Search Results for author:
Found 43 papers, 15 papers with code
OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction
By publishing and maintaining the dataset, we provide a high-quality benchmark for satellite-based map construction and downstream tasks like autonomous driving.
A Survey of Low-shot Vision-Language Model Adaptation via Representer Theorem
As such, this survey paper first proposes a unified computational framework from the perspective of Representer Theorem and then derives many of the existing methods by specializing this framework.
Calibrated Cache Model for Few-Shot Vision-Language Model Adaptation
Weight Calibration introduces a precision matrix into the weight function to adequately model the relation between training samples, transforming the existing cache model to a Gaussian Process (GP) regressor, which could be more accurate than N-W estimator.
AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization
In this study, we introduce a new problem raised by social media and photojournalism, named Image Address Localization (IAL), which aims to predict the readable textual address where an image was taken.
Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis
This paper presents a novel non-rigid point set registration method that is inspired by unsupervised clustering analysis.
A Multimodal Transformer for Live Streaming Highlight Prediction
Therefore, we propose a novel Border-aware Pairwise Loss to learn from a large-scale dataset and utilize user implicit feedback as a weak supervision signal.
MMBee: Live Streaming Gift-Sending Recommendations via Multi-Modal Fusion and Behaviour Expansion
To alleviate the sparsity issue of gifting behaviors, we present a novel Graph-guided Interest Expansion (GIE) approach that learns both user and streamer representations on large-scale gifting graphs with multi-modal attributes.
Xwin-LM: Strong and Scalable Alignment Practice for LLMs
In this work, we present Xwin-LM, a comprehensive suite of alignment methodologies for large language models (LLMs).
Enhancing Visual Continual Learning with Language-Guided Supervision
Existing methods commonly utilize the one-hot labels and randomly initialize the classifier head.
Defying Imbalanced Forgetting in Class Incremental Learning
This intriguing phenomenon, discovered in replay-based Class Incremental Learning (CIL), highlights the imbalanced forgetting of learned classes, as their accuracy is similar before the occurrence of catastrophic forgetting.
Continual Forgetting for Pre-trained Vision Models
(i) For unwanted knowledge, efficient and effective deleting is crucial.
ContentCTR: Frame-level Live Streaming Click-Through Rate Prediction with Multimodal Transformer
However, most previous works treat the live as a whole item and explore the Click-through-Rate (CTR) prediction framework on item-level, neglecting that the dynamic changes that occur even within the same live room.
Free Lunch for Generating Effective Outlier Supervision
Generally, existing approaches in dealing with out-of-distribution (OOD) detection mainly focus on the statistical difference between the features of OOD and in-distribution (ID) data extracted by the classifiers.
Bilateral Memory Consolidation for Continual Learning
Humans are proficient at continuously acquiring and integrating new knowledge.
A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset
Furthermore, based on this dataset, we propose an end-to-end model that jointly optimizes the video understanding objective with knowledge graph embedding, which can not only better inject factual knowledge into video understanding but also generate effective multi-modal entity embedding for KG.
Expanding Language-Image Pretrained Models for General Video Recognition
Extensive experiments demonstrate that our approach is effective and can be generalized to different video recognition scenarios.
Ranked #9 on
Zero-Shot Action Recognition
on Kinetics
Domain Decorrelation with Potential Energy Ranking
PoER helps the neural networks to capture label-related features which contain the domain information first in shallow layers and then distills the label-discriminative representations out progressively, enforcing the neural networks to be aware of the characteristic of objects and background which is vital to the generation of domain-invariant features.
Gradient Concealment: Free Lunch for Defending Adversarial Attacks
Recent studies show that the deep neural networks (DNNs) have achieved great success in various tasks.
Continual Stereo Matching of Continuous Driving Scenes With Growing Architecture
The deep stereo models have achieved state-of-the-art performance on driving scenes, but they suffer from severe performance degradation when tested on unseen scenes.
Boundary Aware Learning for Out-of-distribution Detection
This paper focuses on the problem of detecting out-of-distribution (ood) samples with neural nets.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Differentiable Convolution Search for Point Cloud Processing
It can work in a purely data-driven manner and thus is capable of auto-creating a group of suitable convolutions for geometric shape modeling.
Alleviating Mode Collapse in GAN via Diversity Penalty Module
We compare the proposed method with Unrolled GAN (Metz et al. 2016), BourGAN (Xiao, Zhong, and Zheng 2018), PacGAN (Lin et al. 2018), VEEGAN (Srivastava et al. 2017) and ALI (Dumoulin et al. 2016) on 2D synthetic dataset, and results show that the diversity penalty module can help GAN capture much more modes of the data distribution.
Enhanced Boundary Learning for Glass-like Object Segmentation
We use these two modules to design a decoder that generates accurate and clean segmentation results, especially on the object contours.
Ranked #20 on
Thermal Image Segmentation
on RGB-T-Glass-Segmentation
Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement
The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i. e. style feature, and the feature representing the invariant semantic content, i. e. content feature.
Spatio-Temporal Graph Structure Learning for Traffic Forecasting
To address these issues, we propose a novel framework named Structure Learning Convolution (SLC) that enables to extend the traditional convolutional neural network (CNN) to graph domains and learn the graph structure for traffic forecasting.
Ranked #4 on
Traffic Prediction
on METR-LA
DATA: Differentiable ArchiTecture Approximation
Neural architecture search (NAS) is inherently subject to the gap of architectures during searching and validating.
FontGAN: A Unified Generative Framework for Chinese Character Stylization and De-stylization
In our model, we decouple character images into style representation and content representation, which facilitates more precise control of these two types of variables, thereby improving the quality of the generated results.
DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing
Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable.
Ranked #23 on
3D Part Segmentation
on ShapeNet-Part
Joint haze image synthesis and dehazing with mmd-vae losses
Fog and haze are weathers with low visibility which are adversarial to the driving safety of intelligent vehicles equipped with optical sensors like cameras and LiDARs.
Differentiable Architecture Search with Ensemble Gumbel-Softmax
For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency.
Deep Discriminative Clustering Analysis
Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning.
DetNAS: Backbone Search for Object Detection
In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection.
EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
In our implementations, architectures are first searched on a small dataset, e. g., CIFAR-10.
Structure-Aware Convolutional Neural Networks
Convolutional neural networks (CNNs) are inherently subject to invariable filters that can only aggregate local inputs with the same topological structures.
Joint Neural Architecture Search and Quantization
Here our goal is to automatically find a compact neural network model with high performance that is suitable for mobile devices.
Exploiting Vector Fields for Geometric Rectification of Distorted Document Images
This paper proposes a segment-free method for geometric rectification of a distorted document image captured by a hand-held camera.
Reinforced Evolutionary Neural Architecture Search
To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search (RE- NAS), which is an evolutionary method with the reinforced mutation for NAS.
Deep Adaptive Image Clustering
The main challenge is that the ground-truth similarities are unknown in image clustering.
Ranked #9 on
Image Clustering
on Tiny-ImageNet
AMVH: Asymmetric Multi-Valued Hashing
(2) A multi-integer-embedding is employed for compressing the whole database, which is modeled by binary sparse representation with fixed sparsity.
Extraction of Virtual Baselines From Distorted Document Images Using Curvilinear Projection
In this paper, we propose an efficient method for accurate extraction of these virtual visual cues from a curved document image.
Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity
Based on this observation, we exploit a learning-based sparsity method to simultaneously learn the HU results and a sparse guidance map.
Active Flattening of Curved Document Images via Two Structured Beams
Document images captured by a digital camera often suffer from serious geometric distortions.
Spectral Unmixing via Data-guided Sparsity
Hyperspectral unmixing, the process of estimating a common set of spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization and understanding.
