Search Results for author: Banghuai Li

Found 7 papers, 2 papers with code

Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection

no code implementations CVPR 2022 Banghuai Li

We visualize each learned class representation in the feature space, and observe that some classes, especially under-represented scarce classes, are prone to cluster with analogous ones due to the lack of discriminative representation.

Metric Learning object-detection +2

ES-CRF: Embedded Superpixel CRF for Semantic Segmentation

no code implementations14 Dec 2021 Jie Zhu, Huabin Huang, Banghuai Li, Leye Wang

It utilizes CRF to guide the message passing between pixels in high-level features to purify the feature representation of boundary pixels, with the help of inner pixels belong to the same object.

Metric Learning Model Optimization +1

MSP : Refine Boundary Segmentation via Multiscale Superpixel

no code implementations3 Dec 2021 Jie Zhu, Huabin Huang, Banghuai Li, Yong liu, Leye Wang

Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map.

Scene Parsing Semantic Segmentation

FBNet: Feature Balance Network for Urban-Scene Segmentation

no code implementations5 Nov 2021 Lei Gan, Huabin Huang, Banghuai Li, Ye Yuan

In this paper, we present a novel add-on module, named Feature Balance Network (FBNet), to eliminate the feature camouflage in urban-scene segmentation.

Autonomous Driving Image Segmentation +1

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

2 code implementations CVPR 2021 Bo Sun, Banghuai Li, Shengcai Cai, Ye Yuan, Chi Zhang

We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects.

Contrastive Learning Few-Shot Learning +3

Beta R-CNN: Looking into Pedestrian Detection from Another Perspective

no code implementations NeurIPS 2020 Zixuan Xu, Banghuai Li, Ye Yuan, Anhong Dang

What’s more, to fully exploit Beta Representation, a novel pipeline Beta R-CNN equipped with BetaHead and BetaMask is proposed, leading to high detection performance in occluded and crowded scenes.

Object Detection Pedestrian Detection

AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses

1 code implementation7 Jul 2020 Zixuan Xu, Banghuai Li, Miao Geng, Ye Yuan

Based on the prediction of each anchor template, we propose to aggregate the results, which can reduce the landmark uncertainty due to the large poses.

Face Alignment Facial Landmark Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.