Research map / Architectures and efficiency / CNN design
QuCNet: Quantum Deep Learning Driven Multi-Circuit Network for Remote Sensing Image Classification
Komal Komal, Mukul Gupta, Saumya Singh, Santosh Kumar Vipparthi, C.C. Reddy, Subrahmanyam Murala
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the trainable quantum circuit (TQC) module to the CNN backbone (ablation) | QuCNet · AID | accuracy (%): 86.26 -> 88.84 | Improved |
| add the TQC module (ablation) | QuCNet · USTC SmokeRS | accuracy (%): 92.23 -> 95.75 | Improved |
| add the TQC module (ablation) | QuCNet · IIITDMJ Smoke | accuracy (%): 98.80 -> 99.28 | Improved |
| add the TQC module (ablation) | QuCNet · EuroSAT | accuracy (%): 96.78 -> 97.56 | Improved |
| add final Ry rotation to the gate sequence (Rx-CNOT-Rx-CNOT-Rx-Ry vs without Ry) (ablation) | QuCNet TQC · AID | accuracy (%): 88.00 -> 88.84 | Improved |
| use HCWS cyclic sharing instead of all-shared parameters (ablation) | QuCNet · AID | accuracy (%): 88.05 -> 88.84 | Improved |
| use HCWS instead of fully independent parameters per circuit (ablation) | QuCNet · AID | accuracy (%): 87.59 -> 88.84 | Improved |
| use HCWS instead of alternate shared scheme (ablation) | QuCNet · AID | accuracy (%): 87.85 -> 88.84 | Improved |
| use amplitude encoding instead of angle encoding (ablation) | QuCNet · AID | accuracy (%): 88.84 -> 81.94 | Hurt |
| use amplitude encoding instead of angle encoding (ablation) | QuCNet · IIITDMJ Smoke | accuracy (%): 99.28 -> 99.10 | No clear effect |
| run on noisy simulator and real IBM hardware instead of ideal simulator | QuCNet · AID | accuracy (%): 88.84 -> 77.53 (ibm torino) | Hurt |
| add TQC to the CNN backbone on natural images (ablation) | QuCNet · CIFAR-10 | accuracy (%): 84.27 -> 86.78 | Improved |
Closest papers by meaning
- Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral Image Classification (CVPR 2023 · similarity 0.87)
- SSL4Q: Semi-Supervised Learning of Quantum Data with Application to Quantum State Classification (ICML 2024 · similarity 0.83)
- Quantum Visual Fields with Neural Amplitude Encoding (NeurIPS 2025 · similarity 0.83)
- Structured Unitary Tensor Network Representations for Circuit-Efficient Quantum Data Encoding (NeurIPS 2026 · similarity 0.82)
- ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networks (CVPR 2025 · similarity 0.82)
- Rethink the Role of Deep Learning towards Large-scale Quantum Systems (ICML 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
