Search Results for author:
Found 29 papers, 13 papers with code
Binary Neural Networks: A Survey
The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices.
Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
This paper presents ER-NeRF, a novel conditional Neural Radiance Fields (NeRF) based architecture for talking portrait synthesis that can concurrently achieve fast convergence, real-time rendering, and state-of-the-art performance with small model size.
Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained.
DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
Our motivation stems from the highly efficient representation and surprising quality of the recent 3D Gaussian Splatting, despite it will encounter a geometry degradation when input views decrease.
Goal-Oriented Gaze Estimation for Zero-Shot Learning
Therefore, we introduce a novel goal-oriented gaze estimation module (GEM) to improve the discriminative attribute localization based on the class-level attributes for ZSL.
Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
The stereo contrastive feature loss function explicitly constrains the consistency between learned features of matching pixel pairs which are observations of the same 3D points.
Unsupervised Recognition of Unknown Objects for Open-World Object Detection
Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge.
Robust Synthetic-to-Real Transfer for Stereo Matching
With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains.
Simple Image-level Classification Improves Open-vocabulary Object Detection
This limits their capability in detecting hard objects of small, blurred, or occluded appearance from novel/base categories, whose detection heavily relies on contextual information.
Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning
To this end, we introduce a novel calibrated outlier class learning (COCL) approach, in which 1) a debiased large margin learning method is introduced in the outlier class learning to distinguish OOD samples from both head and tail classes in the representation space and 2) an outlier-class-aware logit calibration method is defined to enhance the long-tailed classification confidence.
Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds
Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes.
Learning Transferable Negative Prompts for Out-of-Distribution Detection
Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression
In this way, most of the representative information in the network can be retained in each cluster.
Fast Subspace Clustering Based on the Kronecker Product
Therefore, the efficiency and scalability of traditional spectral clustering methods can not be guaranteed for large scale datasets.
Deep Character-Level Click-Through Rate Prediction for Sponsored Search
Finally, by combining the predictions of the deep models introduced in this study with the prediction of the model in production of the same commercial search engine, we significantly improve the accuracy and the calibration of the click-through rate prediction of the production system.
On the Sampling Strategy for Evaluation of Spectral-spatial Methods in Hyperspectral Image Classification
Spectral-spatial processing has been increasingly explored in remote sensing hyperspectral image classification.
Online Sketching Hashing
Recently, hashing based approximate nearest neighbor (ANN) search has attracted much attention.
A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks
Our method accelerates the network in one-step pruning-recovery manner with a novel optimization objective function, which achieves higher accuracy with much less cost compared with existing pruning methods.
Unified Multifaceted Feature Learning for Person Re-Identification
The loss structures the augmented images resulted by the two types of image erasing in a two-level hierarchy and enforces multifaceted attention to different parts.
Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection
Video anomaly detection is of critical practical importance to a variety of real applications because it allows human attention to be focused on events that are likely to be of interest, in spite of an otherwise overwhelming volume of video.
Addressing Class-Imbalance Problem in Personalized Ranking
Pairwise ranking models have been widely used to address recommendation problems.
Select, Extract and Generate: Neural Keyphrase Generation with Layer-wise Coverage Attention
Natural language processing techniques have demonstrated promising results in keyphrase generation.
Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning
Though many ZSL methods rely on a direct mapping between the visual and the semantic space, the calibration deviation and hubness problem limit the generalization capability to unseen classes.
Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss
The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches.
HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects
To address this problem, we introduce a lightweight but effective Global Matching Component (GMC) to grab global matching features.
Occluded Person Re-Identification With Single-Scale Global Representations
However, real-world ReID applications typically have highly diverse occlusions and involve a hybrid of occluded and non-occluded pedestrians.
Towards Fully Decoupled End-to-End Person Search
This enables independent learning for different objectives thus fully decoupled the model for persons earch.
Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook
Point cloud classification is the basis of point cloud analysis, and many deep learning-based methods have been widely used in this task.
