# Identifying Ambiguous Similarity Conditions via Semantic Matching

arXiv: https://arxiv.org/abs/2204.04053 · HTML: https://mlsanity.com/paper/2204.04053/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 8 Apr 2022.

## Builds on (most cited first, 25 of 25)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Forward Compatible Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2203.06953/) (2022)
- [Zero-Shot Learning via Semantic Similarity Embedding](https://mlsanity.com/paper/1509.04767/) (2015)
- [Learning Type-Aware Embeddings for Fashion Compatibility](https://mlsanity.com/paper/1803.09196/) (2018)
- [Conditional Image-Text Embedding Networks](https://mlsanity.com/paper/1711.08389/) (2017)
- [Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images](https://mlsanity.com/paper/1612.06341/) (2016)
- [Fashion Outfit Complementary Item Retrieval](https://mlsanity.com/paper/1912.08967/) (2019)
- [Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly](https://mlsanity.com/paper/1801.04815/) (2018)
- [Learning Similarity Conditions Without Explicit Supervision](https://mlsanity.com/paper/1908.08589/) (2019)
- [The Group Loss for Deep Metric Learning](https://mlsanity.com/paper/1912.00385/) (2019)
- [Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks](https://mlsanity.com/paper/2009.10235/) (2020)
- [Neural Similarity Learning](https://mlsanity.com/paper/1910.13003/) (2019)
- [Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning](https://mlsanity.com/paper/2104.02429/) (2021)
- [Contextual Visual Similarity](https://mlsanity.com/paper/1612.02534/) (2016)

## Built on by (most cited first, 4 of 4)

- [Parrot: Multilingual Visual Instruction Tuning](https://mlsanity.com/paper/2406.02539/) (2024)
- [Improved Diversity-Promoting Collaborative Metric Learning for Recommendation](https://mlsanity.com/paper/2409.01012/) (2024)
- [C-STS: Conditional Semantic Textual Similarity](https://mlsanity.com/paper/2305.15093/) (2023)
- [Faith: An Efficient Framework for Transformer Verification on GPUs](https://mlsanity.com/paper/2209.12708/) (2022)

## Abstract (arXiv)

Rich semantics inside an image result in its ambiguous relationship with others, i.e., two images could be similar in one condition but dissimilar in another. Given triplets like "aircraft" is similar to "bird" than "train", Weakly Supervised Conditional Similarity Learning (WS-CSL) learns multiple embeddings to match semantic conditions without explicit condition labels such as "can fly". However, similarity relationships in a triplet are uncertain except providing a condition. For example, the previous comparison becomes invalid once the conditional label changes to "is vehicle". To this end, we introduce a novel evaluation criterion by predicting the comparison's correctness after assigning the learned embeddings to their optimal conditions, which measures how much WS-CSL could cover latent semantics as the supervised model. Furthermore, we propose the Distance Induced Semantic COndition VERification Network (DiscoverNet), which characterizes the instance-instance and triplets-condition relations in a "decompose-and-fuse" manner. To make the learned embeddings cover all semantics, DiscoverNet utilizes a set module or an additional regularizer over the correspondence between a triplet and a condition. DiscoverNet achieves state-of-the-art performance on benchmarks like UT-Zappos-50k and Celeb-A w.r.t. different criteria.