← Search

Nanning Zheng*

2 accepted papers

2024

AugDETR: Improving Multi-scale Learning for Detection Transformer

ECCV 2024poster

"Current end-to-end detectors typically exploit transformers to detect objects and show promising performance. Among them, Deformable DETR is a representative paradigm that effectively exploits multi-scale features. However, small local receptive fields and limited query-encoder interactions weaken…

Cited by 2SourcePDFScholar
2024

MRSP: Learn Multi-Representations of Single Primitive for Compositional Zero-Shot Learning

ECCV 2024poster

"Compositional Zero-Shot Learning (CZSL) aims to classify unseen state-object compositions using seen primitives. Previous methods commonly map an identical primitive from different compositions to the same area within embedding space, aiming to establish primitive representation or assess decoding…

Cited by 3SourcePDFScholar