147 citations · 391 across the 75 of their papers we have counts for
16 papers · 2 filters
Discriminator-Cooperated Feature Map Distillation for GAN Compression
Tie Hu, Mingbao Lin, Lizhou You +2
Despite excellent performance in image generation, Generative Adversarial Networks (GANs) are notorious for its requirements of enormous storage and intensive computation. As an aw…
Exploring Content Relationships for Distilling Efficient GANs
Lizhou You, Mingbao Lin, Tie Hu +2
This paper proposes a content relationship distillation (CRD) to tackle the over-parameterized generative adversarial networks (GANs) for the serviceability in cutting-edge devices…
SMMix: Self-Motivated Image Mixing for Vision Transformers
Mengzhao Chen, Mingbao Lin, ZhiHang Lin +3
CutMix is a vital augmentation strategy that determines the performance and generalization ability of vision transformers (ViTs). However, the inconsistency between the mixed image…
Shadow Removal by High-Quality Shadow Synthesis
Yunshan Zhong, Lizhou You, Yuxin Zhang +3
Most shadow removal methods rely on the invasion of training images associated with laborious and lavish shadow region annotations, leading to the increasing popularity of shadow i…
Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training
Yunshan Zhong, Gongrui Nan, Yuxin Zhang +2
Quantization-aware training (QAT) receives extensive popularity as it well retains the performance of quantized networks. In QAT, the contemporary experience is that all quantized…
LAB-Net: LAB Color-Space Oriented Lightweight Network for Shadow Removal
Hong Yang, Gongrui Nan, Mingbao Lin +4
This paper focuses on the limitations of current over-parameterized shadow removal models. We present a novel lightweight deep neural network that processes shadow images in the LA…
Knowledge Condensation Distillation
Chenxin Li, Mingbao Lin, Zhiyuan Ding +5
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student. Existing methods focus on excavating the knowledge hints a…
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization
Peixian Chen, Kekai Sheng, Mengdan Zhang +5
Open-vocabulary object detection (OVD) aims to scale up vocabulary size to detect objects of novel categories beyond the training vocabulary. Recent work resorts to the rich knowle…
Super Vision Transformer
Mingbao Lin, Mengzhao Chen, Yuxin Zhang +3
We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only…
Shadow-Aware Dynamic Convolution for Shadow Removal
Yimin Xu, Mingbao Lin, Hong Yang +2
With a wide range of shadows in many collected images, shadow removal has aroused increasing attention since uncontaminated images are of vital importance for many downstream multi…
End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation
Mingrui Wu, Jiaxin Gu, Yunhang Shen +3
Most existing Human-Object Interaction~(HOI) Detection methods rely heavily on full annotations with predefined HOI categories, which is limited in diversity and costly to scale fu…
SeqTR: A Simple yet Universal Network for Visual Grounding
Chaoyang Zhu, Yiyi Zhou, Yunhang Shen +7
In this paper, we propose a simple yet universal network termed SeqTR for visual grounding tasks, e.g., phrase localization, referring expression comprehension (REC) and segmentati…
ARM: Any-Time Super-Resolution Method
Bohong Chen, Mingbao Lin, Kekai Sheng +5
This paper proposes an Any-time super-Resolution Method (ARM) to tackle the over-parameterized single image super-resolution (SISR) models. Our ARM is motivated by three observatio…
CF-ViT: A General Coarse-to-Fine Method for Vision Transformer
Mengzhao Chen, Mingbao Lin, Ke Li +4
Vision Transformers (ViT) have made many breakthroughs in computer vision tasks. However, considerable redundancy arises in the spatial dimension of an input image, leading to mass…
Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters
Mingbao Lin, Liujuan Cao, Yuxin Zhang +3
This paper focuses on filter-level network pruning. A novel pruning method, termed CLR-RNF, is proposed. We first reveal a "long-tail" long-tail pruning problem in magnitude-based…
OptG: Optimizing Gradient-driven Criteria in Network Sparsity
Yuxin Zhang, Mingbao Lin, Mengzhao Chen +2
Network sparsity receives popularity mostly due to its capability to reduce the network complexity. Extensive studies excavate gradient-driven sparsity. Typically, these methods ar…