Search Results for author:
Found 66 papers, 34 papers with code
An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
The Segment Anything Model (SAM) has demonstrated exceptional performance and versatility, making it a promising tool for various related tasks.
Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning
Based on this observation, we propose a new learning strategy named False Negative Aware Contrastive (FNAC) to mitigate the problem of misleading the training with such false negative samples.
Transmission-Guided Bayesian Generative Model for Smoke Segmentation
To effectively model the two types of uncertainty, we introduce a Bayesian generative model to simultaneously estimate the posterior distribution of model parameters and its predictions.
PointCaM: Cut-and-Mix for Open-Set Point Cloud Analysis
Specifically, we use the Unknown-Point Simulator to simulate unknown data in the training stage by manipulating the geometric context of partial known data.
Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion
Unsupervised point cloud completion aims to infer the whole geometry of a partial object observation without requiring partial-complete correspondence.
The Devil in Linear Transformer
In this paper, we examine existing kernel-based linear transformers and identify two key issues that lead to such performance gaps: 1) unbounded gradients in the attention computation adversely impact the convergence of linear transformer models; 2) attention dilution which trivially distributes attention scores over long sequences while neglecting neighbouring structures.
Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning
Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process.
Generalised Co-Salient Object Detection
To evaluate the performance of CoSOD models under the GCoSOD setting, we propose two new testing datasets, namely CoCA-Common and CoCA-Zero, where a common salient object is partially present in the former and completely absent in the latter.
Vicinity Vision Transformer
Based on this observation, we present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity.
Towards Deeper Understanding of Camouflaged Object Detection
With the above understanding about camouflaged objects, we present the first triple-task learning framework to simultaneously localize, segment, and rank camouflaged objects, indicating the conspicuousness level of camouflage.
An Energy-Based Prior for Generative Saliency
With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction.
Towards Open-Set Object Detection and Discovery
This new task aims to extend the ability of open-set object detectors to further discover the categories of unknown objects based on their visual appearance without human effort.
Semi-supervised Salient Object Detection with Effective Confidence Estimation
The success of existing salient object detection models relies on a large pixel-wise labeled training dataset.
Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction
In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for salient object detection.
GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation
To bridge their gap, a Class Activation Map (CAM) is usually generated to provide pixel level pseudo labels.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Learning To Segment Dominant Object Motion From Watching Videos
Existing deep learning based unsupervised video object segmentation methods still rely on ground-truth segmentation masks to train.
PU-Transformer: Point Cloud Upsampling Transformer
Given the rapid development of 3D scanners, point clouds are becoming popular in AI-driven machines.
Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
Uncertainty estimation has been extensively studied in recent literature, which can usually be classified as aleatoric uncertainty and epistemic uncertainty.
Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation
To solve this, most existing approaches follow a multi-training pipeline to refine CAMs for better pseudo-labels, which includes: 1) re-training the classification model to generate CAMs; 2) post-processing CAMs to obtain pseudo labels; and 3) training a semantic segmentation model with the obtained pseudo labels.
Ranked #12 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Dense Uncertainty Estimation
Deep neural networks can be roughly divided into deterministic neural networks and stochastic neural networks. The former is usually trained to achieve a mapping from input space to output space via maximum likelihood estimation for the weights, which leads to deterministic predictions during testing.
RGB-D Saliency Detection via Cascaded Mutual Information Minimization
In this paper, we introduce a novel multi-stage cascaded learning framework via mutual information minimization to "explicitly" model the multi-modal information between RGB image and depth data.
PnP-3D: A Plug-and-Play for 3D Point Clouds
With the help of the deep learning paradigm, many point cloud networks have been invented for visual analysis.
Energy-Based Generative Cooperative Saliency Prediction
In this paper, to model the uncertainty of visual saliency, we study the saliency prediction problem from the perspective of generative models by learning a conditional probability distribution over the saliency map given an input image, and treating the saliency prediction as a sampling process from the learned distribution.
Confidence-Aware Learning for Camouflaged Object Detection
Then, we concatenate it with the input image and feed it to the confidence estimation network to produce an one channel confidence map. We generate dynamic supervision for the confidence estimation network, representing the agreement of camouflage prediction with the ground truth camouflage map.
Generative Transformer for Accurate and Reliable Salient Object Detection
For the former, we apply transformer to a deterministic model, and explain that the effective structure modeling and global context modeling abilities lead to its superior performance compared with the CNN based frameworks.
Learning structure-aware semantic segmentation with image-level supervision
Within this pipeline, the class activation map (CAM) is obtained and further processed to serve as a pseudo label to train the semantic segmentation model in a fully-supervised manner.
Weakly Supervised Video Salient Object Detection
Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain.
Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
Given the prominence of current 3D sensors, a fine-grained analysis on the basic point cloud data is worthy of further investigation.
Ranked #6 on
Semantic Segmentation
on Semantic3D
Simultaneously Localize, Segment and Rank the Camouflaged Objects
With the above understanding about camouflaged objects, we present the first ranking based COD network (Rank-Net) to simultaneously localize, segment and rank camouflaged objects.
Recursive Training for Zero-Shot Semantic Segmentation
We propose a recursive training scheme to supervise the retraining of a semantic segmentation model for a zero-shot setting using a pseudo-feature representation.
Robust normalizing flows using Bernstein-type polynomials
Modeling real-world distributions can often be challenging due to sample data that are subjected to perturbations, e. g., instrumentation errors, or added random noise.
Uncertainty-Aware Deep Calibrated Salient Object Detection
Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy.
3D Guided Weakly Supervised Semantic Segmentation
In this paper, we propose a weakly supervised 2D semantic segmentation model by incorporating sparse bounding box labels with available 3D information, which is much easier to obtain with advanced sensors.
2D Semantic Segmentation
Weakly supervised Semantic Segmentation
+1
Rethinking conditional GAN training: An approach using geometrically structured latent manifolds
Conditional GANs (cGAN), in their rudimentary form, suffer from critical drawbacks such as the lack of diversity in generated outputs and distortion between the latent and output manifolds.
Conditional Generative Modeling via Learning the Latent Space
Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings.
Attention Guided Semantic Relationship Parsing for Visual Question Answering
Humans explain inter-object relationships with semantic labels that demonstrate a high-level understanding required to perform complex Vision-Language tasks such as Visual Question Answering (VQA).
Uncertainty Inspired RGB-D Saliency Detection
Our framework includes two main models: 1) a generator model, which maps the input image and latent variable to stochastic saliency prediction, and 2) an inference model, which gradually updates the latent variable by sampling it from the true or approximate posterior distribution.
Ranked #1 on
RGB Salient Object Detection
on DUTS-test
(MAE metric)
RGB-D Salient Object Detection
RGB Salient Object Detection
+1
Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
The proposed model consists of two sub-models parameterized by neural networks: (1) a saliency predictor that maps input images to clean saliency maps, and (2) a noise generator, which is a latent variable model that produces noises from Gaussian latent vectors.
Dense-Resolution Network for Point Cloud Classification and Segmentation
Our DRNet is designed to learn local point features from the point cloud in different resolutions.
Ranked #18 on
3D Part Segmentation
on ShapeNet-Part
Attention Based Real Image Restoration
Furthermore, the evaluation in terms of quantitative metrics and visual quality for four restoration tasks i. e. Denoising, Super-resolution, Raindrop Removal, and JPEG Compression on 11 real degraded datasets against more than 30 state-of-the-art algorithms demonstrate the superiority of our R$^2$Net.
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process.
Ranked #4 on
RGB-D Salient Object Detection
on LFSD
A Systematic Evaluation: Fine-Grained CNN vs. Traditional CNN Classifiers
In this work, we investigate the performance of the landmark general CNN classifiers, which presented top-notch results on large scale classification datasets, on the fine-grained datasets, and compare it against state-of-the-art fine-grained classifiers.
Reducing the Sim-to-Real Gap for Event Cameras
We present strategies for improving training data for event based CNNs that result in 20-40% boost in performance of existing state-of-the-art (SOTA) video reconstruction networks retrained with our method, and up to 15% for optic flow networks.
Any-Shot Object Detection
Any-shot detection offers unique challenges compared to conventional novel object detection such as, a high imbalance between unseen, few-shot and seen object classes, susceptibility to forget base-training while learning novel classes and distinguishing novel classes from the background.
Accuracy vs. Complexity: A Trade-off in Visual Question Answering Models
However, modelling the visual and semantic features in a high dimensional (joint embedding) space is computationally expensive, and more complex models often result in trivial improvements in the VQA accuracy.
Spectral-GANs for High-Resolution 3D Point-cloud Generation
Point-clouds are a popular choice for vision and graphics tasks due to their accurate shape description and direct acquisition from range-scanners.
Representation Learning on Unit Ball with 3D Roto-Translational Equivariance
In this work, we propose a novel `\emph{volumetric convolution}' operation that can effectively model and convolve arbitrary functions in $\mathbb{B}^3$.
Geometric Back-projection Network for Point Cloud Classification
As the basic task of point cloud analysis, classification is fundamental but always challenging.
Ranked #22 on
3D Point Cloud Classification
on ModelNet40
Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes
Existing networks directly learn feature representations on 3D point clouds for shape analysis.
Question-Agnostic Attention for Visual Question Answering
Visual Question Answering (VQA) models employ attention mechanisms to discover image locations that are most relevant for answering a specific question.
Densely Residual Laplacian Super-Resolution
Super-Resolution convolutional neural networks have recently demonstrated high-quality restoration for single images.
Ranked #1 on
Image Super-Resolution
on BSD100 - 8x upscaling
Unsupervised Primitive Discovery for Improved 3D Generative Modeling
Using the primitive parts for shapes as attributes, a parameterized 3D representation is modeled in the first stage.
CED: Color Event Camera Dataset
Event cameras are novel, bio-inspired visual sensors, whose pixels output asynchronous and independent timestamped spikes at local intensity changes, called 'events'.
Real Image Denoising with Feature Attention
Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, their performance is limited on real-noisy photographs and requires multiple stage network modeling.
Ranked #1 on
Color Image Denoising
on BSD68 sigma15
A Deep Journey into Super-resolution: A survey
Deep convolutional networks based super-resolution is a fast-growing field with numerous practical applications.
Volumetric Convolution: Automatic Representation Learning in Unit Ball
Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks.
Asynchronous Spatial Image Convolutions for Event Cameras
In this paper, we propose a method to compute the convolution of a linear spatial kernel with the output of an event camera.
From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts
To evaluate our model, we propose a new split for VQA, separating Unknown visual and semantic concepts from the training set.
Polarity Loss for Zero-shot Object Detection
This setting gives rise to the need for correct alignment between visual and semantic concepts, so that the unseen objects can be identified using only their semantic attributes.
Ranked #4 on
Zero-Shot Object Detection
on PASCAL VOC'07
Continuous-time Intensity Estimation Using Event Cameras
Event cameras provide asynchronous, data-driven measurements of local temporal contrast over a large dynamic range with extremely high temporal resolution.
Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation
Our model simultaneously learns to match the data, reconstruction loss and the latent distributions of real and fake images to improve the quality of generated samples.
Deep Texture and Structure Aware Filtering Network for Image Smoothing
Image smoothing is a fundamental task in computer vision, that aims to retain salient structures and remove insignificant textures.
Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features
Here we propose a novel deep CNN architecture for RGB-D salient object detection that exploits high-level, mid-level, and low level features.
Local Background Enclosure for RGB-D Salient Object Detection
Recent work in salient object detection has considered the incorporation of depth cues from RGB-D images.
Ranked #24 on
RGB-D Salient Object Detection
on NJU2K
Perceptually Consistent Color-to-Gray Image Conversion
In this paper, we propose a color to grayscale image conversion algorithm (C2G) that aims to preserve the perceptual properties of the color image as much as possible.
Learning Structured Hough Voting for Joint Object Detection and Occlusion Reasoning
We propose a structured Hough voting method for detecting objects with heavy occlusion in indoor environments.
