Generalized Class Discovery in Instance Segmentation

Authors: Cuong Manh Hoang, Yeejin Lee, Byeongkeun Kang

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we evaluate our proposed method by conducting experiments on two settings: COCOhalf + LVIS and LVIS + Visual Genome. The experimental results demonstrate that the proposed method outperforms previous state-of-the-art methods.
Researcher Affiliation Academia 1Seoul National University of Science and Technology, Republic of Korea 2Chung-Ang University, Republic of Korea EMAIL, EMAIL
Pseudocode No The paper describes the methods in prose and mathematical formulations, but does not include structured pseudocode or algorithm blocks.
Open Source Code No The code will be publicly available on Git Hub upon publication to ensure reproducibility.
Open Datasets Yes In the COCOhalf + LVIS setting... we use 50K images with labels for the 80 COCO classes for Dl and the entire 100K images without labels for Du. We use the 20K LVIS validation images for evaluation. In the LVIS + VG setting... We use the entire 100K LVIS training data for Dl and the combined 158K LVIS and VG training images for Du. For evaluation, we use 8K images that appear in both the LVIS and VG validation sets.
Dataset Splits Yes In the COCOhalf + LVIS setting... we use 50K images with labels for the 80 COCO classes for Dl and the entire 100K images without labels for Du. We use the 20K LVIS validation images for evaluation. In the LVIS + VG setting... We use the entire 100K LVIS training data for Dl and the combined 158K LVIS and VG training images for Du. For evaluation, we use 8K images that appear in both the LVIS and VG validation sets.
Hardware Specification Yes The experiments were conducted on a computer with two Nvidia Ge Force RTX 3090 GPUs, an Intel Core i9-10940X CPU, and 128 GB RAM.
Software Dependencies No The paper mentions architectural components (Res Net-50) and methods (DINO, MoCo) but does not specify software dependencies with version numbers like Python, PyTorch, or CUDA versions.
Experiment Setup Yes We train fd( ) for 390 epochs with K = 1%, τ min = 0.07, τ max = 1, and λ = 0.35. For the SAM, we set M = 3, d = D/8, w = 0.25 stg, ˆd = 1, s1 = 18/(2stg 1) , s2 = 12/(2stg 1) , and s3 = 8/(2stg 1) , where stg is the stage index and denotes rounding. We train fs( ) for 36 epochs with T = 3.