Statistical Learning
Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
When Spot tries to walk across a sandy beach or on ice, the challenges multiply, and her once-steady walk becomes erratic.
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
Key attributes (cf. Figure 1) include the challenging task of classifying doppelganger animals,
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
This paper presents the first benchmark of uncertainty disentanglement.
Happy: A Debiased Learning Framework for Continual Generalized Category Discovery Shijie Ma
Constantly discovering novel concepts is crucial in evolving environments.
GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
Among these methods, data pruning incurs the least additional training cost and offers the most practical acceleration benefits.
Towards Multi-Domain Learning for Generalizable Video Anomaly Detection
Work done while doing an internship at NA VER Cloud.
Efficient Centroid-Linkage Clustering
We also evaluate our algorithm empirically. By leveraging a state-of-the-art nearest-neighbor search library, we obtain a fast and accurate Centroid-Linkage HAC algorithm.