Related papers: GTNet: Generative Transfer Network for Zero-Shot O…
Recent object detection models require large amounts of annotated data for training a new classes of objects. Few-shot object detection (FSOD) aims to address this problem by learning novel classes given only a few samples. While…
The goal of zero-shot learning (ZSL) is to train a model to classify samples of classes that were not seen during training. To address this challenging task, most ZSL methods relate unseen test classes to seen(training) classes via a…
Convolutional Neural Networks (CNNs) are commonly designed for closed set arrangements, where test instances only belong to some "Known Known" (KK) classes used in training. As such, they predict a class label for a test sample based on the…
Sketch-based 3D shape retrieval is a challenging task due to the large domain discrepancy between sketches and 3D shapes. Since existing methods are trained and evaluated on the same categories, they cannot effectively recognize the…
Infrared-visible object detection (IVOD) seeks to harness the complementary information in infrared and visible images, thereby enhancing the performance of detectors in complex environments. However, existing methods often neglect the…
In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training. We focus on the transductive setting, in which unlabelled visual data from unseen…
When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs…
Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen classes with labels…
The goal of multi-modal learning is to use complimentary information on the relevant task provided by the multiple modalities to achieve reliable and robust performance. Recently, deep learning has led significant improvement in multi-modal…
Most existing point cloud based 3D object detectors focus on the tasks of classification and box regression. However, another bottleneck in this area is achieving an accurate detection confidence for the Non-Maximum Suppression (NMS)…
Zero shot learning in Image Classification refers to the setting where images from some novel classes are absent in the training data but other information such as natural language descriptions or attribute vectors of the classes are…
Images generated by most of generative models trained with limited data often exhibit deficiencies in either fidelity, diversity, or both. One effective solution to address the limitation is few-shot generative model adaption. However, the…
Although zero-shot learning (ZSL) has an inferential capability of recognizing new classes that have never been seen before, it always faces two fundamental challenges of the cross modality and crossdomain challenges. In order to alleviate…
Visual cognition of primates is superior to that of artificial neural networks in its ability to 'envision' a visual object, even a newly-introduced one, in different attributes including pose, position, color, texture, etc. To aid neural…
Recent works on two-stage cross-domain detection have widely explored the local feature patterns to achieve more accurate adaptation results. These methods heavily rely on the region proposal mechanisms and ROI-based instance-level features…
Existing semantic segmentation models heavily rely on dense pixel-wise annotations. To reduce the annotation pressure, we focus on a challenging task named zero-shot semantic segmentation, which aims to segment unseen objects with zero…
Zero-shot personalized image generation models aim to produce images that align with both a given text prompt and subject image, requiring the model to incorporate both sources of guidance. Existing methods often struggle to capture…
Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unrestricted adversarial…
In view of the problems that existing salient object detection (SOD) methods are prone to losing details, blurring edges, and insufficient fusion of single-modal information in complex scenes, this paper proposes a dynamic uncertainty…
Nowadays, there are plenty of works introducing convolutional neural networks (CNNs) to the steganalysis and exceeding conventional steganalysis algorithms. These works have shown the improving potential of deep learning in information…