Resolving Semantic Confusions for Improved Zero-Shot Detection
Not on the map. Why?
Abstract (arXiv)
Zero-shot detection (ZSD) is a challenging task where we aim to recognize and localize objects simultaneously, even when our model has not been trained with visual samples of a few target ("unseen") classes. Recently, methods employing generative models like GANs have shown some of the best results, where unseen-class samples are generated based on their semantics by a GAN trained on seen-class data, enabling vanilla object detectors to recognize unseen objects. However, the problem of semantic confusion still remains, where the model is sometimes unable to distinguish between semantically-similar classes. In this work, we propose to train a generative model incorporating a triplet loss that acknowledges the degree of dissimilarity between classes and reflects them in the generated samples. Moreover, a cyclic-consistency loss is also enforced to ensure that generated visual samples of a class highly correspond to their own semantics. Extensive experiments on two benchmark ZSD datasets - MSCOCO and PASCAL-VOC - demonstrate significant gains over the current ZSD methods, reducing semantic confusion and improving detection for the unseen classes.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 63 references that are in the map. First posted on arXiv 12 Dec 2022.
Builds on
40 of 63 references.
References · 40
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2016Improved Techniques for Training GANscited by 2,938
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2016YOLO9000: Better, Faster, Strongercited by 1,429
- 2016Bag of Tricks for Efficient Text Classificationcited by 869
- 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
28 more
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
- 2018Zero-Shot Object Detectioncited by 189
- 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
- 2015Label-Embedding for Image Classificationcited by 164
- 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
- 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
- 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
- 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
- 2016Latent Embeddings for Zero-shot Classificationcited by 129
- 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
- 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
- 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
- 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
- 2019Dont Even Look Once: Synthesizing Features for Zero-Shot Detectioncited by 58
- 2014Improving zero-shot learning by mitigating the hubness problemcited by 53
- 2018Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Conceptscited by 48
- 2015Ridge Regression, Hubness, and Zero-Shot Learningcited by 44
- 2019Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learningcited by 38
- 2018Zero-Shot Object Detection by Hybrid Region Embeddingcited by 32
- 2020Synthesizing the Unseen for Zero-shot Object Detectioncited by 32
- 2020Background Learnable Cascade for Zero-Shot Object Detectioncited by 31
- 2018Zero-Shot Detectioncited by 27
- 2021Semantics-Guided Contrastive Network for Zero-Shot Object detectioncited by 26
- 2020GTNet: Generative Transfer Network for Zero-Shot Object Detectioncited by 25
- 2018Polarity Loss for Zero-shot Object Detectioncited by 14
- 2020Multi-label Zero-shot Classification by Learning to Transfer from External Knowledgecited by 6
- 2020Bias-Awareness for Zero-Shot Learning the Seen and Unseencited by 2
Built on by
Citing papers per year: 2024: 2.
2 papers.