# ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks

arXiv: https://arxiv.org/abs/2402.17298 · HTML: https://mlsanity.com/paper/2402.17298/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 59 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic](https://mlsanity.com/paper/2111.14447/) (2021)
- [CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment](https://mlsanity.com/paper/2203.07190/) (2022)
- [Text-Only Training for Image Captioning using Noise-Injected CLIP](https://mlsanity.com/paper/2211.00575/) (2022)
- [Language Models Can See: Plugging Visual Controls in Text Generation](https://mlsanity.com/paper/2205.02655/) (2022)
- [DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training](https://mlsanity.com/paper/2303.03032/) (2023)
- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning](https://mlsanity.com/paper/2303.05952/) (2023)
- [VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions](https://mlsanity.com/paper/1803.07464/) (2018)
- [Connecting Multi-modal Contrastive Representations](https://mlsanity.com/paper/2305.14381/) (2023)

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

- [Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models](https://mlsanity.com/paper/2602.07026/) (2026)
- [Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning](https://mlsanity.com/paper/2410.01529/) (2024)
- [Text-Only Data Synthesis for Vision Language Model Training](https://mlsanity.com/paper/2503.22655/) (2025)
- [Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction](https://mlsanity.com/paper/2512.04309/) (2025)

## Abstract (arXiv)

"A data scientist is tasked with developing a low-cost surgical VQA system for a 2-month workshop. Due to data sensitivity, she collects 50 hours of surgical video from a hospital, requiring two months for privacy approvals. Privacy restrictions prevent uploading data to platforms like ChatGPT, so she assembles one annotator and a medical expert to manually create QA pairs. This process takes three weeks and costs over 10,000. The trained model provides accurate responses within the limited data scope but lacks broader generalizability, completing the project in 3 months." To simplify the challenges presented in the scenario above. In this paper, we replace the image input with text for Vision-language training. Inspired by prior noise injection methods to reduce modality gaps, we introduce Adaptive ranged cosine Similarity injected noise (ArcSin). First, we introduce an innovative adaptive noise scale that effectively generates the textual elements with more variability while preserving the original text feature's integrity. Second, a similarity pool strategy is employed, expanding the domain generalization potential by broadening the overall noise scale. This dual strategy effectively broadens the scope of the original domain while safeguarding content integrity. Our empirical results demonstrate that these models closely rival those trained on images in terms of performance. Specifically, our method exhibits substantial improvements over the previous state-of-the-art, achieving gains of 1.9 and 1.1 CIDEr points in S-Cap and M-Cap, respectively. Additionally, we observe increases of 0.5 percentage points (pp), 1.4 pp, and 1.4 pp in accuracy for VQA, VQA-E, and VE, respectively, pushing the boundaries of what is achievable within the constraints of image-trained model benchmarks.