Search Results for author:
Found 38 papers, 14 papers with code
Large Model driven Radiology Report Generation with Clinical Quality Reinforcement Learning
Finally, to better reflect the clinical significant and insignificant errors that radiologists would normally assign in the report, we introduce a novel clinical quality reinforcement learning strategy.
AdaTreeFormer: Few Shot Domain Adaptation for Tree Counting from a Single High-Resolution Image
For the latter, an attention-to-adapt mechanism is introduced to distill relevant information from different domains while generating tree density maps; a hierarchical cross-domain feature alignment scheme is proposed that progressively aligns the features from the source and target domains.
Multitask Learning in Minimally Invasive Surgical Vision: A Review
Recent advancements in machine learning and computer vision have led to successful applications in analyzing videos obtained from MIS with the promise of alleviating challenges in MIS videos.
Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation
Previous methods mitigate this issue by exploring image enhancement or object detection techniques with real low-light image datasets.
VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation
Panoptic Scene Graph Generation (PSG) aims at achieving a comprehensive image understanding by simultaneously segmenting objects and predicting relations among objects.
Ranked #1 on
Panoptic Scene Graph Generation
on PSG Dataset
IMITATE: Clinical Prior Guided Hierarchical Vision-Language Pre-training
The framework derives multi-level visual features from the chest X-ray (CXR) images and separately aligns these features with the descriptive and the conclusive text encoded in the hierarchical medical report.
An investigation into the impact of deep learning model choice on sex and race bias in cardiac MR segmentation
However, the severity and nature of the bias varies between the models, highlighting the importance of model choice when attempting to train fair AI-based segmentation models for medical imaging tasks.
SegMatch: A semi-supervised learning method for surgical instrument segmentation
Surgical instrument segmentation is recognised as a key enabler to provide advanced surgical assistance and improve computer assisted interventions.
When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review
Second, it presents the different challenges arising from such a multi-objective optimisation scheme.
TreeFormer: a Semi-Supervised Transformer-based Framework for Tree Counting from a Single High Resolution Image
Automatic tree density estimation and counting using single aerial and satellite images is a challenging task in photogrammetry and remote sensing, yet has an important role in forest management.
LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation
Referring video object segmentation (RVOS) aims to segment the target instance referred by a given text expression in a video clip.
Ranked #12 on
Referring Expression Segmentation
on Refer-YouTube-VOS (2021 public validation)
(using extra training data)
Referring Expression Segmentation
Referring Video Object Segmentation
+2
HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation
Existing unbiased methods tackle the long-tail problem by data/loss rebalancing to favor low-frequency relations.
Ranked #2 on
Panoptic Scene Graph Generation
on PSG Dataset
Multi-modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense Reasoning
On the other hand, BLIP-2 as an MLLM is employed to process images and texts, and the referring expressions in texts involving specific visual objects are modified with linguistic object labels to serve as comprehensible MLLM inputs.
Domain-General Crowd Counting in Unseen Scenarios
In this paper, we aim to train a model based on a single source domain which can generalize well on any unseen domain.
Exploring and Eliciting Needs and Preferences from Editors for Wikidata Recommendations
Our aim with this paper is to elicit the user requirements for a Wikidata recommendations system.
$α$ DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling
Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning.
Ranked #10 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-100
Facial Video-based Remote Physiological Measurement via Self-supervised Learning
Facial video-based remote physiological measurement aims to estimate remote photoplethysmography (rPPG) signals from human face videos and then measure multiple vital signs (e. g. heart rate, respiration frequency) from rPPG signals.
A systematic study of race and sex bias in CNN-based cardiac MR segmentation
We present the first systematic study of the impact of training set imbalance on race and sex bias in CNN-based segmentation.
Redesigning Multi-Scale Neural Network for Crowd Counting
In this work, we redesign the multi-scale neural network by introducing a hierarchical mixture of density experts, which hierarchically merges multi-scale density maps for crowd counting.
Enhancing Space-time Video Super-resolution via Spatial-temporal Feature Interaction
A popular solution is to first increase the frame rate of the video; then perform feature refinement among different frame features; and last increase the spatial resolutions of these features.
Dam reservoir extraction from remote sensing imagery using tailored metric learning strategies
Extensive experiments were conducted on this benchmark in the water body segmentation task, dam reservoir recognition task, and the joint dam reservoir extraction task.
Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representations
In this paper, we propose a new framework to boost ZSL by explicitly learning attribute prototypes beyond images and contrastively optimizing them with attribute-level features within images.
Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model
In this paper, we introduce a novel method, detection prompt (DetPro), to learn continuous prompt representations for open-vocabulary object detection based on the pre-trained vision-language model.
MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning
Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is introduced with triplet loss formulated on the pixel-level embedding of the input image.
Learning to Recommend Items to Wikidata Editors
The system uses a hybrid of content-based and collaborative filtering techniques to rank items for editors relying on both item features and item-editor previous interaction.
Detecting Human-Object Interaction with Mixed Supervision
Human object interaction (HOI) detection is an important task in image understanding and reasoning.
Fast Fourier Intrinsic Network
We address the problem of decomposing an image into albedo and shading.
Restoring Negative Information in Few-Shot Object Detection
In this paper, we restore the negative information in few-shot object detection by introducing a new negative- and positive-representative based metric learning framework and a new inference scheme with negative and positive representatives.
Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer
We formulate the mutual transformations between the outputs of regression- and detection-based models as two scene-agnostic transformers which enable knowledge distillation between the two models.
Defending Adversarial Examples via DNN Bottleneck Reinforcement
This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks.
Active Crowd Counting with Limited Supervision
To learn a reliable people counter from crowd images, head center annotations are normally required.
Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images
Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set.
Ranked #23 on
Weakly Supervised Object Detection
on PASCAL VOC 2012 test
(using extra training data)
Point in, Box out: Beyond Counting Persons in Crowds
In the end, we propose a curriculum learning strategy to train the network from images of relatively accurate and easy pseudo ground truth first.
Revisiting Perspective Information for Efficient Crowd Counting
Modern crowd counting methods employ deep neural networks to estimate crowd counts via crowd density regressions.
Crowd counting via scale-adaptive convolutional neural network
The task of crowd counting is to automatically estimate the pedestrian number in crowd images.
Weakly Supervised Object Localization Using Things and Stuff Transfer
We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations.
Weakly Supervised Object Localization Using Size Estimates
We present a technique for weakly supervised object localization (WSOL), building on the observation that WSOL algorithms usually work better on images with bigger objects.
Early Burst Detection for Memory-Efficient Image Retrieval
Then, we show the interest of using this strategy in an asymmetrical manner, with only the database features being aggregated but not those of the query.
