SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910109634920448 |
|---|---|
| author | Ni, Mingze Liu, Wei |
| author_facet | Ni, Mingze Liu, Wei |
| contents | An effective integration of rich feature representations with robust classification mechanisms remains a key challenge in visual understanding tasks. This study introduces two novel deep learning models, SleepNet and DreamNet, which are designed to improve representation utilization through feature enrichment and reconstruction strategies. SleepNet integrates supervised learning with representations obtained from pre-trained encoders, leading to stronger and more robust feature learning. Building on this foundation, DreamNet incorporates pre-trained encoder decoder frameworks to reconstruct hidden states, allowing deeper consolidation and refinement of visual representations. Our experiments show that our models consistently achieve superior performance compared with existing state-of-the-art methods, demonstrating the effectiveness of the proposed enrichment and reconstruction approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_01633 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification Ni, Mingze Liu, Wei Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition An effective integration of rich feature representations with robust classification mechanisms remains a key challenge in visual understanding tasks. This study introduces two novel deep learning models, SleepNet and DreamNet, which are designed to improve representation utilization through feature enrichment and reconstruction strategies. SleepNet integrates supervised learning with representations obtained from pre-trained encoders, leading to stronger and more robust feature learning. Building on this foundation, DreamNet incorporates pre-trained encoder decoder frameworks to reconstruct hidden states, allowing deeper consolidation and refinement of visual representations. Our experiments show that our models consistently achieve superior performance compared with existing state-of-the-art methods, demonstrating the effectiveness of the proposed enrichment and reconstruction approaches. |
| title | SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.01633 |