Related papers: Fine-Grained Zero-Shot Learning with DNA as Side I…
We propose a scheme for supervised image classification that uses privileged information, in the form of keypoint annotations for the training data, to learn strong models from small and/or biased training sets. Our main motivation is the…
The zero-shot performance of existing vision-language models (VLMs) such as CLIP is limited by the availability of large-scale, aligned image and text datasets in specific domains. In this work, we leverage two complementary sources of…
Recognizing fine-grained categories remains a challenging task, due to the subtle distinctions among different subordinate categories, which results in the need of abundant annotated samples. To alleviate the data-hungry problem, we…
New categories can be discovered by transforming semantic features into synthesized visual features without corresponding training samples in zero-shot image classification. Although significant progress has been made in generating…
Convolutional neural networks require numerous data for training. Considering the difficulties in data collection and labeling in some specific tasks, existing approaches generally use models pre-trained on a large source domain (e.g.…
Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…
Learning to recognize novel visual categories from a few examples is a challenging task for machines in real-world industrial applications. In contrast, humans have the ability to discriminate even similar objects with little supervision.…
When training samples are scarce, the semantic embedding technique, ie, describing class labels with attributes, provides a condition to generate visual features for unseen objects by transferring the knowledge from seen objects. However,…
The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other. We note that existing methods implicitly address this requirement and leave it to…
Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…
Modern visual systems have a wide range of potential applications in vision tasks for natural science research, such as aiding in species discovery, monitoring animals in the wild, and so on. However, real-world vision tasks may experience…
In this paper, we address an open problem of zero-shot learning. Its principle is based on learning a mapping that associates feature vectors extracted from i.e. images and attribute vectors that describe objects and/or scenes of interest.…
Deep learning has significantly improved the precision of instance segmentation with abundant labeled data. However, in many areas like medical and manufacturing, collecting sufficient data is extremely hard and labeling this data requires…
Accurate classification of fine-grained images remains a challenge in backbones based on convolutional operations or self-attention mechanisms. This study proposes novel dual-current neural networks (DCNN), which combine the advantages of…
Named Entity Recognition (NER) frequently suffers from the problem of insufficient labeled data, particularly in fine-grained NER scenarios. Although $K$-shot learning techniques can be applied, their performance tends to saturate when the…
We develop a novel compositional generative model for zero- and few-shot learning to recognize fine-grained classes with a few or no training samples. Our key observation is that generating holistic features for fine-grained classes fails…
Contemporary deep learning techniques have made image recognition a reasonably reliable technology. However training effective photo classifiers typically takes numerous examples which limits image recognition's scalability and…
One-shot learning focuses on adapting pretrained models to recognize newly introduced and unseen classes based on a single labeled image. While variations of few-shot and zero-shot learning exist, one-shot learning remains a challenging yet…
As research interests in medical image analysis become increasingly fine-grained, the cost for extensive annotation also rises. One feasible way to reduce the cost is to annotate with coarse-grained superclass labels while using limited…
In this report we present an unsupervised image registration framework, using a pre-trained deep neural network as a feature extractor. We refer this to zero-shot learning, due to nonoverlap between training and testing dataset (none of the…