Multi-Scale Feature Fusion and Advanced Representation Learning for Multi Label Image Classification
Source abstract
Abstract
Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images. Obtaining class-specific precise representations at different scales is a key aspect of feature rep... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Algorithms and Applications · Advanced Measurement and Detection Methods · Advanced Sensor and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (58)
Show source-provided references
1. Deep learning with optimal hierarchical spiking neural network for medical image classification10.32604/csse.2023.026128 ↗
2. Research on multi-scale feature fusion network algorithm based on brain tumor medical image classification
3. MSGC: a new bottom-up model for salient object detection
4. CATIRI: an efficient method for content-and-text based image retrieval10.1007/s11390-019-1911-2 ↗
5. Fusion of hash-based hard and soft biometrics for enhancing face image database search and retrieval
6. Image deraining based on dual-channel component decomposition10.1016/j.cag.2023.08.010 ↗
7. HCP: a flexible CNN framework for multi-label image classification10.1109/TPAMI.2015.2491929 ↗
8. Exploit bounding box annotations for multi-label object recognition
9. Visual attention consistency under image transforms for multi-label image classification
10. Contextual debiasing for visual recognition with causal mechanisms
11. Attention-driven dynamic graph convolutional network for multi-label image recognition
12. Modular graph transformer networks for multi-label image classification
13. Multi-label image recognition with graph convolutional networks
14. Feature learning network with transformer for multi-label image classification10.1016/j.patcog.2022.109203 ↗
15. DATran: dual attention transformer for multi-label image classification10.1109/TCSVT.2023.3284812 ↗
16. Cross-modality attention with semantic graph embedding for multi-label classification
17. Liu S, Zhang L, Yang X, Su H, Zhu J. Query2label: a simple transformer way to multi-label classification. arXiv:2107.10834. 2021.
18. Multi-label image recognition by recurrently discovering attentional regions
19. Ml-decoder: scalable and versatile classification head
20. Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv:1609.02907. 2016.
21. Multi-label image classification model based on multiscale fusion and adaptive label correlation
22. Bert: pre-training of deep bidirectional transformers for language understanding
23. Yang Z. XLNet: generalized autoregressive pretraining for language understanding. arXiv:1906.08237. 2019.
24. Exploring the limits of transfer learning with a unified text-to-text transformer
25. Alexey D. An image is worth 16 × 16 words: transformers for image recognition at scale. arXiv:2010.11929. 2020.
26. Swin transformer: hierarchical vision transformer using shifted windows
27. Training data-efficient image transformers & distillation through attention
28. SegFormer: simple and efficient design for semantic segmentation with transformers
29. Deep residual learning for image recognition
30. MSFA: multi-stage feature aggregation network for multi-label image recognition10.1049/ipr2.13068 ↗
31. Mining semantic information with dual relation graph network for multi-label image classification10.1109/TMM.2023.3277279 ↗
32. Transformer driven matching selection mechanism for multi-label image classification10.1109/TCSVT.2023.3288205 ↗
33. Multi-label image classification using adaptive graph convolutional networks: from a single domain to multiple domains10.1016/j.cviu.2024.104062 ↗
34. Causality compensated attention for contextual biased visual recognition
35. Double attention based on graph attention network for image multi-label classification
36. Contrastively enforcing distinctiveness for multi-label image classification10.1016/j.neucom.2023.126605 ↗
37. Learning spatial regularization with image-level supervisions for multi-label image classification
38. Multi-label image classification via knowledge distillation from weakly-supervised detection
39. Semantic representation and dependency learning for multi-label image recognition10.1016/j.neucom.2023.01.018 ↗
40. Recurrent attentional reinforcement learning for multi-label image recognition
41. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. 2014.
42. Learning to discover multi-class attentional regions for multi-label image recognition10.1109/TIP.2021.3088605 ↗
43. Multi-label image recognition with joint class-aware map disentangling and label correlation embedding
44. Learning semantic-specific graph representation for multi-label image recognition
45. General multi-label image classification with transformers
46. Transformer-based dual relation graph for multi-label image recognition
47. Cnn-rnn: a unified framework for multi-label image classification
48. Knowledge-guided multi-label few-shot learning for general image recognition10.1109/TPAMI.2020.3025814 ↗
49. Learning graph convolutional networks for multi-label recognition and applications10.1109/TPAMI.2021.3063496 ↗
50. Learning discriminative representations for multi-label image recognition10.1016/j.jvcir.2022.103448 ↗
51. Xu J, Huang S, Zhou F, Huangfu L, Zeng D, Liu B. Boosting multi-label image classification with complementary parallel self-distillation. arXiv:2205.10986. 2022.10.24963/ijcai.2022/208 ↗
52. An attention-driven multi-label image classification with semantic embedding and graph convolutional networks10.1007/s12559-021-09977-9 ↗
53. Deep semantic dictionary learning for multi-label image classification
54. A multi-scale semantic attention representation for multi-label image recognition with graph networks10.1016/j.neucom.2022.03.057 ↗
55. Paszke · Advances in neural information processing systems · 2019
56. Loshchilov I. Decoupled weight decay regularization. arXiv:1711.05101. 2017.
57. Randaugment: practical automated data augmentation with a reduced search space
58. DeVries T. Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552. 2017.