# Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning

arXiv: https://arxiv.org/abs/2402.17510 · HTML: https://mlsanity.com/paper/2402.17510/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 60 of its 75 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 60)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)

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

- [MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data](https://mlsanity.com/paper/2603.09206/) (2026)
- [GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning](https://mlsanity.com/paper/2509.25026/) (2025)
- [Probing Mechanical Reasoning in Large Vision Language Models](https://mlsanity.com/paper/2410.00318/) (2024)
- [Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding](https://mlsanity.com/paper/2509.22437/) (2025)
- [Watch Before You Answer: Learning from Visually Grounded Post-Training](https://mlsanity.com/paper/2604.05117/) (2026)
- [Shortcut Learning Susceptibility in Vision Classifiers](https://mlsanity.com/paper/2502.09150/) (2025)
- [MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering](https://mlsanity.com/paper/2506.18071/) (2025)
- [Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance](https://mlsanity.com/paper/2509.05669/) (2025)
- [Confusion-Aware In-Context-Learning for Vision-Language Models in Robotic Manipulation](https://mlsanity.com/paper/2603.15134/) (2026)
- [Discriminative Axis, Not Data Volume: What a Contrastive Corpus Teaches an Audio Embedding](https://mlsanity.com/paper/2608.01560/) (2026)
- [Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization](https://mlsanity.com/paper/2509.05695/) (2025)
- [Contextualized Multimodal Lifelong Person Re-Identification in Hybrid Clothing States](https://mlsanity.com/paper/2509.11247/) (2025)
- [PragMatch: Separating Pragmatic Incongruity from Cross-Modal Mismatch in Large Vision-Language Models](https://mlsanity.com/paper/2608.09772/) (2026)
- [Prospective Prediction of OOD Degradation from Source-Side Training Dynamics](https://mlsanity.com/paper/2610.12397/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) mainly rely on contrastive training to learn general-purpose representations of images and captions. We focus on the situation when one image is associated with several captions, each caption containing both information shared among all captions and unique information per caption about the scene depicted in the image. In such cases, it is unclear whether contrastive losses are sufficient for learning task-optimal representations that contain all the information provided by the captions or whether the contrastive learning setup encourages the learning of a simple shortcut that minimizes contrastive loss. We introduce synthetic shortcuts for vision-language: a training and evaluation framework where we inject synthetic shortcuts into image-text data. We show that contrastive VLMs trained from scratch or fine-tuned with data containing these synthetic shortcuts mainly learn features that represent the shortcut. Hence, contrastive losses are not sufficient to learn task-optimal representations, i.e., representations that contain all task-relevant information shared between the image and associated captions. We examine two methods to reduce shortcut learning in our training and evaluation framework: (i) latent target decoding and (ii) implicit feature modification. We show empirically that both methods improve performance on the evaluation task, but only partly reduce shortcut learning when training and evaluating with our shortcut learning framework. Hence, we show the difficulty and challenge of our shortcut learning framework for contrastive vision-language representation learning.