Related papers: Fine-Grained Zero-Shot Learning with DNA as Side I…
One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images. Recent work has shown that learning from textual descriptions, such as Wikipedia articles, avoids the problem of…
Prototypical networks have been shown to perform well at few-shot learning tasks in computer vision. Yet these networks struggle when classes are very similar to each other (fine-grain classification) and currently have no way of taking…
This work introduces a model that can recognize objects in images even if no training data is available for the objects. The only necessary knowledge about the unseen categories comes from unsupervised large text corpora. In our zero-shot…
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs). Many popular methods impose deep supervision to perform…
We propose a zero-shot learning relation classification (ZSLRC) framework that improves on state-of-the-art by its ability to recognize novel relations that were not present in training data. The zero-shot learning approach mimics the way…
Fine-grained classification of microscopic image data with limited samples is an open problem in computer vision and biomedical imaging. Deep learning based vision systems mostly deal with high number of low-resolution images, whereas…
High-throughput screening using automated microscopes is a key driver in biopharma drug discovery, enabling the parallel evaluation of thousands of drug candidates for diseases such as cancer. Traditional image analysis and deep learning…
Data-efficient image classification is a challenging task that aims to solve image classification using small training data. Neural network-based deep learning methods are effective for image classification, but they typically require…
Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative…
Computer vision based fine-grained recognition has received great attention in recent years. Existing works focus on discriminative part localization and feature learning. In this paper, to improve the performance of fine-grained…
Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…
There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large. This makes end-to-end supervised training of a recognition system impractical as no training set is…
The aim of fine-grained recognition is to identify sub-ordinate categories in images like different species of birds. Existing works have confirmed that, in order to capture the subtle differences across the categories, automatic…
In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distribution which makes it hard for the…
Deep learning is a data-hungry approach, which requires massive training data. However, it is time-consuming and labor-intensive to collect abundant fully-annotated training data for all categories. Assuming the existence of base categories…
Convolutional neural networks are able to learn realistic image priors from numerous training samples in low-level image generation and restoration. We show that, for high-level image recognition tasks, we can further reconstruct…
We address the difficult problem of distinguishing fine-grained object categories in low resolution images. Wepropose a simple an effective deep learning approach that transfers fine-grained knowledge gained from high resolution training…
Fine-grained classification is a relatively new field that has concentrated on using information from a single image, while ignoring the enormous potential of using video data to improve classification. In this work we present the novel…
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by generating either…
Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the attribute. In this paper, we put forth a new GZSL technique that improves the GZSL classification performance greatly.…