Domain-Adaptive Self-Supervised Face & Body Detection in Drawings
Authors: Barış Batuhan Topal, Deniz Yuret, Tevfik Metin Sezgin
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our combined architecture yields detectors with state-of-the-art (SOTA) and near-SOTA performance using minimal annotation effort. Our code can be accessed from https://github. com/barisbatuhan/DASS_Detector. |
| Researcher Affiliation | Academia | Barıs Batuhan Topal1 , Deniz Yuret1 , Tevfik Metin Sezgin1 1Department of Computer Engineering, KUIS AI Center, Koc University {baristopal20, dyuret, mtsezgin}@ku.edu.tr |
| Pseudocode | No | The paper includes figures illustrating the model architecture and training process, but it does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code can be accessed from https://github. com/barisbatuhan/DASS_Detector. |
| Open Datasets | Yes | We process COCO and WIDER FACE datasets with 11 different styles. [...] We also utilized 198,657 pages from COMICS and leveraged i Cartoon Face, Manga 109 pages, Comic2k, Watercolor2k, and Clipart1k images. [...] COCO [Lin et al., 2014], WIDER FACE [Yang et al., 2016]. [...] COMICS [Iyyer et al., 2016]. [...] i Cartoon Face [Zheng et al., 2020]. [...] Manga 109 [Matsui et al., 2017]. [...] DCM 772 [Nguyen et al., 2018]. [...] Comic2k, Watercolor2k, and Clipart1k [Inoue et al., 2018]. |
| Dataset Splits | Yes | i Cartoon Face contains a significant amount of face data with its 50,000 training and 10,000 validation images. |
| Hardware Specification | Yes | In all variations and experiments, the batch size is set to 16, and one Tesla T4 GPU is used. |
| Software Dependencies | No | The paper does not explicitly provide specific version numbers for software dependencies such as Python, PyTorch, or CUDA. |
| Experiment Setup | Yes | In all variations and experiments, the batch size is set to 16, and one Tesla T4 GPU is used. [...] At stages 1 and 3, the learning rate is fixed at 0.001. The highest-scoring checkpoints in the evaluation set among 350 epochs are chosen as the final models. [...] For the teacher-student network, the learning rate is set as 0.0001, and the best checkpoints in 10000 iterations are taken as final models. [...] In our final model, we set Φ to 500, β to 2, d to 0.9996, and positive and negative thresholds (ctthres pos and ctthres neg ) to 0.5. |