Related papers: Free-Grained Hierarchical Visual Recognition

For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in…

When faced with learning challenging new tasks, humans often follow sequences of steps that allow them to incrementally build up the necessary skills for performing these new tasks. However, in machine learning, models are most often…

Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be…

Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing objects of novel classes unseen during training still remains challenging. The…

Over the past decade, deep neural networks have proven to be adept in image classification tasks, often surpassing humans in terms of accuracy. However, standard neural networks often fail to understand the concept of hierarchical…

Strong image search models can be learned for a specific domain, ie. set of labels, provided that some labeled images of that domain are available. A practical visual search model, however, should be versatile enough to solve multiple…

A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs. Whilst the number of photos can be…

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention.…

Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abundant images with reliable labels and effective learning…

People typically learn through exposure to visual concepts associated with linguistic descriptions. For instance, teaching visual object categories to children is often accompanied by descriptions in text or speech. In a machine learning…

Automatic plant classification is a challenging problem due to the wide biodiversity of the existing plant species in a fine-grained scenario. Powerful deep learning architectures have been used to improve the classification performance in…

The rapid development of deep learning has made a great progress in image segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithms mostly rely on the availability of pixel-level…

This paper presents experiments extending the work of Ba et al. (2014) on recurrent neural models for attention into less constrained visual environments, specifically fine-grained categorization on the Stanford Dogs data set. In this work…

Learning an empirically effective model with generalization using limited data is a challenging task for deep neural networks. In this paper, we propose a novel learning framework called PurifiedLearning to exploit task-irrelevant features…

In recent years, simultaneous learning of multiple dense prediction tasks with partially annotated label data has emerged as an important research area. Previous works primarily focus on leveraging cross-task relations or conducting…

Vision-language models (VLMs) like CLIP have been cherished for their ability to perform zero-shot visual recognition on open-vocabulary concepts. This is achieved by selecting the object category whose textual representation bears the…

Supervision for metric learning has long been given in the form of equivalence between human-labeled classes. Although this type of supervision has been a basis of metric learning for decades, we argue that it hinders further advances in…

Self-driving vehicles must perceive and predict the future positions of nearby actors in order to avoid collisions and drive safely. A learned deep learning module is often responsible for this task, requiring large-scale, high-quality…

Deep learning for Earth imagery plays an increasingly important role in geoscience applications such as agriculture, ecology, and natural disaster management. Still, progress is often hindered by the limited training labels. Given Earth…

Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases. To accommodate such requirements, we…