3 papers
cs.CV2026
Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting
Kevin Dave, Sai Aditya Patkuri, Chhaya Kumar Das +3
Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence. Current continuous-regime approaches achieve this v…
cs.CV2025
Mix, Align, Distil: Reliable Cross-Domain Atypical Mitosis Classification
Kaustubh Atey, Sameer Anand Jha, Gouranga Bala +1
Atypical mitotic figures (AMFs) are important histopathological markers yet remain challenging to identify consistently, particularly under domain shift stemming from scanner, stai…
cs.CV2024
Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement
Gouranga Bala, Anuj Gupta, Subrat Kumar Behera +1
Deep learning models rely heavily on large volumes of labeled data to achieve high performance. However, real-world datasets often contain noisy labels due to human error, ambiguit…