471 citations · 1.6k across the 45 of their papers we have counts for
46 papers
Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
Wen Wen, Hao Chen, Shiliang Zhang
Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from semantic drift, limited adapt…
Looping Back to Move Forward: Recursive Transformers for Efficient and Flexible Large Multimodal Models
Ruihan Xu, Yuting Gao, Lan Wang +5
Large Multimodal Models (LMMs) have achieved remarkable success in vision-language tasks, yet their vast parameter counts are often underutilized during both training and inference…
FlattenGPT: Depth Compression for Transformer with Layer Flattening
Ruihan Xu, Qingpei Guo, Yao Zhu +3
Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pr…
PixelGen: Improving Pixel Diffusion with Perceptual Supervision
Zehong Ma, Ruihan Xu, Shiliang Zhang
Pixel diffusion generates images directly in pixel space, avoiding the VAE artifacts and representational bottlenecks of two-stage latent diffusion. Recent JiT further simplifies p…
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
Zehong Ma, Longhui Wei, Shuai Wang +2
Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the two-stage latent diffusion, offering hi…
MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling
Haoyu Wang, Hao Tang, Donglin Di +5
Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, lon…
When Person Re-Identification Meets Event Camera: A Benchmark Dataset and An Attribute-guided Re-Identification Framework
Xiao Wang, Qian Zhu, Shujuan Wu +2
Recent researchers have proposed using event cameras for person re-identification (ReID) due to their promising performance and better balance in terms of privacy protection, event…
NN-Former: Rethinking Graph Structure in Neural Architecture Representation
Ruihan Xu, Haokui Zhang, Yaowei Wang +2
The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recent…
MagCache: Fast Video Generation with Magnitude-Aware Cache
Zehong Ma, Longhui Wei, Feng Wang +2
Existing acceleration techniques for video diffusion models often rely on uniform heuristics or time-embedding variants to skip timesteps and reuse cached features. These approache…
Efficient Multi-modal Long Context Learning for Training-free Adaptation
Zehong Ma, Shiliang Zhang, Longhui Wei +1
Traditional approaches to adapting multi-modal large language models (MLLMs) to new tasks have relied heavily on fine-tuning. This paper introduces Efficient Multi-Modal Long Conte…
Evolved Hierarchical Masking for Self-Supervised Learning
Zhanzhou Feng, Shiliang Zhang
Existing Masked Image Modeling methods apply fixed mask patterns to guide the self-supervised training. As those mask patterns resort to different criteria to depict image contents…
Multi-modal Reference Learning for Fine-grained Text-to-Image Retrieval
Zehong Ma, Hao Chen, Wei Zeng +2
Fine-grained text-to-image retrieval aims to retrieve a fine-grained target image with a given text query. Existing methods typically assume that each training image is accurately…
Anti-Forgetting Adaptation for Unsupervised Person Re-identification
Hao Chen, Francois Bremond, Nicu Sebe +1
Regular unsupervised domain adaptive person re-identification (ReID) focuses on adapting a model from a source domain to a fixed target domain. However, an adapted ReID model can h…
Dataset Distillation for Histopathology Image Classification
Cong Cong, Shiyu Xuan, Sidong Liu +3
Deep neural networks (DNNs) have exhibited remarkable success in the field of histopathology image analysis. On the other hand, the contemporary trend of employing large models and…
OVMR: Open-Vocabulary Recognition with Multi-Modal References
Zehong Ma, Shiliang Zhang, Longhui Wei +1
The challenge of open-vocabulary recognition lies in the model has no clue of new categories it is applied to. Existing works have proposed different methods to embed category cues…
LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model
Dongkai Wang, Shiyu Xuan, Shiliang Zhang
The capacity of existing human keypoint localization models is limited by keypoint priors provided by the training data. To alleviate this restriction and pursue more general model…
MV-VTON: Multi-View Virtual Try-On with Diffusion Models
Haoyu Wang, Zhilu Zhang, Donglin Di +2
The goal of image-based virtual try-on is to generate an image of the target person naturally wearing the given clothing. However, existing methods solely focus on the frontal try-…
Decoupled Contrastive Learning for Long-Tailed Recognition
Shiyu Xuan, Shiliang Zhang
Supervised Contrastive Loss (SCL) is popular in visual representation learning. Given an anchor image, SCL pulls two types of positive samples, i.e., its augmentation and other ima…
Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs
Shiyu Xuan, Qingpei Guo, Ming Yang +1
Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks…
MixBCT: Towards Self-Adapting Backward-Compatible Training
Yu Liang, Yufeng Zhang, Shiliang Zhang +4
Backward-compatible training circumvents the need for expensive updates to the old gallery database when deploying an advanced new model in the retrieval system. Previous methods a…
Deep Active Learning for Computer Vision: Past and Future
Rinyoichi Takezoe, Xu Liu, Shunan Mao +4
As an important data selection schema, active learning emerges as the essential component when iterating an Artificial Intelligence (AI) model. It becomes even more critical given…
ParCNetV2: Oversized Kernel with Enhanced Attention
Ruihan Xu, Haokui Zhang, Wenze Hu +2
Transformers have shown great potential in various computer vision tasks. By borrowing design concepts from transformers, many studies revolutionized CNNs and showed remarkable res…
ALBench: A Framework for Evaluating Active Learning in Object Detection
Zhanpeng Feng, Shiliang Zhang, Rinyoichi Takezoe +5
Active learning is an important technology for automated machine learning systems. In contrast to Neural Architecture Search (NAS) which aims at automating neural network architect…
Enhancing Social Relation Inference with Concise Interaction Graph and Discriminative Scene Representation
Xiaotian Yu, Hanling Yi, Yi Yu +3
There has been a recent surge of research interest in attacking the problem of social relation inference based on images. Existing works classify social relations mainly by creatin…