De novo peptide sequencing aims to recover amino acid sequences of a peptide from tandem mass spectrometry (MS) data.
Experimenting on three 3D point cloud recognition backbones (PointNet, DGCNN, and PointConv) and synthetic (ModelNet40, ModelNet10) and real scanned (ScanObjectNN) datasets, we establish new baseline results on learning without forgetting for 3D data.
Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner.
In this paper, we propose addressing this problem using a mixture of subspaces.
Instead of constraining the translation process by using a reference image, the users can command the model to retouch the generated images by involving the semantic information in the generation process.
A plethora of research in the literature shows how human eye fixation pattern varies depending on different factors, including genetics, age, social functioning, cognitive functioning, and so on.
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference.
Ranked #1 on Zero-Shot Object Detection on PASCAL VOC'07
Smiles play a vital role in the understanding of social interactions within different communities, and reveal the physical state of mind of people in both real and deceptive ways.
Any-shot detection offers unique challenges compared to conventional novel object detection such as, a high imbalance between unseen, few-shot and seen object classes, susceptibility to forget base-training while learning novel classes and distinguishing novel classes from the background.
This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification.
To the best of our knowledge, we are the first to propose a transductive zero-shot object detection approach that convincingly reduces the domain-shift and model-bias against unseen classes.
In this paper, we therefore propose a loss to specifically address the hubness problem.
This setting gives rise to the need for correct alignment between visual and semantic concepts, so that the unseen objects can be identified using only their semantic attributes.
Ranked #1 on Zero-Shot Object Detection on MS-COCO
Deep neural networks (DNNs) can be easily fooled by adding human imperceptible perturbations to the images.
In-line with the success of deep learning on traditional recognition problem, several end-to-end deep models for zero-shot recognition have been proposed in the literature.
We hypothesize that this setting is ill-suited for real-world applications where unseen objects appear only as a part of a complex scene, warranting both the `recognition' and `localization' of an unseen category.
Ranked #2 on Zero-Shot Object Detection on ImageNet Detection
Then, it learns how to combine these directions to obtain the principal direction for each unseen class such that the CAPD of the test image is aligned with the semantic embedding of the true class, and opposite to the other classes.