3 papers
cs.CV2025
Learning What Helps: Task-Aligned Context Selection for Vision Tasks
Jingyu Guo, Emir Konuk, Fredrik Strand +2
Humans often resolve visual uncertainty by comparing an image with relevant examples, but ViTs lack the ability to identify which examples would improve their predictions. We prese…
cs.CV2025
Hyper3D: Efficient 3D Representation via Hybrid Triplane and Octree Feature for Enhanced 3D Shape Variational Auto-Encoders
Jingyu Guo, Sensen Gao, Jia-Wang Bian +4
Recent 3D content generation pipelines often leverage Variational Autoencoders (VAEs) to encode shapes into compact latent representations, facilitating diffusion-based generation.…
cs.CV2025
Efficient Self-Supervised Adaptation for Medical Image Analysis
Moein Sorkhei, Emir Konuk, Jingyu Guo +3
Self-supervised adaptation (SSA) improves foundation model transfer to medical domains but is computationally prohibitive. Although parameter efficient fine-tuning methods such as…