

## Abstract (arXiv)

Many real-world tasks require models to compare images along multiple similarity conditions (e.g. similarity in color, category or shape). Existing methods often reason about these complex similarity relationships by learning condition-aware embeddings. While such embeddings aid models in learning different notions of similarity, they also limit their capability to generalize to unseen categories since they require explicit labels at test time. To address this deficiency, we propose an approach that jointly learns representations for the different similarity conditions and their contributions as a latent variable without explicit supervision. Comprehensive experiments across three datasets, Polyvore-Outfits, Maryland-Polyvore and UT-Zappos50k, demonstrate the effectiveness of our approach: our model outperforms the state-of-the-art methods, even those that are strongly supervised with pre-defined similarity conditions, on fill-in-the-blank, outfit compatibility prediction and triplet prediction tasks. Finally, we show that our model learns different visually-relevant semantic sub-spaces that allow it to generalize well to unseen categories.