Related papers: The MixCount Dataset: Bridging the Data Gap for Op…
This paper introduces MixTex, an end-to-end LaTeX OCR model designed for low-bias multilingual recognition, along with its novel data collection method. In applying Transformer architectures to LaTeX text recognition, we identified specific…
Major advancements in computer vision can primarily be attributed to the use of labeled datasets. However, acquiring labels for datasets often results in errors which can harm model performance. Recent works have proposed methods to…
A coreset is a subset of the training set, using which a machine learning algorithm obtains performances similar to what it would deliver if trained over the whole original data. Coreset discovery is an active and open line of research as…
Numerosity remains a challenge for state-of-the-art text-to-image generation models like FLUX and GPT-4o, which often fail to accurately follow counting instructions in text prompts. In this paper, we aim to study a fundamental yet often…
Computer vision-based deep learning object detection algorithms have been developed sufficiently powerful to support the ability to recognize various objects. Although there are currently general datasets for object detection, there is…
This paper proposes a dataset augmentation method by fine-tuning pre-trained diffusion models. Generating images using a pre-trained diffusion model with textual conditioning often results in domain discrepancy between real data and…
Recently, semantic segmentation models trained with image-level text supervision have shown promising results in challenging open-world scenarios. However, these models still face difficulties in learning fine-grained semantic alignment at…
Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric…
Current object detectors often suffer significant perfor-mance degradation in real-world applications when encountering distributional shifts. Consequently, the out-of-distribution (OOD) generalization capability of object detectors has…
Despite the numerous developments in object tracking, further development of current tracking algorithms is limited by small and mostly saturated datasets. As a matter of fact, data-hungry trackers based on deep-learning currently rely on…
State-of-the-art large language and vision models are trained over trillions of tokens that are aggregated from a large variety of sources. As training data collections grow, manually managing the samples becomes time-consuming, tedious,…
We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…
Common object counting in a natural scene is a challenging problem in computer vision with numerous real-world applications. Existing image-level supervised common object counting approaches only predict the global object count and rely on…
Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy…
High-quality annotations are essential for object detection models, but ensuring label accuracy - especially for bounding boxes - remains both challenging and costly. This paper introduces ClipGrader, a novel approach that leverages…
MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the application of MixUp to the natural language understanding…
Deep learning on an edge device requires energy efficient operation due to ever diminishing power budget. Intentional low quality data during the data acquisition for longer battery life, and natural noise from the low cost sensor degrade…
The number of objects is considered an important factor in a variety of tasks in the agricultural domain. Automated counting can improve farmers decisions regarding yield estimation, stress detection, disease prevention, and more. In recent…
Recently, detection of label errors and improvement of label quality in datasets for supervised learning tasks has become an increasingly important goal in both research and industry. The consequences of incorrectly annotated data include…
Visible images offer rich texture details, while infrared images emphasize salient targets. Fusing these complementary modalities enhances scene understanding, particularly for advanced vision tasks under challenging conditions. Recently,…