Search Results for author:
Found 29 papers, 10 papers with code
Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns
We present a comprehensive study of sparse attention patterns in Transformer models.
SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis
On the highly competitive ADE20K and COCO benchmarks, our data generation method markedly improves the performance of state-of-the-art segmentation models in semantic segmentation, panoptic segmentation, and instance segmentation.
AIMS: All-Inclusive Multi-Level Segmentation
Despite the progress of image segmentation for accurate visual entity segmentation, completing the diverse requirements of image editing applications for different-level region-of-interest selections remains unsolved.
TopNet: Transformer-based Object Placement Network for Image Compositing
Given a background image and a segmented object, the goal is to train a model to predict plausible placements (location and scale) of the object for compositing.
High Quality Entity Segmentation
Given the high-quality and -resolution nature of the dataset, we propose CropFormer which is designed to tackle the intractability of instance-level segmentation on high-resolution images.
SceneComposer: Any-Level Semantic Image Synthesis
We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes.
High-Quality Entity Segmentation
It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image.
Improving the Reliability for Confidence Estimation
Confidence estimation, a task that aims to evaluate the trustworthiness of the model's prediction output during deployment, has received lots of research attention recently, due to its importance for the safe deployment of deep models.
Text-to-Image Generation via Implicit Visual Guidance and Hypernetwork
We develop an approach for text-to-image generation that embraces additional retrieval images, driven by a combination of implicit visual guidance loss and generative objectives.
Meta Spatio-Temporal Debiasing for Video Scene Graph Generation
Video scene graph generation (VidSGG) aims to parse the video content into scene graphs, which involves modeling the spatio-temporal contextual information in the video.
Unified Pretraining Framework for Document Understanding
Document intelligence automates the extraction of information from documents and supports many business applications.
Ranked #7 on
Document Layout Analysis
on PubLayNet val
GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing
To move a step further, this paper proposes GALA (Geometry-and-Lighting-Aware), a generic foreground object search method with discriminative modeling on geometry and lighting compatibility for open-world image compositing.
CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation
To improve instance-level detection/segmentation performance, existing self-supervised and semi-supervised methods extract either task-unrelated or task-specific training signals from unlabeled data.
UniDoc: Unified Pretraining Framework for Document Understanding
Document intelligence automates the extraction of information from documents and supports many business applications.
High Quality Segmentation for Ultra High-resolution Images
To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation.
Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling
To address this, we propose a cross-modal pseudo-labeling framework, which generates training pseudo masks by aligning word semantics in captions with visual features of object masks in images.
Multi-Scale Aligned Distillation for Low-Resolution Detection
However, this option traditionally hurts the detection performance much.
Open-World Entity Segmentation
By removing the need of class label prediction, the models trained for such task can focus more on improving segmentation quality.
SelfDoc: Self-Supervised Document Representation Learning
For downstream usage, we propose a novel modality-adaptive attention mechanism for multimodal feature fusion by adaptively emphasizing language and vision signals.
Multimodal Contrastive Training for Visual Representation Learning
We first train our model on COCO and evaluate the learned visual representations on various downstream tasks including image classification, object detection, and instance segmentation.
Self-Supervised Relationship Probing
Structured representations of images that model visual relationships are beneficial for many vision and vision-language applications.
Scaling Object Detection by Transferring Classification Weights
Large scale object detection datasets are constantly increasing their size in terms of the number of classes and annotations count.
Motion-Guided Cascaded Refinement Network for Video Object Segmentation
Then, the proposed Cascaded Refinement Network(CRN) takes the coarse segmentation as guidance to generate an accurate segmentation of full resolution.
Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification
Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space.
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
We propose a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint).
DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows
Deluge Networks (DelugeNets) are deep neural networks which efficiently facilitate massive cross-layer information inflows from preceding layers to succeeding layers.
Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle
Visual representation is crucial for a visual tracking method's performances.
Recurrent Attentional Networks for Saliency Detection
Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection.
Recent Advances in Convolutional Neural Networks
In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing.
