Search Results for author:
Found 38 papers, 13 papers with code
Cerberus: Attribute-based person re-identification using semantic IDs
Our framework performs individual comparisons of local and global person representations between query and gallery images for attribute-based reID.
Disentangled Representations for Short-Term and Long-Term Person Re-Identification
To tackle this problem, we propose to factorize person images into identity-related and unrelated features.
Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients
Based on this, we derive an upper bound of quantization error for the large gradients in terms of the quantization interval, and obtain an optimal condition for the interval minimizing the quantization error for large gradients.
FYI: Flip Your Images for Dataset Distillation
Dataset distillation synthesizes a small set of images from a large-scale real dataset such that synthetic and real images share similar behavioral properties (e. g, distributions of gradients or features) during a training process.
Transition Rate Scheduling for Quantization-Aware Training
It is thus difficult to control the degree of changes for quantized weights by scheduling the LR manually.
Instance-Aware Group Quantization for Vision Transformers
In particular, the distribution of activations for each channel vary drastically according to input instances, making PTQ methods for CNNs inappropriate for ViTs.
AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search
To address this issue, we propose AZ-NAS, a novel approach that leverages the ensemble of various zero-cost proxies to enhance the correlation between a predicted ranking of networks and the ground truth substantially in terms of the performance.
RankMixup: Ranking-Based Mixup Training for Network Calibration
In this paper, we present RankMixup, a novel mixup-based framework alleviating the problem of the mixture of labels for network calibration.
Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification
To address the camera bias problem, we also introduce a camera-diversity (CD) loss encouraging person images of the same pseudo label, but captured across various cameras, to involve more for discriminative feature learning, providing person representations robust to inter-camera variations.
Domain Adaptation
Domain Adaptive Person Re-Identification
+4
ACLS: Adaptive and Conditional Label Smoothing for Network Calibration
We present in this paper an in-depth analysis of existing regularization-based methods, providing a better understanding on how they affect to network calibration.
ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation
Based on this, we then introduce an adaptive logit regularizer (ALI) that enables our model to better learn new categories, while retaining knowledge for previous ones.
Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation
We introduce a CISS framework that alleviates the forgetting problem and facilitates learning novel classes effectively.
Class-Incremental Semantic Segmentation
Knowledge Distillation
Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation
We present a novel unsupervised domain adaptation method for semantic segmentation that generalizes a model trained with source images and corresponding ground-truth labels to a target domain.
OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
To this end, we introduce a novel normalization layer, dubbed ProtoNorm, that calibrates features from pedestrian proposals, while considering a long-tail distribution of person IDs, enabling L2 normalized person representations to be discriminative.
Video-based Person Re-identification with Spatial and Temporal Memory Networks
Spatial and temporal distractors in person videos, such as background clutter and partial occlusions over frames, respectively, make this task much more challenging than image-based person reID.
Ranked #8 on
Person Re-Identification
on MARS
Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences
We address the problem of visible-infrared person re-identification (VI-reID), that is, retrieving a set of person images, captured by visible or infrared cameras, in a cross-modal setting.
Distance-aware Quantization
This alleviates the gradient mismatch, but causes a quantizer gap problem.
Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation
To this end, we leverage visual and semantic encoders to learn a joint embedding space, where the semantic encoder transforms semantic features to semantic prototypes that act as centers for visual features of corresponding classes.
HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection
To this end, we propose a new convolutional neural network (CNN) architecture, dubbed HVPR, that integrates both features into a single 3D representation effectively and efficiently.
Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
We address the problem of weakly-supervised semantic segmentation (WSSS) using bounding box annotations.
Network Quantization with Element-wise Gradient Scaling
Network quantization aims at reducing bit-widths of weights and/or activations, particularly important for implementing deep neural networks with limited hardware resources.
Learning with Privileged Information for Efficient Image Super-Resolution
The student and the decoder in the teacher, having the same network architecture as FSRCNN, try to reconstruct HR images.
Learning Memory-guided Normality for Anomaly Detection
To address this problem, we present an unsupervised learning approach to anomaly detection that considers the diversity of normal patterns explicitly, while lessening the representation capacity of CNNs.
Learning Semantic Correspondence Exploiting an Object-level Prior
We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category.
Relation Network for Person Re-identification
To address this issue, we propose a new relation network for person reID that considers relations between individual body parts and the rest of them.
Ranked #3 on
Person Re-Identification
on CUHK03-C
Learning Disentangled Representation for Robust Person Re-identification
We address the problem of person re-identification (reID), that is, retrieving person images from a large dataset, given a query image of the person of interest.
Ranked #46 on
Person Re-Identification
on DukeMTMC-reID
Deformable Kernel Networks for Joint Image Filtering
Previous methods based on convolutional neural networks (CNNs) combine nonlinear activations of spatially-invariant kernels to estimate structural details and regress the filtering result.
Temporally Consistent Depth Prediction with Flow-Guided Memory Units
To address this problem, we propose to memorize temporal consistency in the video sequence, and leverage it for the task of depth prediction.
SFNet: Learning Object-aware Semantic Correspondence
We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category.
Deformable kernel networks for guided depth map upsampling
We address the problem of upsampling a low-resolution (LR) depth map using a registered high-resolution (HR) color image of the same scene.
SCNet: Learning Semantic Correspondence
This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category.
Proposal Flow: Semantic Correspondences from Object Proposals
Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout.
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
The sampling patterns of local structure and the self-similarity measure are jointly learned within the proposed network in an end-to-end and multi-scale manner.
DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation
In this paper, we propose a novel dense descriptor, called dense adaptive self-correlation (DASC), to estimate multi-modal and multi-spectral dense correspondences.
Efficient Splitting-based Method for Global Image Smoothing
In this paper, we introduce a highly efficient splitting-based method for global EPS that minimizes the objective function of ${l_2}$ data and prior terms (possibly non-smooth and non-convex) in linear time.
Proposal Flow
Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout.~Semantic flow methods are designed to handle images depicting different instances of the same object or scene category.
Robust Image Filtering Using Joint Static and Dynamic Guidance
Regularizing images under a guidance signal has been used in various tasks in computer vision and computational photography, particularly for noise reduction and joint upsampling.
DASC: Dense Adaptive Self-Correlation Descriptor for Multi-Modal and Multi-Spectral Correspondence
To further improve the matching quality and runtime efficiency, we propose a patch-wise receptive field pooling, in which a sampling pattern is optimized with a discriminative learning.
