Any-Shot Object Detection

Rahman, Shafin; Khan, Salman; Barnes, Nick; Khan, Fahad Shahbaz

doi:10.1007/978-3-030-69535-4_6

Cited by 15 publications

(12 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning without forgetting using word vectors: Word vectors have shown promising success on various computer vision tasks such as zero-shot learning, few-shot learning, image/video captioning and visual question answering [15,29,39,43,9,46,47,6,5,7]. Lately, some works [25,8,49] have shown word vectors can likewise be beneficial for learning without forgetting. Rahman et al [25] has used semantic word vectors in the any-shot object detection problem in order to detect both unseen and few-shot objects simultaneously.…”

Section: Related Workmentioning

confidence: 99%

“…Lately, some works [25,8,49] have shown word vectors can likewise be beneficial for learning without forgetting. Rahman et al [25] has used semantic word vectors in the any-shot object detection problem in order to detect both unseen and few-shot objects simultaneously. Word vectors helped to reduce the forgetting of seen classes during fine-tuning.…”

Section: Related Workmentioning

confidence: 99%

“…We identify two critical challenges in this problem. (a) Catastrophic forgetting of base classes: Recent works observed a fascinating performance using word vectors in the learning process (in addition to knowledge distillation techniques) to address the forgetting problem [25,8,49]. The general motivation is that shared attributes (e.g., shape, color) between the base (e.g., horse, tiger) and novel class (e.g., zebra) help to understand novel classes better using a few examples and not to forget base classes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Synthesized Feature based Few-Shot Class-Incremental Learning on a Mixture of Subspaces

Cheraghian

Rahman

Ramasinghe

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

Few-shot class incremental learning (FSCIL) aims to incrementally add sets of novel classes to a well-trained base model in multiple training sessions with the restriction that only a few novel instances are available per class. While learning novel classes, FSCIL methods gradually forget base (old) class training and overfit to a few novel class samples. Existing approaches have addressed this problem by computing the class prototypes from the visual or semantic word vector domain. In this paper, we propose addressing this problem using a mixture of subspaces. Subspaces define the cluster structure of the visual domain and help to describe the visual and semantic domain considering the overall distribution of the data. Additionally, we propose to employ a variational autoencoder (VAE) to generate synthesized visual samples for augmenting pseudo-feature while learning novel classes incrementally. The combined effect of the mixture of subspaces and synthesized features reduces the forgetting and overfitting problem of FSCIL. Extensive experiments on three image classification datasets show that our proposed method achieves competitive results compared to state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Synthesized Feature based Few-Shot Class-Incremental Learning on a Mixture of Subspaces

Cheraghian

Rahman

Ramasinghe

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Word embedding for catastrophic forgetting: The use of semantic representation to prevent catastrophic forgetting is relatively new [24,4,42]. Such approaches explore the semantic relation between old and new classes to reduce the forgetting of old classes while training new classes.…”

Section: Related Workmentioning

confidence: 99%

“…Because of the difficulties of 3D data, this approach exhibits a large amount of forgetting of old classes. To minimize forgetting, we employ semantic word vectors of classes inside the network pipeline [24,4,42]. During both new and old task training, the network tries to align point cloud features to their corresponding semantics.…”

Section: Introductionmentioning

confidence: 99%

Learning without Forgetting for 3D Point Cloud Objects

Chowdhury¹,

Jalisha²,

Cheraghian³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

When we fine-tune a well-trained deep learning model for a new set of classes, the network learns new concepts but gradually forgets the knowledge of old training. In some real-life applications, we may be interested in learning new classes without forgetting the capability of previous experience. Such learning without forgetting problem is often investigated using 2D image recognition tasks. In this paper, considering the growth of depth camera technology, we address the same problem for the 3D point cloud object data. This problem becomes more challenging in the 3D domain than 2D because of the unavailability of large datasets and powerful pretrained backbone models. We investigate knowledge distillation techniques on 3D data to reduce catastrophic forgetting of the previous training. Moreover, we improve the distillation process by using semantic word vectors of object classes. We observe that exploring the interrelation of old and new knowledge during training helps to learn new concepts without forgetting old ones. 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. This research will instigate many future works in this area.

show abstract