paper-with-me

Papers

Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language

2023-06-28 · William Berrios, Gautam Mittal, Tristan Thrush, Douwe Kiela, Amanpreet Singh

We propose LENS, a modular approach for tackling computer vision problems by leveraging the power of large language models (LLMs). Our system uses a language model to reason over outputs from a set of independent and highly descriptive vision modules that provide exhaustive information about an image. We evaluate the approach on pure computer vision settings such as zero- and few-shot object recognition, as well as on vision and language problems. LENS can be applied to any off-the-shelf LLM and we find that the LLMs with LENS perform highly competitively with much bigger and much more sophisticated systems, without any multimodal training whatsoever. We open-source our code at https://github.com/ContextualAI/lens and provide an interactive demo.

📄 PDF Abstract BibTeX arXiv:2306.16410

Code (1)

contextualai/lens 공식 구현 pytorch

Tasks

DescriptiveLanguage ModelingLanguage ModellingObject Recognition

Similar Papers 제목 키워드 기반

Image Quality Is Not All You Want: Task-Driven Lens Design for Image Classification

2023-05-26 · Xinge Yang, Qiang Fu, Yunfeng Nie, Wolfgang Heidrich

In computer vision, it has long been taken for granted that high-quality images obtained through well-designed camera lenses would lead to superior results. However, we find that this common perception is not a "one-size…

Allimage-classificationImage Classification

ViT-Explainer: An Interactive Walkthrough of the Vision Transformer Pipeline

2026-04-02 · Juan Manuel Hernandez, Mariana Fernandez-Espinosa, Denis Parra, Diego Gomez-Zara arxiv

Transformer-based architectures have become the shared backbone of natural language processing and computer vision. However, understanding how these models operate remains challenging, particularly in vision settings, wh…

A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation

2023-06-12 · Jeremy Gwinnup, Kevin Duh

Large language models such as BERT and the GPT series started a paradigm shift that calls for building general-purpose models via pre-training on large datasets, followed by fine-tuning on task-specific datasets. There i…

Image CaptioningMachine TranslationMultimodal Machine TranslationQuestion Answering+2

Adaptive Camera Sensor for Vision Models

2025-03-04 · Eunsu Baek, Sunghwan Han, Taesik Gong, Hyung-Sin Kim

Domain shift remains a persistent challenge in deep-learning-based computer vision, often requiring extensive model modifications or large labeled datasets to address. Inspired by human visual perception, which adjusts i…

Exploring Data Pipelines through the Process Lens: a Reference Model forComputer Vision

2021-07-05 · Agathe Balayn, Bogdan Kulynych, Seda Guerses

Researchers have identified datasets used for training computer vision (CV) models as an important source of hazardous outcomes, and continue to examine popular CV datasets to expose their harms. These works tend to trea…