Differences

This shows you the differences between two versions of the page.

--- intern:vitransformer [2024/09/25 04:47] – lizhengyu
+++ intern:vitransformer [2025/07/28 08:24] (current) – [Week 2: Collaborative Paper Development (August 28 – September 3)] lizhengyu
@@ Line 1: / Line 1: @@
-/22-29 Read articles.
+== Research Activities (August 22, 2024 – September 15, 2024) ==
-- ***Attention is All You Need***, ***Masked-attention Mask Transformer for Universal Image Segmentation***.
+=== Week log ===
+==== Week 1: Foundational Research (August 22–27) ====
+  * Reviewed seminal papers on attention mechanisms, including:
+    * //Attention Is All You Need//
+    * //Masked-attention Mask Transformer for Universal Image Segmentation//
+  * Developed proficiency in Anaconda and Python programming for AI applications.
+  * Joined laboratory research under mentorship of senior researchers.
+==== Week 2: Collaborative Paper Development (August 28 – September 3) ====
+  * Supported experiments for the paper //TGMformer: Transferability Guided Mask Transformer for Segmentation Domain Adaptation// (led by senior Zhang Enming):
+    * Implemented baseline models comparing fine-tuning strategies (last layer vs. full network) for transfer learning.
+    * Formalized mathematical definitions for transfer learning, clustering algorithms, and attention masking in the Methods section.
+    * Assisted with LaTeX typesetting and document formatting.
+==== Week 3: Data Pipeline Implementation (September 4–10) ====
+    * Continued working on the paper //TGMformer: Transferability Guided Mask Transformer for Segmentation Domain Adaptation//
+    * Engineered a data loader and task-splitting module for the ImageNet-R dataset to support experiments with the //Hypernet// framework.
+    * Debugged and optimized code to improve functional reliability.
+==== Week 4: Analysis and Synthesis (September 11–15) ====
+    * Evaluated experimental results from the //Hypernet// project and documented insights.
+    * Authored a reflective summary highlighting growth in research skills, data processing, and software testing.