Related papers: Describing Differences in Image Sets with Natural …
Personalized image generation aims to faithfully preserve a reference subject's identity while adapting to diverse text prompts. Existing optimization-based methods ensure high fidelity but are computationally expensive, while…
A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a…
Text-to-image diffusion models achieved a remarkable leap in capabilities over the last few years, enabling high-quality and diverse synthesis of images from a textual prompt. However, even the most advanced models often struggle to…
Clothes-changing person re-identification (CC-ReID) aims to recognize individuals under different clothing scenarios. Current CC-ReID approaches either concentrate on modeling body shape using additional modalities including silhouette,…
Discriminativeness is a desirable feature of image captions: captions should describe the characteristic details of input images. However, recent high-performing captioning models, which are trained with reinforcement learning (RL), tend to…
The performance of machine learning models relies heavily on the quality of input data, yet real-world applications often face significant data-related challenges. A common issue arises when curating training data or deploying models: two…
Large-scale diffusion-based generative models have led to breakthroughs in text-conditioned high-resolution image synthesis. Starting from random noise, such text-to-image diffusion models gradually synthesize images in an iterative fashion…
We study the problem of (learning) algorithm comparison, where the goal is to find differences between models trained with two different learning algorithms. We begin by formalizing this goal as one of finding distinguishing feature…
The problem of distinguishing natural images from photo-realistic computer-generated ones either addresses natural images versus computer graphics or natural images versus GAN images, at a time. But in a real-world image forensic scenario,…
The detection of manufacturing errors is crucial in fabrication processes to ensure product quality and safety standards. Since many defects occur very rarely and their characteristics are mostly unknown a priori, their detection is still…
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…
Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be both faithful and…
For long time, person re-identification and image search are two separately studied tasks. However, for person re-identification, the effectiveness of local features and the "query-search" mode make it well posed for image search…
Advances in Natural Language Processing (NLP) have revolutionized the way researchers and practitioners address crucial societal problems. Large language models are now the standard to develop state-of-the-art solutions for text detection…
Images can be described in terms of the objects they contain, or in terms of the types of scene or place that they instantiate. In this paper we address to what extent pretrained Vision and Language models can learn to align descriptions of…
Contrastive Language-Image Pre-training (CLIP) formulates image classification as an image-to-text matching task, i.e., matching images to the corresponding natural language descriptions instead of discrete category IDs. This allows for…
We describe a novel approach to image based localisation in urban environments using semantic matching between images and a 2-D map. It contrasts with the vast majority of existing approaches which use image to image database matching. We…
Image captioning is a widely known problem in the area of AI. Caption generation from floor plan images has applications in indoor path planning, real estate, and providing architectural solutions. Several methods have been explored in…
While different language models are ubiquitous in NLP, it is hard to contrast their outputs and identify which contexts one can handle better than the other. To address this question, we introduce LMdiff, a tool that visually compares…
The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of…