# Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training

arXiv: https://arxiv.org/abs/2301.02280 · HTML: https://mlsanity.com/paper/2301.02280/

## Key facts

- Cited by 91 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 64 of its 94 references that are in the map.
- First posted on arXiv 5 Jan 2023.

## 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 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [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)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)

## Built on by (most cited first, 30 of 91)

- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents](https://mlsanity.com/paper/2306.16527/) (2023)
- [SemDeDup: Data-efficient learning at web-scale through semantic deduplication](https://mlsanity.com/paper/2303.09540/) (2023)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement](https://mlsanity.com/paper/2504.07934/) (2025)
- [A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions](https://mlsanity.com/paper/2312.08578/) (2023)
- [Improving Multimodal Datasets with Image Captioning](https://mlsanity.com/paper/2307.10350/) (2023)
- [AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model](https://mlsanity.com/paper/2309.16058/) (2023)
- [Tag2Text: Guiding Vision-Language Model via Image Tagging](https://mlsanity.com/paper/2303.05657/) (2023)
- [An Inverse Scaling Law for CLIP Training](https://mlsanity.com/paper/2305.07017/) (2023)
- [Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic](https://mlsanity.com/paper/2404.07177/) (2024)
- [Verbs in Action: Improving verb understanding in video-language models](https://mlsanity.com/paper/2304.06708/) (2023)
- [ALIP: Adaptive Language-Image Pre-training with Synthetic Caption](https://mlsanity.com/paper/2308.08428/) (2023)
- [Open-Set Image Tagging with Multi-Grained Text Supervision](https://mlsanity.com/paper/2310.15200/) (2023)
- [COLA: A Benchmark for Compositional Text-to-image Retrieval](https://mlsanity.com/paper/2305.03689/) (2023)
- [CoVR-2: Automatic Data Construction for Composed Video Retrieval](https://mlsanity.com/paper/2308.14746/) (2023)
- [Multimodal Fusion on Low-quality Data: A Comprehensive Survey](https://mlsanity.com/paper/2404.18947/) (2024)
- [T-MARS: Improving Visual Representations by Circumventing Text Feature Learning](https://mlsanity.com/paper/2307.03132/) (2023)
- [Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision](https://mlsanity.com/paper/2504.02477/) (2025)
- [MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation](https://mlsanity.com/paper/2409.19483/) (2024)
- [MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation](https://mlsanity.com/paper/2403.20253/) (2024)
- [Effective pruning of web-scale datasets based on complexity of concept clusters](https://mlsanity.com/paper/2401.04578/) (2024)
- [Sieve: Multimodal Dataset Pruning Using Image Captioning Models](https://mlsanity.com/paper/2310.02110/) (2023)
- [Data curation via joint example selection further accelerates multimodal learning](https://mlsanity.com/paper/2406.17711/) (2024)
- [Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework](https://mlsanity.com/paper/2403.07636/) (2024)
- [Composed Video Retrieval via Enriched Context and Discriminative Embeddings](https://mlsanity.com/paper/2403.16997/) (2024)
- [Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval](https://mlsanity.com/paper/2505.19650/) (2025)
- [Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining](https://mlsanity.com/paper/2311.03964/) (2023)
- [CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination](https://mlsanity.com/paper/2408.09441/) (2024)

## Abstract (arXiv)

Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems. In this paper we improve the following three aspects of the contrastive pre-training pipeline: dataset noise, model initialization and the training objective. First, we propose a straightforward filtering strategy titled Complexity, Action, and Text-spotting (CAT) that significantly reduces dataset size, while achieving improved performance across zero-shot vision-language tasks. Next, we propose an approach titled Concept Distillation to leverage strong unimodal representations for contrastive training that does not increase training complexity while outperforming prior work. Finally, we modify the traditional contrastive alignment objective, and propose an importance-sampling approach to up-sample the importance of hard-negatives without adding additional complexity. On an extensive zero-shot benchmark of 29 tasks, our Distilled and Hard-negative Training (DiHT) approach improves on 20 tasks compared to the baseline. Furthermore, for few-shot linear probing, we propose a novel approach that bridges the gap between zero-shot and few-shot performance, substantially improving over prior work. Models are available at https://github.com/facebookresearch/diht.