Search Results for author: Jianlong Wu

Found 27 papers, 18 papers with code

Local Correlation Consistency for Knowledge Distillation

no code implementations ECCV 2020 Xiaojie Li, Jianlong Wu, Hongyu Fang, Yue Liao, Fei Wang, Chen Qian

Sufficient knowledge extraction from the teacher network plays a critical role in the knowledge distillation task to improve the performance of the student network.

Knowledge Distillation

WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More

no code implementations19 Feb 2024 Yuxuan Yue, Zhihang Yuan, Haojie Duanmu, Sifan Zhou, Jianlong Wu, Liqiang Nie

Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process.

Quantization Text Generation

SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks

1 code implementation31 Jan 2024 Xingning Dong, Qingpei Guo, Tian Gan, Qing Wang, Jianlong Wu, Xiangyuan Ren, Yuan Cheng, Wei Chu

By employing one shared BERT-type network to refine textual and cross-modal features simultaneously, SNP is lightweight and could support various downstream applications.


Detecting and Grounding Multi-Modal Media Manipulation and Beyond

1 code implementation25 Sep 2023 Rui Shao, Tianxing Wu, Jianlong Wu, Liqiang Nie, Ziwei Liu

HAMMER performs 1) manipulation-aware contrastive learning between two uni-modal encoders as shallow manipulation reasoning, and 2) modality-aware cross-attention by multi-modal aggregator as deep manipulation reasoning.

Binary Classification Contrastive Learning +4

Temporal Sentence Grounding in Streaming Videos

1 code implementation14 Aug 2023 Tian Gan, Xiao Wang, Yan Sun, Jianlong Wu, Qingpei Guo, Liqiang Nie

The goal of TSGSV is to evaluate the relevance between a video stream and a given sentence query.

Sentence Temporal Sentence Grounding

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants

2 code implementations3 Aug 2023 Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip Torr, DaCheng Tao, Bernard Ghanem

Beyond the normal case, long-tail class incremental learning and few-shot class incremental learning are also proposed to consider the data imbalance and data scarcity, respectively, which are common in real-world implementations and further exacerbate the well-known problem of catastrophic forgetting.

Few-Shot Class-Incremental Learning Incremental Learning

Micro-video Tagging via Jointly Modeling Social Influence and Tag Relation

1 code implementation15 Mar 2023 Xiao Wang, Tian Gan, Yinwei Wei, Jianlong Wu, Dai Meng, Liqiang Nie

Existing methods mostly focus on analyzing video content, neglecting users' social influence and tag relation.

Link Prediction Relation +3

CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning

1 code implementation CVPR 2023 Jianlong Wu, Haozhe Yang, Tian Gan, Ning Ding, Feijun Jiang, Liqiang Nie

In the meantime, we make full use of the structured information in the hierarchical labels to learn an accurate affinity graph for contrastive learning.

Contrastive Learning

Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problem

no code implementations24 Jul 2022 Yudong Han, Liqiang Nie, Jianhua Yin, Jianlong Wu, Yan Yan

Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the answer whereas ignoring the image contents.

Question Answering Visual Question Answering

Semantic-aware Modular Capsule Routing for Visual Question Answering

no code implementations21 Jul 2022 Yudong Han, Jianhua Yin, Jianlong Wu, Yinwei Wei, Liqiang Nie

Visual Question Answering (VQA) is fundamentally compositional in nature, and many questions are simply answered by decomposing them into modular sub-problems.

Question Answering Visual Question Answering

HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors

1 code implementation12 Jul 2022 Luting Wang, Xiaojie Li, Yue Liao, Zeren Jiang, Jianlong Wu, Fei Wang, Chen Qian, Si Liu

We observe that the core difficulty for heterogeneous KD (hetero-KD) is the significant semantic gap between the backbone features of heterogeneous detectors due to the different optimization manners.

Knowledge Distillation Object +3

Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation

1 code implementation CVPR 2022 Xingning Dong, Tian Gan, Xuemeng Song, Jianlong Wu, Yuan Cheng, Liqiang Nie

Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compact summary graph.

Graph Generation Unbiased Scene Graph Generation

Dynamic Modality Interaction Modeling for Image-Text Retrieval

1 code implementation ACM Special Interest Group on Information Retrieval 2021 Leigang Qu, Meng Liu, Jianlong Wu, Zan Gao, Liqiang Nie

To address these issues, we develop a novel modality interaction modeling network based upon the routing mechanism, which is the first unified and dynamic multimodal interaction framework towards image-text retrieval.

Cross-Modal Retrieval Information Retrieval +2

Graph Contrastive Clustering

1 code implementation ICCV 2021 Huasong Zhong, Jianlong Wu, Chong Chen, Jianqiang Huang, Minghua Deng, Liqiang Nie, Zhouchen Lin, Xian-Sheng Hua

On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments.

Clustering Contrastive Learning

Fast and Differentiable Matrix Inverse and Its Extension to SVD

no code implementations1 Jan 2021 Xingyu Xie, Hao Kong, Jianlong Wu, Guangcan Liu, Zhouchen Lin

First of all, to perform matrix inverse, we provide a differentiable yet efficient way, named LD-Minv, which is a learnable deep neural network (DNN) with each layer being an $L$-th order matrix polynomial.

Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space

1 code implementation NeurIPS 2020 Shangchen Du, Shan You, Xiaojie Li, Jianlong Wu, Fei Wang, Chen Qian, ChangShui Zhang

In this paper, we examine the diversity of teacher models in the gradient space and regard the ensemble knowledge distillation as a multi-objective optimization problem so that we can determine a better optimization direction for the training of student network.

Knowledge Distillation

Multi-modal Cooking Workflow Construction for Food Recipes

no code implementations20 Aug 2020 Liangming Pan, Jingjing Chen, Jianlong Wu, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Yu-Gang Jiang, Tat-Seng Chua

Understanding food recipe requires anticipating the implicit causal effects of cooking actions, such that the recipe can be converted into a graph describing the temporal workflow of the recipe.

Common Sense Reasoning

Maximum-and-Concatenation Networks

1 code implementation ICML 2020 Xingyu Xie, Hao Kong, Jianlong Wu, Wayne Zhang, Guangcan Liu, Zhouchen Lin

While successful in many fields, deep neural networks (DNNs) still suffer from some open problems such as bad local minima and unsatisfactory generalization performance.

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families

no code implementations23 Nov 2019 Yibo Yang, Jianlong Wu, Hongyang Li, Xia Li, Tiancheng Shen, Zhouchen Lin

We establish a stability condition for ResNets with step sizes and weight parameters, and point out the effects of step sizes on the stability and performance.

SOGNet: Scene Overlap Graph Network for Panoptic Segmentation

1 code implementation18 Nov 2019 Yibo Yang, Hongyang Li, Xia Li, Qijie Zhao, Jianlong Wu, Zhouchen Lin

In order to overcome the lack of supervision, we introduce a differentiable module to resolve the overlap between any pair of instances.

Instance Segmentation Panoptic Segmentation +1

Differentiable Linearized ADMM

1 code implementation15 May 2019 Xingyu Xie, Jianlong Wu, Zhisheng Zhong, Guangcan Liu, Zhouchen Lin

Recently, a number of learning-based optimization methods that combine data-driven architectures with the classical optimization algorithms have been proposed and explored, showing superior empirical performance in solving various ill-posed inverse problems, but there is still a scarcity of rigorous analysis about the convergence behaviors of learning-based optimization.

Matrix Recovery with Implicitly Low-Rank Data

1 code implementation9 Nov 2018 Xingyu Xie, Jianlong Wu, Guangcan Liu, Jun Wang

To tackle this issue, we propose a novel method for matrix recovery in this paper, which could well handle the case where the target matrix is low-rank in an implicit feature space but high-rank or even full-rank in its original form.

Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining

no code implementations ECCV 2018 Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu, Hongbin Zha

In heavy rain, rain streaks have various directions and shapes, which can be regarded as the accumulation of multiple rain streak layers.

Single Image Deraining

Essential Tensor Learning for Multi-view Spectral Clustering

no code implementations10 Jul 2018 Jianlong Wu, Zhouchen Lin, Hongbin Zha

In this paper, we focus on the Markov chain based spectral clustering method and propose a novel essential tensor learning method to explore the high order correlations for multi-view representation.


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