12 papers
Where Is the Bee? Detecting Tiny Pollinators with a Single Collaborative-Head Transformer
Junsu Kim, Seungryul Baek
The CVPPA@ECCV 2026 BuzzSpot Challenge asks us to detect bees, bumblebees, hoverflies, and moths in 1920x1080 field keyframes. Its annotations carry 2 difficulties: the median box…
Local K-Similarity Constraint for Federated Learning with Label Noise
Sanskar Amgain, Prashant Shrestha, Bidur Khanal +5
Federated learning on clients with noisy labels is a challenging problem, as such clients can infiltrate the global model, impacting the overall generalizability of the system. Exi…
Beyond Synthetic Replays: Turning Diffusion Features into Few-Shot Class-Incremental Learning Knowledge
Junsu Kim, Yunhoe Ku, Dongyoon Han +1
Few-shot class-incremental learning (FSCIL) is challenging due to extremely limited training data while requiring models to acquire new knowledge without catastrophic forgetting. R…
Can Synthetic Images Conquer Forgetting? Beyond Unexplored Doubts in Few-Shot Class-Incremental Learning
Junsu Kim, Yunhoe Ku, Seungryul Baek
Few-shot class-incremental learning (FSCIL) is challenging due to extremely limited training data; while aiming to reduce catastrophic forgetting and learn new information. We prop…
Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark
Junsu Kim, Naeun Kim, Jaeho Lee +3
The reasoning-based pose estimation (RPE) benchmark has emerged as a widely adopted evaluation standard for pose-aware multimodal large language models (MLLMs). Despite its signifi…
Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection
Taehoon Kim, Jongwook Choi, Yonghyun Jeong +4
We introduce a deepfake video detection approach that exploits pixel-wise temporal inconsistencies, which traditional spatial frequency-based detectors often overlook. Traditional…