100 research outputs found
Talon cusp affecting primary dentition in two siblings: a case report
No full textThe term talon cusp refers to a rare developmental dental anomaly characterized by a cusp-like structure projecting from the cingulum area or cement-enamel junction. This condition can occur in the maxillary and mandibular arches of the primary and permanent dentitions. The purpose of this paper is to report on the presence of talon cusps in the primary dentition of two southern Chinese siblings. The 4 years and 2 months old girl had a talon cusp on her maxillary right primary central incisor, while her 2 years and 9 months old brother had bilateral talon cusps on the maxillary primary central incisors. The presence of this rare dental anomaly in two siblings has scarcely been reported in the literature and this may provide further evidence of a hereditary etiology.Article Link:
http://www.rjme.ro/RJME/resources/files/540113211213.pd
Structured Representation Learning for Visual Data
No full textVisual data like images and videos are characterized by high-dimensional and noisy samples that are hard to understand and reason upon. To support the effective processing of such data, classic machine learning approaches relied on meaningful crafted features from raw data to enhance the performance of downstream models. However, the manual design of features is a labor-intensive process that requires expertise in the domain of interest, making it economically and time-demanding.
Contrary to the human-engineered features approach, representation learning automatically discovers informative data representations that ease downstream processing in diverse applications.
This dissertation investigates new approaches and assumptions for representation learning in visual data, such as images or videos. Specifically, we focus on the application of deep learning techniques to uncover and interpret the spatial and causal structure inherent in visual information. The research is structured around three main questions, each addressing a different aspect of visual data, such as what information to preserve, how to structure it, and how to adapt to new data.
The first part of the thesis addresses the challenge of reconstructing the spatial structure from unordered visual parts. We introduce GANZZLE and GANZZLE++ that overcome the combinatorial complexity of puzzles using a generative approach to estimate the global solution. Contrary to other deep learning solutions, the approaches can handle a variable number of pieces.
The second section of the thesis explores the organization and structuring of image representations. It delves into the concept of disentanglement in data representation, aiming to align the learned representation with the data generative process. We develop new strategies that facilitate the disentanglement process, enhancing the interpretability of the representation.
Finally, the thesis examines the adaptability of structured representations to new and unseen environments. We present DECAF, a novel framework that alters existing representations to address a new, different environment. This approach highlights the importance of modular causal representations for re-usability and composition of available knowledge
GANzzle + + : Generative approaches for jigsaw puzzle solving as local to global assignment in latent spatial representations
No full textJigsaw puzzles are a popular and enjoyable pastime that humans can easily solve, even with many pieces. However, solving a jigsaw is a combinatorial problem, and the space of possible solutions is exponential in the number of pieces, intractable for pairwise solutions. In contrast to the classical pairwise local matching of pieces based on edge heuristics, we estimate an approximate solution image, i.e., a mental image, of the puzzle and exploit it to guide the placement of pieces as a piece-to-global assignment problem. Therefore, from unordered pieces, we consider conditioned generation approaches, including Generative Adversarial Networks (GAN) models, Slot Attention (SA) and Vision Transformers (ViT), to recover the solution image. Given the generated solution representation, we cast the jigsaw solving as a 1-to-1 assignment matching problem using Hungarian attention, which places pieces in corresponding positions in the global solution estimate. Results show that the newly proposed GANzzle-SA and GANzzle-VIT benefit from the early fusion strategy where pieces are jointly compressed and gathered for global structure recovery. A single deep learning model generalizes to puzzles of different sizes and improves the performances by a large margin. Evaluated on PuzzleCelebA and PuzzleWikiArts, our approaches bridge the gap of deep learning strategies with respect to optimization-based classic puzzle solvers
Talon, Omer
No full textInternational audienceOmer Talon was a French humanist and author of books on rhetoric. He was a close friend and colleague of Petrus Ramus
Seeing the Abstract: Translating the Abstract Language for Vision Language Models
No full textNatural language goes beyond dryly describing visual content. It contains rich abstract concepts to express feeling, creativity and properties that cannot be directly perceived. Yet, current research in Vision Language Models (VLMs) has not shed light on abstract-oriented language. Our research breaks new ground by uncovering its wide presence and under-estimated value, with extensive analysis. Particularly, we focus our investigation on the fashion domain, a highly-representative field with abstract expressions. By analyzing recent large-scale multimodal fashion datasets, we find that abstract terms have a dominant presence, rivaling the concrete ones, providing novel information, and being useful in the retrieval task. However, a critical challenge emerges: current general-purpose or fashion-specific VLMs are pre-trained with databases that lack sufficient abstract words in their text corpora, thus hindering their ability to effectively represent abstract-oriented language. We propose a training-free and model-agnostic method, Abstract-to-Concrete Translator (ACT), to shift abstract representations towards well-represented concrete ones in the VLM latent space, using pre-trained models and existing multi-modal databases. On the text-to-image retrieval task, despite being training-free, ACT outperforms the fine-tuned VLMs in both same- and cross-dataset settings, exhibiting its effectiveness with a strong generalization capability. Moreover, the improvement introduced by ACT is consistent with various VLMs, making it a plug-and-play solution
Evaluating Attribute Confusion in Fashion Text-to-Image Generation
No full textDespite the rapid advances in Text-to-Image (T2I) generation models, their evaluation remains challenging in domains like fashion, involving complex compositional generation. Recent automated T2I evaluation methods leverage pre-trained vision-language models to measure cross-modal alignment. However, our preliminary study reveals that they are still limited in assessing rich entity-attribute semantics, facing challenges in attribute confusion, i.e., when attributes are correctly depicted but associated to the wrong entities. To address this, we build on a Visual Question Answering (VQA) localization strategy targeting one single entity at a time across both visual and textual modalities. We propose a localized human evaluation protocol and introduce a novel automatic metric, Localized VQAScore (L-VQAScore), that combines visual localization with VQA probing both correct (reflection) and miss-localized (leakage) attribute generation. On a newly curated dataset featuring challenging compositional alignment scenarios, L-VQAScore outperforms state-of-the-art T2I evaluation methods in terms of correlation with human judgments, demonstrating its strength in capturing fine-grained entity-attribute associations. We believe L-VQAScore can be a reliable and scalable alternative to subjective evaluations
One VLM to Keep it Learning: Generation and Balancing for Data-free Continual Visual Question Answering
No full textVision-Language Models (VLMs) have shown significant promise in Visual Question Answering (VQA) tasks by leveraging web-scale multimodal datasets. However, these models often struggle with continual learning due to catastrophic forgetting when adapting to new tasks. As an effective remedy to mitigate catastrophic forgetting, rehearsal strategy uses the data of past tasks upon learning new task. However, such strategy incurs the need of storing past data, which might not be feasible due to hardware constraints or privacy concerns. In this work, we propose the first data-free method that leverages the language generation capability of a VLM, instead of relying on external models, to produce pseudo-rehearsal data for addressing continual VQA. Our proposal, named as GaB, generates pseudo-rehearsal data by posing previous task questions on new task data. Yet, despite being effective, the distribution of generated questions skews towards the most frequently posed questions due to the limited and task-specific training data. To mitigate this issue, we introduce a pseudo-rehearsal balancing module that aligns the generated data towards the ground-truth data distribution using either the question meta-statistics or an unsupervised clustering method. We evaluate our proposed method on two recent benchmarks, i.e. VQACL- VQAv2 and CLOVE-function benchmarks. GaB outperforms all the data-free baselines with substantial improvement in maintaining VQA performance across evolving tasks, while being on-par with methods with access to the past data. Code and models are available at https://github.com/Deepayan137/GaB
Talon cusps in mandibular incisors: Report of eight rare cases
No full textTalon cusps in mandibular anterior teeth are very rare. Talon cusps in mandibular anterior teeth associated with other anomalies are even rarer and that a bilateral case in the mandible has not been reported before. In this report, eight such rare cases of talon cusps in permanent mandibular incisors are presented. It includes a bilateral case that in the author′s knowledge is the first case reported in the English literatures
Management of a permanent lateral incisor with a talon cusp and immature apex : a case report
No full textDATA AVAILABILITY STATEMENT :
The data that support the findings of this study are
available from the corresponding author upon reasonable
request.This case report focuses on the diagnosis and treatment of a maxillary lateral
incisor affected by a talon cusp, a rare developmental dental anomaly. The case
presented with irreversible pulpitis and an immature apex. The article discusses
the prevalence, etiology, classification, and treatment options for talon cusps,
highlighting their clinical significance and potential complications. Clinical
and radiographic findings obtained from a periapical radiograph and a cone-beam
computed tomography (CBCT) scan are outlined. The treatment approach
involved the removal of the talon cusp, endodontic therapy including apexification
with mineral trioxide aggregate, and aesthetic restoration of the tooth. The report
underscores the value of precise diagnosis, careful treatment planning, and the
utility of CBCT scans in effectively managing talon cusps.http://wileyonlinelibrary.com/journal/ccr3am2024OdontologySDG-03:Good heatlh and well-bein
LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing
No full textFashion design is a complex creative process that blends visual and textual expressions. Designers convey ideas through sketches, which define spatial structure and design elements, and textual descriptions, capturing material, texture, and stylistic details. In this paper, we present LOcalized Text and Sketch for fashion image generation (LOTS), an approach for compositional sketch-text based generation of complete fashion outlooks. LOTS leverages a global description with paired localized sketch + text information for conditioning and introduces a novel step-based merging strategy for diffusion adaptation. First, a Modularized Pair-Centric representation encodes sketches and text into a shared latent space while preserving independent localized features; then, a Diffusion Pair Guidance phase integrates both local and global conditioning via attention-based guidance within the diffusion model’s multi-step denoising process. To validate our method, we build on Fashionpedia to release Sketchy, the first fashion dataset where multiple text-sketch pairs are provided per image. Quantitative results show LOTS achieves state-of-the-art image generation performance on both global and localized metrics, while qualitative examples and a human evaluation study highlight its unprecedented level of design customization
- …
