Haichuan Song

Haichuan Song

Auto-generated profile, based on publicly available information

Haichuan Song

East China Normal University, Shanghai, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 April 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
WYWenya Yang
Wenya Yang
XCXiao-Diao Chen
Xiao-Diao Chen
WWWen Wu
Wen Wu
HQhongshuai qin
hongshuai qin
KYKangming Yan
Kangming Yan
HSHaichuan Song
Haichuan Song
Segment anything model (SAM), a vision foundation network trained on a massive segmentation corpus, exhibits a superior boundary localization capability for nature images. This work aims to leverage such strengths to develop a deep unsupervised edge detection (UED) framework for alleviating the high reliance on dense labeling. However, applying vanilla SAM to edge detection fails to identify the salient edge cues but only the semantic boundary. This article introduces a lightweight adapter-tuning scheme to learn detailed edge information for filling the gap between boundary and edge, enabling a well-fitting even with limited training data. Moreover, considering the low-quality pseudo labels used in our UED framework, we propose two training strategies, adaptive progressive learning and gradient-guided pseudo label updating, to alleviate the impact of noisy labels from traditional UED methods. Extensive experiments demonstrate that our method achieves comparable results to state-of-the-art fully supervised edge detectors.

26 September 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XTXin Tan
Xin Tan
QMQihang Ma
Qihang Ma
JGJingyu Gong
Jingyu Gong
JXJiachen Xu
Jiachen Xu
ZZZhizhong Zhang
Zhizhong Zhang
LMLizhuang Ma
Lizhuang Ma
Hidden features in the neural networks usually fail to learn informative representation for 3D segmentation as supervisions are only given on output prediction, while this can be solved by omni-scale supervision on intermediate layers. In this paper, we bring the first omni-scale supervision method to 3D segmentation via the proposed gradual Receptive Field Component Reasoning (RFCR), where target Receptive Field Component Codes (RFCCs) is designed to record categories within receptive fields for hidden units in the encoder. Then, target RFCCs will supervise the decoder to gradually infer the RFCCs in a coarse-to-fine categories reasoning manner, and finally obtain the semantic labels. To purchase more supervisions, we also propose an RFCR-NL model with complementary negative codes (i.e., Negative RFCCs, NRFCCs) with negative learning. Because many hidden features are inactive with tiny magnitudes and make minor contributions to RFCC prediction, we propose Feature Densification with a centrifugal potential to obtain more unambiguous features, and it is in effect equivalent to entropy regularization over features. More active features can unleash the potential of omni-supervision method. We embed our method into three prevailing backbones, which are significantly improved in all three datasets on both fully and weakly supervised segmentation tasks and achieve competitive performances.


30 April 2025 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
JZJunkang Zhang
Junkang Zhang
FFFaming Fang
Faming Fang
TWTingting Wang
Tingting Wang
GZGuixu Zhang
Guixu Zhang
HSHaichuan Song
Haichuan Song
The process of fusing low-resolution multispectral (LRMS) and high-resolution panchromatic (PAN) imagery, commonly referred to as pansharpening, is intended to generate high-resolution multispectral (HRMS) imagery. Typically, most pre-existing pansharpening frameworks mainly emphasize the straightforward learning of the mapping relationship among PAN and LRMS images to HRMS images. However, a key limitation of these frameworks is their potential overemphasis on spatial information, particularly the enhancement of low-frequency components. As a result, such an oversight potentially hinders the model's ability to simultaneously restore both spectral and spatial details. To address this issue, we propose a novel pansharpening model based on the denoising diffusion probabilistic model (DDPM), dubbed FrDiff. Specifically, we build a framelet-based conditional diffusion model that leverages the generative power of diffusion models to produce more refine results. Different from conventional methods directly inferring HRMS images, our strategy is designed to project their framelet coefficients, utilizing the available PAN and LRMS images as resources. This approach enables the separation of high-frequency and low-frequency components through framelet transformation, which are subsequently recombined to create a novel set of conditional embeddings that feed into the diffusion process. At the same time, the powerful predictive power of the diffusion model is exploited to simultaneously recover the high-frequency and low-frequency components of the HRMS. Moreover, we introduce a framelet-oriented cross-attention module dedicated to honing spectral fidelity. This module is crucial for improving the spectral precision of the HRMS images, ensuring a balanced emphasis on both spatial and spectral enhancements. Quantitative and qualitative experiments on multiple benchmark datasets demonstrate that the proposed method achieves more robustness and high-quality results than other state-of-the-art pansharpening methods.

27 September 2025
Verified
Conference Paper
Open access
YXYingjing Xiao
Yingjing Xiao
ZHZhichao Huang
Zhichao Huang
JRJunbin Ren
Junbin Ren
YBYuting Bai
Yuting Bai
HSHaichuan Song
Haichuan Song
YGYang Gao
Yang Gao

22 February 2026 in Neural Networks
Verified
Journal Article
Closed access
WZWeijian Zhang
Weijian Zhang
HSHaichuan Song
Haichuan Song
ZZZhizhong Zhang
Zhizhong Zhang
XTXin Tan
Xin Tan
LMLizhuang Ma
Lizhuang Ma
YXYuan Xie
Yuan Xie