Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

[IEEE Geoscience and Remote Sensing Letters] Log-Based Transformation Feature Learning for Change Detection in Heterogeneous Images

Tao Zhan, Maoguo Gong, Shuwei Li, Xinming Jiang

A log-based feature transformation method for detecting changes in heterogeneous remote sensing image pairs.

[IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing] A Generative Discriminatory Classified Network for Change Detection in Multispectral Imagery

Maoguo Gong, Yudong Yang, Tao Zhan, Shuwei Li

A generative adversarial network-based approach for change detection in multispectral remote sensing images.

[Arxiv 2022] MIMT: Multi-Illuminant Color Constancy via Multi-Task Local Surface and Light Color Learning

Shuwei Li, Jikai Wang, Michael S. Brown, Robby T. Tan

A multi-task learning framework for color constancy under multiple illuminants via joint local surface and light color estimation.

[CVPR 2024] NightCC: Nighttime Color Constancy via Adaptive Channel Masking

Shuwei Li, Robby T. Tan

An unsupervised domain-adaptation pipeline for nighttime color constancy using Adaptive Channel Masking and a Light Uncertainty module, reducing mean angular error by 21.5% over prior state-of-the-art.

[AAAI 2026 (Oral)] Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation

Shuwei Li, Lei Tan, Robby T. Tan

The first I2I translation framework that actively detects and suppresses target-class hallucinations using a dual-head discriminator with SAM2 pseudo-labels, improving mAP by +15.5% on BDD100K day-to-night adaptation. Oral presentation.

[AAAI 2026] Aggregating Diverse Cue Experts for AI-Generated Image Detection

Lei Tan, Shuwei Li, Mohan Kankanhalli, Robby T. Tan

Proposes a Mixture-of-Encoder Adapter (MoEA) framework that integrates diverse cues for robust AI-generated image detection, achieving 89.7% average accuracy on GenImage.

[CVPR 2026] White-Balance First, Adjust Later: Cross-Camera Color Constancy via Vision-Language Evaluation

Shuwei Li, Lei Tan, Robby T. Tan

Reformulates color constancy as an iterative perceptual-feedback process using VLMs, achieving 36.8% reduction in mean angular error and 43.6% in Worst-25% error on the Gehler-Shi dataset.

[ICML 2026] FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification

Xuanhao Qi, Tom H. Luan, Yukang Zhang, Jinkai Zheng, Su Zhou*, Shuwei Li*, Lei Tan

A multi-modal object re-identification framework that aligns cross-modal representations via frequency-domain unification and spectral energy alignment.

[ECCV 2026] UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models

Lei Tan, Shuwei Li, Mohan Kankanhalli, Robby T. Tan

The first VLM training framework for AI-generated image detection without reasoning annotations, achieving 96.7% / 82.4% accuracy on GenImage / Chameleon.

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015