Search Results for author:
Found 30 papers, 8 papers with code
Deep FisherNet for Object Classification
Our proposed FisherNet combines convolutional neural network training and Fisher Vector encoding in a single end-to-end structure.
Revisiting Multiple Instance Neural Networks
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 Detection Network with Online Instance Classifier Refinement
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.
Ranked #4 on
Weakly Supervised Object Detection
on ImageNet
Deep Patch Learning for Weakly Supervised Object Classification and Discovery
Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background.
Rethink ReLU to Training Better CNNs
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.
Object Detection in Videos by High Quality Object Linking
In particular, our method improves results by 8. 8% over the static image detector for fast moving objects.
Semi-Supervised Multi-Organ Segmentation via Deep Multi-Planar Co-Training
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.
Training Multi-organ Segmentation Networks with Sample Selection by Relaxed Upper Confident Bound
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).
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection
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.
Ranked #1 on
Weakly Supervised Object Detection
on ImageNet
Weakly Supervised Region Proposal Network and Object Detection
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.
Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models
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.
Proposal Learning for Semi-Supervised Object Detection
two-stage object detectors) by training on both labeled and unlabeled data.
Look Closer to Ground Better: Weakly-Supervised Temporal Grounding of Sentence in Video
In this paper, we study the problem of weakly-supervised temporal grounding of sentence in video.
Shape-Texture Debiased Neural Network Training
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.
Ranked #598 on
Image Classification
on ImageNet
Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction
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.
Automatic Fine-grained Glomerular Lesion Recognition in Kidney Pathology
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.
Unsupervised Tissue Segmentation via Deep Constrained Gaussian Network
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.
Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation
especially for cohorts with different lung diseases.
RNN-Guard: Certified Robustness Against Multi-frame Attacks for Recurrent Neural Networks
In this paper, we propose the first certified defense against multi-frame attacks for RNNs called RNN-Guard.
DocFormerv2: Local Features for Document Understanding
We propose DocFormerv2, a multi-modal transformer for Visual Document Understanding (VDU).
Ranked #9 on
Visual Question Answering (VQA)
on DocVQA test
(using extra training data)
document understanding
Optical Character Recognition (OCR)
+1
Graph-Ensemble Learning Model for Multi-label Skin Lesion Classification using Dermoscopy and Clinical Images
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.
SR-R$^2$KAC: Improving Single Image Defocus Deblurring
To further alleviate the contingent effect of recursive stacking, i. e., ringing artifacts, we add identity shortcuts between atrous convolutions to simulate residual deconvolutions.
DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models
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.
Multiple-Question Multiple-Answer Text-VQA
We present Multiple-Question Multiple-Answer (MQMA), a novel approach to do text-VQA in encoder-decoder transformer models.
Joint-Individual Fusion Structure with Fusion Attention Module for Multi-Modal Skin Cancer Classification
Most convolutional neural network (CNN) based methods for skin cancer classification obtain their results using only dermatological images.
Feature Norm Regularized Federated Learning: Transforming Skewed Distributions into Global Insights
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.
SSDRec: Self-Augmented Sequence Denoising for Sequential Recommendation
In the second stage, we devise a self-augmentation module to augment sequences to alleviate OUPs.
Federated Semi-supervised Learning for Medical Image Segmentation with intra-client and inter-client Consistency
The intra-client and inter-client consistency learning are introduced to smooth predictions at the data level and avoid confirmation bias of local models.
Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA
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.
Single-Shared Network with Prior-Inspired Loss for Parameter-Efficient Multi-Modal Imaging Skin Lesion Classification
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.
