Differences
This shows you the differences between two versions of the page.
|
dsm:assignments:01 [2025/10/05 18:13] emilian.radoi |
dsm:assignments:01 [2025/11/20 16:31] (current) andrei.niculae1004 |
||
|---|---|---|---|
| Line 17: | Line 17: | ||
| === Milestones and Deliverables === | === Milestones and Deliverables === | ||
| - | == 1. M1 (04.11.24) - Related Work / State-of-the-Art Review + Presentation (1p) == | + | == 1. M1 (03.11.25) - Related Work / State-of-the-Art Review + Presentation (1p) == |
| * **Objective**: Establish the research context by reviewing and summarising related work (existing studies and relevant literature related to your topic). | * **Objective**: Establish the research context by reviewing and summarising related work (existing studies and relevant literature related to your topic). | ||
| * **Action Items**: | * **Action Items**: | ||
| Line 23: | Line 23: | ||
| * Summarise the current state-of-the-art methods in the field. | * Summarise the current state-of-the-art methods in the field. | ||
| * Identify gaps in the research or areas for potential improvement. | * Identify gaps in the research or areas for potential improvement. | ||
| - | * **Documentation**: Create a report section (2 pages excluding references) detailing your findings, including citations of key papers and a discussion of how your project will build upon or differ from existing work, in **English**. | + | * **Documentation (English, IEEE format)**: Create a report section (2 pages excluding references) detailing your findings, including citations of key papers and a discussion of how your project will build upon or differ from existing work. |
| - | * **Upload Documentation**: [[https://curs.upb.ro/2024/mod/assign/view.php?id=49434|Upload]] (Must contain title and authors) | + | |
| * **Grading** | * **Grading** | ||
| - | * **References (0.3p)**: Include a minimum of 10 academic papers in your review. | + | * **(0.3p) References**: Include a minimum of 10 academic papers in your review. |
| - | * **Research Questions (0.2p)**: Provide at least 2 meaningful research questions that will answer, or that should be addressed in future work. Helpful guide [[https://atlasti.com/guides/qualitative-research-guide-part-1/research-question | here]]. | + | * **(0.2p) Research Questions**: Provide at least 2 meaningful research questions that will answer, or that should be addressed in future work. Helpful guide [[https://atlasti.com/guides/qualitative-research-guide-part-1/research-question | here]]. |
| - | * **Content (0.5p)**: Capture the current landscape of the topic. You may use qualitative surveys for inspiration. Also **check the tips below**). In your review explicitly answer these sub-questions, each worth 0.1p: | + | * **(0.5p) Content**: Capture the current landscape of the topic. You may use qualitative surveys for inspiration. Also **check the tips below**). In your review explicitly answer these sub-questions, each worth 0.1p: |
| * What datasets are used and why? (0.1p) | * What datasets are used and why? (0.1p) | ||
| * What benchmarks or evaluation methods are used? Are there any limitations? (0.1p) | * What benchmarks or evaluation methods are used? Are there any limitations? (0.1p) | ||
| Line 45: | Line 44: | ||
| * Document each papers by noting its **main contributions** (these are usually stated explicitly by the authors). | * Document each papers by noting its **main contributions** (these are usually stated explicitly by the authors). | ||
| * Explore top conferences using the [[https://portal.core.edu.au/conf-ranks | CORE ranking portal]]. | * Explore top conferences using the [[https://portal.core.edu.au/conf-ranks | CORE ranking portal]]. | ||
| - | * Focus on highly ranked conferences such as CVPR, ECCV, NeurIPS and EMNLP. You can scout the accepted papers in the current year by searching them on arXiv. Example: [[https://neurips.cc/Downloads/2025 | NeurIPS 2025 accepted papers]]. | + | * Focus on highly ranked conferences such as CVPR, ECCV, NeurIPS, EMNLP, etc. You can scout the accepted papers in the current year by searching for them on arXiv. Example: [[https://neurips.cc/Downloads/2025 | NeurIPS 2025 accepted papers]]. |
| * Evaluate papers based on the **number of citations** (though newer papers may have fewer), year of publication and author credibility. | * Evaluate papers based on the **number of citations** (though newer papers may have fewer), year of publication and author credibility. | ||
| * Choose a topic that truly interests you. It will make the research process more engaging and enjoyable. | * Choose a topic that truly interests you. It will make the research process more engaging and enjoyable. | ||
| + | * **Upload M1 (Documentation)**: [[https://curs.upb.ro/2025/mod/assign/view.php?id=24449|Upload]] must contain title and authors. | ||
| | | ||
| - | == 2. M2 (18.11.24) - Dataset Collection and Baseline Results (1p) == | + | == 2. M2 (24.11.25) - Dataset Collection and Baseline Results (1p) == |
| * **Objective**: Obtain the datasets required for your project and implement a baseline model for comparison. | * **Objective**: Obtain the datasets required for your project and implement a baseline model for comparison. | ||
| * **Action Items**: | * **Action Items**: | ||
| Line 60: | Line 60: | ||
| * Obtain preliminary results to compare against future improvements. | * Obtain preliminary results to compare against future improvements. | ||
| * **Evaluation Metrics**: Choose appropriate metrics (e.g., accuracy, F1-score, ROC-AUC) and document initial performance. | * **Evaluation Metrics**: Choose appropriate metrics (e.g., accuracy, F1-score, ROC-AUC) and document initial performance. | ||
| - | * **Documentation ** (IEEE conference paper format): Submit a report section (2 pages excluding references) describing the dataset, preprocessing steps, baseline model, and results. | + | * **Documentation (English, IEEE format)**: Submit a report section (2 pages excluding references) describing the dataset, preprocessing steps, baseline model, and results. |
| - | * **Upload Documentation**: [[https://curs.upb.ro/2024/mod/assign/view.php?id=49438|Upload]] | + | |
| * **Grading** | * **Grading** | ||
| - | * Description of selected **datasets**: purpose, number of records, quality, method of collection, size, feature description - 0.5. | + | * **(0.5p) Dataset description**: Description and rationale for the selected datasets, including dataset purpose, number of records, data quality, collection method, size, and feature description. |
| - | * Description of **implemented baseline**: - 0.1 | + | * **(0.1p) Baseline description**: Clear explanation of the implemented baseline method. |
| - | * Report **initial results**: - 0.3 | + | * **(0.3p) Initial results**: Presentation of baseline performance results |
| - | * Result analysis - 0.1 | + | * **(0.1p) Result analysis**: Interpretation and insights from the obtained results. |
| + | * **Upload M2 (Documentation and Code)**: [[https://curs.upb.ro/2025/mod/assign/view.php?id=24452|Upload]] must contain title and authors. | ||
| - | == 3. M3 (18.12.24) - Own Contribution (1p) == | + | |
| - | * **Objective**: Implement your novel contribution to the field, either by solving a new problem or improving an existing method. | + | == 3. M3 (15.12.25) - Own Contribution (1p) == |
| - | * **Types of Contributions**: | + | * **Objective**: Develop and implement your original contribution to the field, either by addressing a new research problem or improving an existing approach. |
| - | * Address a New Problem: Tackle a medical data science issue that has not been addressed by related work. | + | * **Types of contributions**: |
| - | * Improve Existing Methods: | + | * Address a new problem: Investigate a medical data science challenge that has not been sufficiently explored in prior work. |
| - | * Improve Results: Enhance the performance of an existing solution by optimising models or experimenting with different techniques. | + | * Improve existing methods: |
| - | * Extensive Experiments: Conduct extensive experiments to assess your model’s robustness, including testing with different datasets or under varying conditions. | + | * Improve results: Optimise existing models or experiment with alternative techniques to achieve better performance. |
| - | * New Approach: Introduce a new method or architecture (e.g., switching from traditional CNNs to transformers), even if it does not outperform state-of-the-art methods, as long as it provides a novel perspective. | + | * Extensive experiments: Conduct comprehensive testing to evaluate your model’s robustness across multiple datasets or varying conditions. Novelty is important: even if your model does not outperform the state-of-the-art, it should offer a new perspective or insight. |
| * Examples: | * Examples: | ||
| * Use a different deep learning architecture (e.g., ResNet vs. EfficientNet). | * Use a different deep learning architecture (e.g., ResNet vs. EfficientNet). | ||
| * Apply a novel training strategy, such as self-supervised learning or data augmentation techniques. | * Apply a novel training strategy, such as self-supervised learning or data augmentation techniques. | ||
| * Propose a hybrid model that combines multiple approaches (e.g., combining CNNs with decision trees). | * Propose a hybrid model that combines multiple approaches (e.g., combining CNNs with decision trees). | ||
| - | * **Documentation** (IEEE conference paper format): Write a report section (2 pages excluding references) **justifying your chosen approach**, detailing your contribution, how it differs from existing work, and comparing your experimental results to the baseline and state of the art. | + | * **Documentation (English, IEEE format)**: Write a report section (2 pages excluding references) **justifying your chosen approach**, detailing your contribution, how it differs from existing work, and comparing your experimental results to the baseline and state-of-the-art. |
| - | * **Upload Documentation and code**: [[https://curs.upb.ro/2024/mod/assign/view.php?id=49446|Upload]] | + | |
| * **Grading**: | * **Grading**: | ||
| - | * Description of proposed contribution: 0.3 | + | * (0.3p) Clear and well-justified explanation of your contribution/s. |
| - | * Implementation and results on selected dataset: 0.5 | + | * (0.5p) Implementation and results on selected dataset/s. |
| - | * Result analysis, comparison with baseline: 0.2 | + | * (0.2p) Result analysis, and comparison with the baseline. |
| + | * **Upload M3 (Documentation and Code)**: [[https://curs.upb.ro/2025/mod/assign/view.php?id=24454|Upload]] must contain title and authors. | ||
| - | == 4. M4 (08.01.25) - Final paper + Presentation (1p) == | + | |
| + | == 4. M4 (12.01.25) - Final paper + Presentation (1p) == | ||
| * **Objective**: Compile your project into a well-organised academic report. | * **Objective**: Compile your project into a well-organised academic report. | ||
| * **Action Items**: | * **Action Items**: | ||
| - | * Write a research-style report following the IEEE conference paper format. | + | * Write a research-style report following the IEEE format (8 pages excluding references). |
| * **Structure**: | * **Structure**: | ||
| - | * **Abstract**: Briefly summarize your project, contributions, and key findings. | + | * **Abstract**: Summarise the project, contributions and key findings. |
| - | * **Introduction**: Explain the problem you are addressing, motivation, and background. | + | * **Introduction**: Describe the problem, motivation and background. |
| - | * **Related Work**: Include the summary from M1. | + | * **Related Work**: Include the literature review from M1. |
| - | * **Methodology**: Detail your approach, including algorithms, models, and techniques used. | + | * **Methodology**: Detail your approach, including algorithms, models and techniques. |
| - | * **Experiments**: Describe the datasets, baseline methods, and results from M2. | + | * **Experiments**: Describe datasets, baseline methods, and results from M2. |
| - | * **Own Contribution**: Document your original contribution, as outlined in M3. | + | * **Own Contribution**: Document your original contribution, as in M3. |
| - | * **Results and Discussion**: Present detailed results with visualizations (graphs, tables) and discuss their implications. | + | * **Results and Discussion**: Present results with visualisations (graphs, tables) and discuss implications. |
| - | * **Conclusion**: Summarize the outcomes, limitations, and future work. | + | * **Conclusion**: Summarise outcomes, limitations and suggest directions for future research. |
| - | * **Documentation**: Submit a polished, formal academic report in IEEE format (8 pages excluding references). | + | * **Documentation (English, IEEE format)**: Submit a polished, formal academic report in IEEE format (8 pages excluding references). |
| - | * **Upload Documentation**: [[https://curs.upb.ro/2024/mod/assign/view.php?id=49445|Upload]] | + | * **Presentation (6 minutes)** - prepare a concise, visually clear presentation covering: |
| - | * **Presentation**: Prepare a 6 minute presentation covering: | + | * The problem addressed and its relevance. |
| - | * The problem you addressed and its relevance. | + | |
| * Key steps of your methodology. | * Key steps of your methodology. | ||
| - | * Experimental results and key contributions. | + | * Experimental results and your main contributions. |
| * Conclusions and potential areas for future research. | * Conclusions and potential areas for future research. | ||
| - | * Create well- polished slides with clear visuals, including figures, graphs, and performance metrics. | + | * **Presentations tips**: create well-polished slides with clear visuals, including figures, graphs and performance metrics. |
| - | * **Evaluation**: Your presentation will be graded based on clarity, depth of explanation, the quality of results and the Q&A section. The final project grade will be weighted by your presentation quality. | + | * **Evaluation**: The presentation will be graded based on clarity, depth of explanation, the quality of results and the Q&A section. The final project grade will be weighted based on the presentation quality. |
| - | * **Upload Presentation**: [[https://curs.upb.ro/2024/mod/assign/view.php?id=49444|Upload]] | + | * **Upload M4 (Documentation and Slides)**: [[https://curs.upb.ro/2025/mod/assign/view.php?id=24456|Upload]] must contain title and authors. |
| Line 118: | Line 118: | ||
| * M1 and M4 will have their grade (G) scaled by the score of the presentation (P): TOTAL = G * P | * M1 and M4 will have their grade (G) scaled by the score of the presentation (P): TOTAL = G * P | ||
| - | === Examples of Project Ideas === | + | ---- |
| + | |||
| + | |||
| + | ==== Examples of Project Ideas ==== | ||
| === 1. Bad Posture Detection === | === 1. Bad Posture Detection === | ||
