# Contrastive Learning with Enhanced Abstract Representations using Grouped Loss of Abstract Semantic Supervision

arXiv: https://arxiv.org/abs/2509.12771 · HTML: https://mlsanity.com/paper/2509.12771/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 58 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 30 of 42)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [BREEDS: Benchmarks for Subpopulation Shift](https://mlsanity.com/paper/2008.04859/) (2020)
- [Hyperbolic Image-Text Representations](https://mlsanity.com/paper/2304.09172/) (2023)
- [Representation Learning by Learning to Count](https://mlsanity.com/paper/1708.06734/) (2017)
- [Parametric Classification for Generalized Category Discovery: A Baseline Study](https://mlsanity.com/paper/2211.11727/) (2022)
- [Waffling around for Performance: Visual Classification with Random Words and Broad Concepts](https://mlsanity.com/paper/2306.07282/) (2023)
- [Dynamic Conceptional Contrastive Learning for Generalized Category Discovery](https://mlsanity.com/paper/2303.17393/) (2023)
- [Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training](https://mlsanity.com/paper/2301.02280/) (2023)
- [NV-Retriever: Improving text embedding models with effective hard-negative mining](https://mlsanity.com/paper/2407.15831/) (2024)
- [Hard negative examples are hard, but useful](https://mlsanity.com/paper/2007.12749/) (2020)
- [HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention](https://mlsanity.com/paper/2303.02995/) (2023)
- [Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding](https://mlsanity.com/paper/2306.08832/) (2023)
- [Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens](https://mlsanity.com/paper/2303.14865/) (2023)
- [Active Generalized Category Discovery](https://mlsanity.com/paper/2403.04272/) (2024)
- [Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery](https://mlsanity.com/paper/2403.07369/) (2024)
- [Federated Generalized Category Discovery](https://mlsanity.com/paper/2305.14107/) (2023)
- [Open-world machine learning: A review and new outlooks](https://mlsanity.com/paper/2403.01759/) (2024)

## Abstract (arXiv)

Humans can recognize an image as an instance of a general concept, beyond simply identifying its objects and their relationships. In this paper, we investigate 1. The extent to which VLMs have this concept abstraction capacity, and 2. Strategies for encoding the sort of higher-concept information in images that would enable the resulting VLM model (CLEAR GLASS model) to have this capability to a greater degree. To this end, we introduce a grouped image-caption dataset (MAGIC), which consists of several groups of image captions and for each group a set of associated images and higher-level conceptual labels. We use a novel contrastive loss technique to induce the model to encode in the representation of each image (caption) in a group the information that is common to all members of the image-caption group. Our main contribution is a grouped contrastive loss function based on text-image contrastive groups (outer contrastive loss) as well as an inner loss which measures the distances between image-caption instances in the group. Our training methodology results in the CLEAR GLASS model having the concept abstraction capacity as an emergent capacity because the model is not exposed to the higher-level concepts associated with each group. Instead, the training forces the model to create for each image-caption group a semantic representation that brings it closer to the semantic representation of the higher-level concepts in the latent semantic space. Our experiments show that this training methodology results in a model which shows improvement in abstract concept recognition compared to SOTA models.