7 citations · 28 across the 19 of their papers we have counts for
9 papers · 1 filter
Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions
Kai Liu, Zhihang Fu, Chao Chen +5
The key to OOD detection has two aspects: generalized feature representation and precise category description. Recently, vision-language models such as CLIP provide significant adv…
Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution
Kai Liu, Zhihang Fu, Sheng Jin +6
Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed neural networks to void unreliable predictions. In real-world scenarios, however, the eff…
ESOD: Efficient Small Object Detection on High-Resolution Images
Kai Liu, Zhihang Fu, Sheng Jin +5
Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computati…
Uncertainty-aware Unsupervised Multi-Object Tracking
Kai Liu, Sheng Jin, Zhihang Fu +3
Without manually annotated identities, unsupervised multi-object trackers are inferior to learning reliable feature embeddings. It causes the similarity-based inter-frame associati…
Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection
Ze Chen, Zhihang Fu, Jianqiang Huang +5
Weakly supervised object detection (WSOD), which is an effective way to train an object detection model using only image-level annotations, has attracted considerable attention fro…
Dynamic Supervisor for Cross-dataset Object Detection
Ze Chen, Zhihang Fu, Jianqiang Huang +6
The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learn…
SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection
Ze Chen, Zhihang Fu, Rongxin Jiang +2
Based on the framework of multiple instance learning (MIL), tremendous works have promoted the advances of weakly supervised object detection (WSOD). However, most MIL-based method…
HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation
Chao Chen, Zhihang Fu, Zhihong Chen +4
Minimizing the discrepancy of feature distributions between different domains is one of the most promising directions in unsupervised domain adaptation. From the perspective of dis…
Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
Chao Chen, Zhihang Fu, Zhihong Chen +3
Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across doma…