Search Results for author:
Found 45 papers, 13 papers with code
Guided Semantic Flow
Establishing dense semantic correspondences requires dealing with large geometric variations caused by the unconstrained setting of images.
TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning
Transfer learning paradigm has driven substantial advancements in various vision tasks.
Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models
In this work, we dive deep into the impact of additive noise in pre-training deep networks.
Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detection
Continual Test Time Adaptation (CTTA) has emerged as a critical approach for bridging the domain gap between the controlled training environments and the real-world scenarios, enhancing model adaptability and robustness.
UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching
Unlike other vision tasks where Transformer-based approaches are becoming increasingly common, stereo depth estimation is still dominated by convolution-based approaches.
iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation
To secure flexible learning ability on input instances in various downstream tasks, we introduce an input-Conditioned Network (iCoN) in the dynamic adapter that enables instance-level feature transformation.
MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling
In stereo matching, CNNs have traditionally served as the predominant architectures.
SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction
Masked Image Modeling (MIM) techniques have redefined the landscape of computer vision, enabling pre-trained models to achieve exceptional performance across a broad spectrum of tasks.
CLDA: Collaborative Learning for Enhanced Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) endeavors to bridge the gap between a model trained on a labeled source domain and its deployment in an unlabeled target domain.
Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge
In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount.
Fine-grained Background Representation for Weakly Supervised Semantic Segmentation
Generating reliable pseudo masks from image-level labels is challenging in the weakly supervised semantic segmentation (WSSS) task due to the lack of spatial information.
Ranked #3 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 train
(using extra training data)
Emerging Property of Masked Token for Effective Pre-training
Initially, we delve into an exploration of the inherent properties that a masked token ought to possess.
Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training
In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Modeling (MIM) approaches by prioritizing token salience.
Environment Agnostic Representation for Visual Reinforcement Learning
Generalization capability of vision-based deep reinforcement learning (RL) is indispensable to deal with dynamic environment changes that exist in visual observations.
Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning
Recent vision-based reinforcement learning (RL) methods have found extracting high-level features from raw pixels with self-supervised learning to be effective in learning policies.
Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters.
Contour-Aware Equipotential Learning for Semantic Segmentation
This novel module transfers the predicted/ground-truth semantic labels to a self-defined potential domain to learn and infer decision boundaries along customized directions.
Sequential Cross Attention Based Multi-task Learning
The cross-task attention module (CTAM) is first applied to facilitate the exchange of relevant information between the multiple task features of the same scale.
PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
To mitigate this issue, we propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix, to provide a robust initialization of stereo models for online stereo adaptation.
Pin the Memory: Learning to Generalize Semantic Segmentation
The rise of deep neural networks has led to several breakthroughs for semantic segmentation.
KNN Local Attention for Image Restoration
In this way, the pair-wise operation establishes non-local connectivity while maintaining the desired properties of the local attention, i. e., inductive bias of locality and linear complexity to input resolution.
DIML/CVL RGB-D Dataset: 2M RGB-D Images of Natural Indoor and Outdoor Scenes
This manual is intended to provide a detailed description of the DIML/CVL RGB-D dataset.
Self-Supervised Structured Representations for Deep Reinforcement Learning
The proposed method imposes similarity constraints on the three latent volumes; warped query representations by estimated flows, predicted target representations from the transition model, and target representations of future state.
Weakly-Supervised Learning of Disentangled and Interpretable Skills for Hierarchical Reinforcement Learning
Given the latent representations as skills, a skill-based policy network is trained to generate similar trajectories to the learned decoder of the trajectory VAE.
Self-balanced Learning For Domain Generalization
Domain generalization aims to learn a prediction model on multi-domain source data such that the model can generalize to a target domain with unknown statistics.
Mining Better Samples for Contrastive Learning of Temporal Correspondence
We present a novel framework for contrastive learning of pixel-level representation using only unlabeled video.
On the confidence of stereo matching in a deep-learning era: a quantitative evaluation
Stereo matching is one of the most popular techniques to estimate dense depth maps by finding the disparity between matching pixels on two, synchronized and rectified images.
Pseudo Label-Guided Multi Task Learning for Scene Understanding
More importantly, the pseudo depth labels serve to impose a cross-view consistency on the estimated monocular depth and segmentation maps of two views.
Adaptive confidence thresholding for monocular depth estimation
To cope with the prediction error of the confidence map itself, we also leverage the threshold network that learns the threshold dynamically conditioned on the pseudo depth maps.
Joint Learning of Semantic Alignment and Object Landmark Detection
Based on the key insight that the two tasks can mutually provide supervisions to each other, our networks accomplish this through a joint loss function that alternatively imposes a consistency constraint between the two tasks, thereby boosting the performance and addressing the lack of training data in a principled manner.
A Large RGB-D Dataset for Semi-supervised Monocular Depth Estimation
In this paper, we present a simple yet effective approach for monocular depth estimation using stereo image pairs.
Semantic Attribute Matching Networks
SAM-Net accomplishes this through an iterative process of establishing reliable correspondences by reducing the attribute discrepancy between the images and synthesizing attribute transferred images using the learned correspondences.
Recurrent Transformer Networks for Semantic Correspondence
Our networks accomplish this through an iterative process of estimating spatial transformations between the input images and using these transformations to generate aligned convolutional activations.
PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
To the best of our knowledge, it is the first work that attempts to estimate dense affine transformation fields in a coarse-to-fine manner within deep networks.
DCTM: Discrete-Continuous Transformation Matching for Semantic Flow
In this way, our approach draws solutions from the continuous space of affine transformations in a manner that can be computed efficiently through constant-time edge-aware filtering and a proposed affine-varying CNN-based descriptor.
Fast 2-D Complex Gabor Filter with Kernel Decomposition
To obtain the 2-D complex Gabor filter bank output, existing methods are repeatedly applied with respect to multiple orientations and frequencies.
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.
Deeply Aggregated Alternating Minimization for Image Restoration
The proposed framework enables the convolutional neural networks (CNNs) to operate as a prior or regularizer in the AM algorithm.
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.
Deep Self-Convolutional Activations Descriptor for Dense Cross-Modal Correspondence
We present a novel descriptor, called deep self-convolutional activations (DeSCA), designed for establishing dense correspondences between images taken under different imaging modalities, such as different spectral ranges or lighting conditions.
SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs
However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint.
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.
Cross-Scale Cost Aggregation for Stereo Matching
We firstly reformulate cost aggregation from a unified optimization perspective and show that different cost aggregation methods essentially differ in the choices of similarity kernels.
Patch Match Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation
Recent studies on fast cost volume filtering based on efficient edge-aware filters have provided a fast alternative to solve discrete labeling problems, with the complexity independent of the support window size.
