Related papers: Generative One-Class Models for Text-based Person …

Generative modeling, which learns joint probability distribution from data and generates samples according to it, is an important task in machine learning and artificial intelligence. Inspired by probabilistic interpretation of quantum…

Scene text detection techniques have garnered significant attention due to their wide-ranging applications. However, existing methods have a high demand for training data, and obtaining accurate human annotations is labor-intensive and…

Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…

This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting…

With the recent exhibited strength of generative diffusion models, an open research question is if images generated by these models can be used to learn better visual representations. While this generative data expansion may suffice for…

In this paper, we investigate the problem of retrieving images from a database based on a multi-modal (image-text) query. Specifically, the query text prompts some modification in the query image and the task is to retrieve images with the…

Given a natural language description, text-based person retrieval aims to identify images of a target person from a large-scale person image database. Existing methods generally face a \textbf{color over-reliance problem}, which means that…

Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such…

Text infilling is defined as a task for filling in the missing part of a sentence or paragraph, which is suitable for many real-world natural language generation scenarios. However, given a well-trained sequential generative model,…

Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…

Text-based person search is a sub-task in the field of image retrieval, which aims to retrieve target person images according to a given textual description. The significant feature gap between two modalities makes this task very…

Realizing when a model is right for a wrong reason is not trivial and requires a significant effort by model developers. In some cases an input salience method, which highlights the most important parts of the input, may reveal problematic…

Image classifiers should be used with caution in the real world. Performance evaluated on a validation set may not reflect performance in the real world. In particular, classifiers may perform well for conditions that are frequently…

Joint machine learning models that allow synthesizing and classifying data often offer uneven performance between those tasks or are unstable to train. In this work, we depart from a set of empirical observations that indicate the…

The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or…

In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) purpose. We propose a new end-to-end model that jointly…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

We present FlowDet, the first formulation of object detection using modern Conditional Flow Matching techniques. This work follows from DiffusionDet, which originally framed detection as a generative denoising problem in the bounding box…

With the rise of generative language models, machine-generated text detection has become a critical challenge. A wide variety of models is available, but inconsistent datasets, evaluation metrics, and assessment strategies obscure…

We demonstrate in this paper that a generative model can be designed to perform classification tasks under challenging settings, including adversarial attacks and input distribution shifts. Specifically, we propose a conditional variational…