4 citations · 4 across the 4 of their papers we have counts for
5 papers
Is Spurious Correlation Removal Always Learnable?
Yibo Zhou, Bo Li, Hai-Miao Hu +3
Invariant learning can fail even when the invariant structure is statistically identifiable. We show a conditional computational barrier: under a black-box samplable supervised spa…
FeLoG: Scalable and Efficient Distributed Graph Embedding with Feedback Loop Mechanism
Peng Fang, Arijit Khan, Ziqiang Wu +4
Graph embedding maps graph nodes into low-dimensional vectors to support applications such as recommendation, fraud detection, and graph-based retrieval-augmented generation (Graph…
Pedestrian Attribute Recognition as Label-balanced Multi-label Learning
Yibo Zhou, Hai-Miao Hu, Yirong Xiang +2
Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (…
A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition
Yibo Zhou, Hai-Miao Hu, Jinzuo Yu +3
Recent studies on pedestrian attribute recognition progress with either explicit or implicit modeling of the co-occurrence among attributes. Considering that this known a prior is…
Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection
Yibo Zhou
In some scenarios, classifier requires detecting out-of-distribution samples far from its training data. With desirable characteristics, reconstruction autoencoder-based methods de…