Search Results for author: Minghan Li

Found 27 papers, 16 papers with code

An Encoder Attribution Analysis for Dense Passage Retriever in Open-Domain Question Answering

no code implementations NAACL (TrustNLP) 2022 Minghan Li, Xueguang Ma, Jimmy Lin

The bi-encoder design of dense passage retriever (DPR) is a key factor to its success in open-domain question answering (QA), yet it is unclear how DPR’s question encoder and passage encoder individually contributes to overall performance, which we refer to as the encoder attribution problem.

Open-Domain Question Answering Retrieval

Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question Answering

1 code implementation Findings (EMNLP) 2021 Minghan Li, Ming Li, Kun Xiong, Jimmy Lin

Our method reaches state-of-the-art performance on 5 benchmark QA datasets, with up to 10% improvement in top-100 accuracy compared to a joint-training multi-task DPR on SQuAD.

Open-Domain Question Answering Retrieval

Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval

no code implementations EMNLP 2021 Xueguang Ma, Minghan Li, Kai Sun, Ji Xin, Jimmy Lin

Recent work has shown that dense passage retrieval techniques achieve better ranking accuracy in open-domain question answering compared to sparse retrieval techniques such as BM25, but at the cost of large space and memory requirements.

Open-Domain Question Answering Passage Retrieval +2

OpenSD: Unified Open-Vocabulary Segmentation and Detection

1 code implementation10 Dec 2023 Shuai Li, Minghan Li, Pengfei Wang, Lei Zhang

To address these challenges, we present a universal transformer-based framework, abbreviated as OpenSD, which utilizes the same architecture and network parameters to handle open-vocabulary segmentation and detection tasks.

Segmentation Zero Shot Segmentation

Generate, Filter, and Fuse: Query Expansion via Multi-Step Keyword Generation for Zero-Shot Neural Rankers

no code implementations15 Nov 2023 Minghan Li, Honglei Zhuang, Kai Hui, Zhen Qin, Jimmy Lin, Rolf Jagerman, Xuanhui Wang, Michael Bendersky

We first show that directly applying the expansion techniques in the current literature to state-of-the-art neural rankers can result in deteriorated zero-shot performance.

Instruction Following Language Modelling +1

BoxVIS: Video Instance Segmentation with Box Annotations

1 code implementation26 Mar 2023 Minghan Li, Lei Zhang

As a result, the amount of pixel-wise annotations in existing video instance segmentation (VIS) datasets is small, limiting the generalization capability of trained VIS models.

Instance Segmentation Semantic Segmentation +2

MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos

1 code implementation CVPR 2023 Minghan Li, Shuai Li, Wangmeng Xiang, Lei Zhang

The proposed MDQE is the first VIS method with per-clip input that achieves state-of-the-art results on challenging videos and competitive performance on simple videos.

Instance Segmentation Semantic Segmentation +1

One-to-Few Label Assignment for End-to-End Dense Detection

1 code implementation CVPR 2023 Shuai Li, Minghan Li, Ruihuang Li, Chenhang He, Lei Zhang

The positive and negative weights of these soft anchors are dynamically adjusted during training so that they can contribute more to ``representation learning'' in the early training stage, and contribute more to ``duplicated prediction removal'' in the later stage.

Representation Learning

How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval

1 code implementation15 Feb 2023 Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, Xilun Chen

We hence propose a new DA approach with diverse queries and sources of supervision to progressively train a generalizable DR. As a result, DRAGON, our dense retriever trained with diverse augmentation, is the first BERT-base-sized DR to achieve state-of-the-art effectiveness in both supervised and zero-shot evaluations and even competes with models using more complex late interaction (ColBERTv2 and SPLADE++).

Contrastive Learning Data Augmentation +1

SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes

1 code implementation13 Feb 2023 Minghan Li, Sheng-Chieh Lin, Xueguang Ma, Jimmy Lin

Multi-vector retrieval methods have demonstrated their effectiveness on various retrieval datasets, and among them, ColBERT is the most established method based on the late interaction of contextualized token embeddings of pre-trained language models.

Information Retrieval Retrieval

Improving Out-of-Distribution Generalization of Neural Rerankers with Contextualized Late Interaction

no code implementations13 Feb 2023 Xinyu Zhang, Minghan Li, Jimmy Lin

Recent progress in information retrieval finds that embedding query and document representation into multi-vector yields a robust bi-encoder retriever on out-of-distribution datasets.

Information Retrieval Out-of-Distribution Generalization +1

Domain Adaptation for Dense Retrieval through Self-Supervision by Pseudo-Relevance Labeling

no code implementations13 Dec 2022 Minghan Li, Eric Gaussier

To address this issue, researchers have resorted to adversarial learning and query generation approaches; both approaches nevertheless resulted in limited improvements.

Domain Adaptation Information Retrieval +2

CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval

1 code implementation18 Nov 2022 Minghan Li, Sheng-Chieh Lin, Barlas Oguz, Asish Ghoshal, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, Xilun Chen

In this paper, we unify different multi-vector retrieval models from a token routing viewpoint and propose conditional token interaction via dynamic lexical routing, namely CITADEL, for efficient and effective multi-vector retrieval.


Query Expansion Using Contextual Clue Sampling with Language Models

no code implementations13 Oct 2022 Linqing Liu, Minghan Li, Jimmy Lin, Sebastian Riedel, Pontus Stenetorp

To balance these two considerations, we propose a combination of an effective filtering strategy and fusion of the retrieved documents based on the generation probability of each context.

Information Retrieval Language Modelling +1

Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking

1 code implementation19 May 2022 Minghan Li, Xinyu Zhang, Ji Xin, Hongyang Zhang, Jimmy Lin

For example, on MS MARCO Passage v1, our method yields an average candidate set size of 27 out of 1, 000 which increases the reranking speed by about 37 times, while the MRR@10 is greater than a pre-specified value of 0. 38 with about 90% empirical coverage and the empirical baselines fail to provide such guarantee.

Computational Efficiency Information Retrieval +1

Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

1 code implementation CVPR 2022 Yabin Zhang, Minghan Li, Ruihuang Li, Kui Jia, Lei Zhang

In this work, we, for the first time to our best knowledge, propose to perform Exact Feature Distribution Matching (EFDM) by exactly matching the empirical Cumulative Distribution Functions (eCDFs) of image features, which could be implemented by applying the Exact Histogram Matching (EHM) in the image feature space.

Domain Generalization Style Transfer

One-stage Video Instance Segmentation: From Frame-in Frame-out to Clip-in Clip-out

no code implementations12 Mar 2022 Minghan Li, Lei Zhang

Based on the fact that adjacent frames in a short clip are highly coherent in content, we propose to extend the one-stage FiFo framework to a clip-in clip-out (CiCo) one, which performs VIS clip by clip.

Instance Segmentation Semantic Segmentation +1

The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval

1 code implementation18 Nov 2021 Minghan Li, Diana Nicoleta Popa, Johan Chagnon, Yagmur Gizem Cinar, Eric Gaussier

On a wide range of natural language processing and information retrieval tasks, transformer-based models, particularly pre-trained language models like BERT, have demonstrated tremendous effectiveness.

Information Retrieval Retrieval

Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering

no code implementations4 Oct 2021 Minghan Li, Jimmy Lin

Previous work on generalization of DPR mainly focus on testing both encoders in tandem on out-of-distribution (OOD) question-answering (QA) tasks, which is also known as domain adaptation.

Domain Adaptation Open-Domain Question Answering +2

SmoothI: Smooth Rank Indicators for Differentiable IR Metrics

1 code implementation3 May 2021 Thibaut Thonet, Yagmur Gizem Cinar, Eric Gaussier, Minghan Li, Jean-Michel Renders

To address this shortcoming, we propose SmoothI, a smooth approximation of rank indicators that serves as a basic building block to devise differentiable approximations of IR metrics.

Information Retrieval Learning-To-Rank +1

Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation

1 code implementation CVPR 2021 Minghan Li, Shuai Li, Lida Li, Lei Zhang

To further explore temporal correlation among video frames, we aggregate a temporal fusion module to infer instance masks from each frame to its adjacent frames, which helps our framework to handle challenging videos such as motion blur, partial occlusion and unusual object-to-camera poses.

Instance Segmentation Segmentation +3

Learning to Rank for Active Learning: A Listwise Approach

no code implementations31 Jul 2020 Minghan Li, Xialei Liu, Joost Van de Weijer, Bogdan Raducanu

Active learning emerged as an alternative to alleviate the effort to label huge amount of data for data hungry applications (such as image/video indexing and retrieval, autonomous driving, etc.).

Active Learning Autonomous Driving +3

A Survey on Rain Removal from Video and Single Image

1 code implementation18 Sep 2019 Hong Wang, Yichen Wu, Minghan Li, Qian Zhao, Deyu Meng

The investigations on rain removal from video or a single image has thus been attracting much research attention in the field of computer vision and pattern recognition, and various methods have been proposed against this task in the recent years.

Rain Removal

Video Rain/Snow Removal by Transformed Online Multiscale Convolutional Sparse Coding

1 code implementation13 Sep 2019 Minghan Li, Xiangyong Cao, Qian Zhao, Lei Zhang, Chenqiang Gao, Deyu Meng

Furthermore, a transformation operator imposed on the background scenes is further embedded into the proposed model, which finely conveys the dynamic background transformations, such as rotations, scalings and distortions, inevitably existed in a real video sequence.

Snow Removal

Accelerating Large Scale Knowledge Distillation via Dynamic Importance Sampling

no code implementations3 Dec 2018 Minghan Li, Tanli Zuo, Ruicheng Li, Martha White, Wei-Shi Zheng

Knowledge distillation is an effective technique that transfers knowledge from a large teacher model to a shallow student.

Knowledge Distillation Machine Translation +2

Video Rain Streak Removal by Multiscale Convolutional Sparse Coding

no code implementations CVPR 2018 Minghan Li, Qi Xie, Qian Zhao, Wei Wei, Shuhang Gu, Jing Tao, Deyu Meng

Based on such understanding, we specifically formulate both characteristics into a multiscale convolutional sparse coding (MS-CSC) model for the video rain streak removal task.

Rain Removal

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