Search Results for author: Peng Tang

Found 32 papers, 8 papers with code

Pay Less On Clinical Images: Asymmetric Multi-Modal Fusion Method For Efficient Multi-Label Skin Lesion Classification

no code implementations13 Jul 2024 Peng Tang, Tobias Lasser

In clinical settings, both clinical and dermoscopy images are captured for diagnosis; however, dermoscopy images exhibit more crucial visual features for multi-label skin lesion classification.

Lesion Classification Skin Lesion Classification

Single-Shared Network with Prior-Inspired Loss for Parameter-Efficient Multi-Modal Imaging Skin Lesion Classification

no code implementations28 Mar 2024 Peng Tang, Tobias Lasser

Firstly, unlike current methods that usually employ two individual models for for clinical and dermoscopy modalities, we verified that multimodal feature can be learned by sharing the parameters of encoder while leaving the individual modal-specific classifiers.

Lesion Classification Skin Lesion Classification

Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA

no code implementations25 Mar 2024 Zhuowan Li, Bhavan Jasani, Peng Tang, Shabnam Ghadar

In particular, our approach improves the accuracy of the previous state-of-the-art approach from 38% to 54% on the human-written questions in the ChartQA dataset, which needs strong reasoning.

Data Augmentation Question Answering +1

Federated Semi-supervised Learning for Medical Image Segmentation with intra-client and inter-client Consistency

no code implementations19 Mar 2024 Yubin Zheng, Peng Tang, Tianjie Ju, Weidong Qiu, Bo Yan

The intra-client and inter-client consistency learning are introduced to smooth predictions at the data level and avoid confirmation bias of local models.

Data Augmentation Federated Learning +5

Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA

no code implementations CVPR 2024 Zhuowan Li, Bhavan Jasani, Peng Tang, Shabnam Ghadar

In particular our approach improves the accuracy of the previous state-of-the-art approach from 38% to 54% on the human-written questions in the ChartQA dataset which needs strong reasoning.

Data Augmentation Question Answering +1

Feature Norm Regularized Federated Learning: Transforming Skewed Distributions into Global Insights

1 code implementation12 Dec 2023 Ke Hu, Weidong Qiu, Peng Tang

Our comprehensive analysis reveals that FNR-FL not only accelerates convergence but also significantly surpasses other contemporary federated learning algorithms in test accuracy, particularly under feature distribution skew scenarios.

Federated Learning

DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models

no code implementations15 Nov 2023 Peng Tang, Pengkai Zhu, Tian Li, Srikar Appalaraju, Vijay Mahadevan, R. Manmatha

Based on the multi-exit model, we perform step-level dynamic early exit during inference, where the model may decide to use fewer decoder layers based on its confidence of the current layer at each individual decoding step.

Decoder

Multiple-Question Multiple-Answer Text-VQA

no code implementations15 Nov 2023 Peng Tang, Srikar Appalaraju, R. Manmatha, Yusheng Xie, Vijay Mahadevan

We present Multiple-Question Multiple-Answer (MQMA), a novel approach to do text-VQA in encoder-decoder transformer models.

Decoder Denoising +2

SR-R$^2$KAC: Improving Single Image Defocus Deblurring

no code implementations30 Jul 2023 Peng Tang, Zhiqiang Xu, Pengfei Wei, Xiaobin Hu, Peilin Zhao, Xin Cao, Chunlai Zhou, Tobias Lasser

To further alleviate the contingent effect of recursive stacking, i. e., ringing artifacts, we add identity shortcuts between atrous convolutions to simulate residual deconvolutions.

Deblurring Image Defocus Deblurring

Graph-Ensemble Learning Model for Multi-label Skin Lesion Classification using Dermoscopy and Clinical Images

no code implementations4 Jul 2023 Peng Tang, Yang Nan, Tobias Lasser

However, most methods only focus on designing a better module for multi-modal data fusion; few methods explore utilizing the label correlation between SPC and skin disease for performance improvement.

Attribute Classification +4

RNN-Guard: Certified Robustness Against Multi-frame Attacks for Recurrent Neural Networks

no code implementations17 Apr 2023 Yunruo Zhang, Tianyu Du, Shouling Ji, Peng Tang, Shanqing Guo

In this paper, we propose the first certified defense against multi-frame attacks for RNNs called RNN-Guard.

Unsupervised Tissue Segmentation via Deep Constrained Gaussian Network

no code implementations4 Aug 2022 Yang Nan, Peng Tang, Guyue Zhang, Caihong Zeng, Zhihong Liu, Zhifan Gao, Heye Zhang, Guang Yang

However, most machine and deep learning based approaches are supervised and developed using a large number of training samples, in which the pixelwise annotations are expensive and sometimes can be impossible to obtain.

Segmentation

Automatic Fine-grained Glomerular Lesion Recognition in Kidney Pathology

no code implementations11 Mar 2022 Yang Nan, Fengyi Li, Peng Tang, Guyue Zhang, Caihong Zeng, Guotong Xie, Zhihong Liu, Guang Yang

Recognition of glomeruli lesions is the key for diagnosis and treatment planning in kidney pathology; however, the coexisting glomerular structures such as mesangial regions exacerbate the difficulties of this task.

Fine-Grained Image Classification whole slide images

Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction

no code implementations31 May 2021 Yan Wang, Peng Tang, Yuyin Zhou, Wei Shen, Elliot K. Fishman, Alan L. Yuille

We instantiate both the global and the local classifiers by multiple instance learning (MIL), where the attention guidance, indicating roughly where the PDAC regions are, is the key to bridging them: For global MIL based normal/PDAC classification, attention serves as a weight for each instance (voxel) during MIL pooling, which eliminates the distraction from the background; For local MIL based semi-supervised PDAC segmentation, the attention guidance is inductive, which not only provides bag-level pseudo-labels to training data without per-voxel annotations for MIL training, but also acts as a proxy of an instance-level classifier.

Multiple Instance Learning Segmentation

Shape-Texture Debiased Neural Network Training

1 code implementation ICLR 2021 Yingwei Li, Qihang Yu, Mingxing Tan, Jieru Mei, Peng Tang, Wei Shen, Alan Yuille, Cihang Xie

To prevent models from exclusively attending on a single cue in representation learning, we augment training data with images with conflicting shape and texture information (eg, an image of chimpanzee shape but with lemon texture) and, most importantly, provide the corresponding supervisions from shape and texture simultaneously.

Adversarial Robustness Data Augmentation +2

Look Closer to Ground Better: Weakly-Supervised Temporal Grounding of Sentence in Video

no code implementations25 Jan 2020 Zhenfang Chen, Lin Ma, Wenhan Luo, Peng Tang, Kwan-Yee K. Wong

In this paper, we study the problem of weakly-supervised temporal grounding of sentence in video.

Sentence

Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models

1 code implementation11 May 2019 Hongru Zhu, Peng Tang, Jeongho Park, Soojin Park, Alan Yuille

We test both humans and the above-mentioned computational models in a challenging task of object recognition under extreme occlusion, where target objects are heavily occluded by irrelevant real objects in real backgrounds.

Object Object Recognition

Weakly Supervised Region Proposal Network and Object Detection

no code implementations ECCV 2018 Peng Tang, Xinggang Wang, Angtian Wang, Yongluan Yan, Wenyu Liu, Junzhou Huang, Alan Yuille

The Convolutional Neural Network (CNN) based region proposal generation method (i. e. region proposal network), trained using bounding box annotations, is an essential component in modern fully supervised object detectors.

Object object-detection +2

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

4 code implementations9 Jul 2018 Peng Tang, Xinggang Wang, Song Bai, Wei Shen, Xiang Bai, Wenyu Liu, Alan Yuille

The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one.

Multiple Instance Learning Object +3

Training Multi-organ Segmentation Networks with Sample Selection by Relaxed Upper Confident Bound

no code implementations7 Apr 2018 Yan Wang, Yuyin Zhou, Peng Tang, Wei Shen, Elliot K. Fishman, Alan L. Yuille

Based on the fact that very hard samples might have annotation errors, we propose a new sample selection policy, named Relaxed Upper Confident Bound (RUCB).

Image Segmentation Medical Image Segmentation +3

Semi-Supervised Multi-Organ Segmentation via Deep Multi-Planar Co-Training

no code implementations7 Apr 2018 Yuyin Zhou, Yan Wang, Peng Tang, Song Bai, Wei Shen, Elliot K. Fishman, Alan L. Yuille

In multi-organ segmentation of abdominal CT scans, most existing fully supervised deep learning algorithms require lots of voxel-wise annotations, which are usually difficult, expensive, and slow to obtain.

Image Segmentation Organ Segmentation +2

Object Detection in Videos by High Quality Object Linking

no code implementations30 Jan 2018 Peng Tang, Chunyu Wang, Xinggang Wang, Wenyu Liu, Wen-Jun Zeng, Jingdong Wang

In particular, our method improves results by 8. 8% over the static image detector for fast moving objects.

General Classification Object +3

Rethink ReLU to Training Better CNNs

no code implementations19 Sep 2017 Gangming Zhao, Zhao-Xiang Zhang, He Guan, Peng Tang, Jingdong Wang

Most of convolutional neural networks share the same characteristic: each convolutional layer is followed by a nonlinear activation layer where Rectified Linear Unit (ReLU) is the most widely used.

Deep Patch Learning for Weakly Supervised Object Classification and Discovery

1 code implementation6 May 2017 Peng Tang, Xinggang Wang, Zilong Huang, Xiang Bai, Wenyu Liu

Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background.

Classification General Classification +3

Multiple Instance Detection Network with Online Instance Classifier Refinement

4 code implementations CVPR 2017 Peng Tang, Xinggang Wang, Xiang Bai, Wenyu Liu

We propose a novel online instance classifier refinement algorithm to integrate MIL and the instance classifier refinement procedure into a single deep network, and train the network end-to-end with only image-level supervision, i. e., without object location information.

Multiple Instance Learning Object +3

Revisiting Multiple Instance Neural Networks

no code implementations8 Oct 2016 Xinggang Wang, Yongluan Yan, Peng Tang, Xiang Bai, Wenyu Liu

We propose a new multiple instance neural network to learn bag representations, which is different from the existing multiple instance neural networks that focus on estimating instance label.

Multiple Instance Learning Weakly-supervised Learning

Deep FisherNet for Object Classification

no code implementations31 Jul 2016 Peng Tang, Xinggang Wang, Baoguang Shi, Xiang Bai, Wenyu Liu, Zhuowen Tu

Our proposed FisherNet combines convolutional neural network training and Fisher Vector encoding in a single end-to-end structure.

Classification Computational Efficiency +3

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