Search Results for author:
Found 186 papers, 117 papers with code
Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
Continual learning in computer vision faces the critical challenge of catastrophic forgetting, where models struggle to retain prior knowledge while adapting to new tasks.
AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction
Novel view synthesis (NVS) is a cornerstone for image-to-3d creation.
InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration
Diffusion priors have been used for blind face restoration (BFR) by fine-tuning diffusion models (DMs) on restoration datasets to recover low-quality images.
One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
Drawing inspiration from the inherent context consistency, we propose a novel training-free method for consistent text-to-image (T2I) generation, termed "One-Prompt-One-Story" (1Prompt1Story).
RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark
Our approach can effectively improve the performance of existing state-of-the-art weakly supervised methods and even surpasses fully supervised models on existing optical benchmarks (i. e., DOTA-v1. 0 dataset).
Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection
While witnessed with rapid development, remote sensing object detection remains challenging for detecting high aspect ratio objects.
Ranked #1 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection
To address these, we establish a benchmark dataset and propose a unified model, SM3Det (Single Model for Multi-Modal datasets and Multi-Task object Detection).
TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction
We present TAR3D, a novel framework that consists of a 3D-aware Vector Quantized-Variational AutoEncoder (VQ-VAE) and a Generative Pre-trained Transformer (GPT) to generate high-quality 3D assets.
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation
Open-vocabulary image segmentation has been advanced through the synergy between mask generators and vision-language models like Contrastive Language-Image Pre-training (CLIP).
Ranked #1 on
Open Vocabulary Semantic Segmentation
on ADE20K-150
ATPrompt: Textual Prompt Learning with Embedded Attributes
Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text prompt inputs, aiming to align image and text (category) spaces for downstream tasks.
DenseVLM: A Retrieval and Decoupled Alignment Framework for Open-Vocabulary Dense Prediction
Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot recognition capability, but still underperform in dense prediction tasks.
Multi-Token Enhancing for Vision Representation Learning
Ensemble learning has also succeeded in enhancing the performance and robustness of the vision models.
Towards RAW Object Detection in Diverse Conditions
We find that sRGB pre-training constrains the potential of RAW object detection due to the domain gap between sRGB and RAW, prompting us to directly pre-train on the RAW domain.
Ranked #1 on
Object Detection
on AODRaw
PR-MIM: Delving Deeper into Partial Reconstruction in Masked Image Modeling
One cost-saving strategy makes the decoder reconstruct only a subset of masked tokens and throw the others, and we refer to this method as partial reconstruction.
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
In this paper, we define semantic binding as the task of associating a given object with its attribute, termed attribute binding, or linking it to other related sub-objects, referred to as object binding.
Multimodality Helps Few-Shot 3D Point Cloud Semantic Segmentation
Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples.
Few-shot 3D Point Cloud Semantic Segmentation
Point Cloud Segmentation
+1
ClearSR: Latent Low-Resolution Image Embeddings Help Diffusion-Based Real-World Super Resolution Models See Clearer
We show that the proper use of latent LR embeddings can produce higher-quality control signals, which enables the super-resolution results to be more consistent with the LR image and leads to clearer visual results.
OPUS: Occupancy Prediction Using a Sparse Set
Mainstream occupancy prediction works first discretize the 3D environment into voxels, then perform classification on such dense grids.
From Words to Worth: Newborn Article Impact Prediction with LLM
As the academic landscape expands, the challenge of efficiently identifying impactful newly published articles grows increasingly vital.
Towards Stable 3D Object Detection
In autonomous driving, the temporal stability of 3D object detection greatly impacts the driving safety.
Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
Our Cascade-CLIP is flexible and can be easily applied to existing zero-shot semantic segmentation methods.
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
This module converts the generated sequence of images into videos with smooth transitions and consistent subjects that are significantly more stable than the modules based on latent spaces only, especially in the context of long video generation.
Generative Multi-modal Models are Good Class-Incremental Learners
In class-incremental learning (CIL) scenarios, the phenomenon of catastrophic forgetting caused by the classifier's bias towards the current task has long posed a significant challenge.
LSKNet: A Foundation Lightweight Backbone for Remote Sensing
While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios.
Ranked #1 on
Semantic Segmentation
on ISPRS Vaihingen
Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Specifically, our TES leverages the property that CLIP can generate aligned vision-language features, converting visual embeddings into tokens of the CLIP's text encoder to generate pseudo text embeddings.
SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection
To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created.
Ranked #2 on
2D Object Detection
on SARDet-100K
(using extra training data)
Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning
For this reason, this paper explores a Source-Free CDFSL (SF-CDFSL) problem, in which CDFSL is addressed through the use of existing pretrained models instead of training a model with source data, avoiding accessing source data.
Sora Generates Videos with Stunning Geometrical Consistency
We employ a method that transforms the generated videos into 3D models, leveraging the premise that the accuracy of 3D reconstruction is heavily contingent on the video quality.
A Literature Review of Literature Reviews in Pattern Analysis and Machine Intelligence
This paper presents a thorough analysis of these literature reviews within the PAMI field, and tries to address three core research questions: (1) What are the prevalent structural and statistical characteristics of PAMI literature reviews?
Generative Multi-modal Models are Good Class Incremental Learners
In class incremental learning (CIL) scenarios the phenomenon of catastrophic forgetting caused by the classifier's bias towards the current task has long posed a significant challenge.
Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning
Considering this challenge, we propose a novel framework of fine-grained knowledge selection and restoration.
Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
This insight motivates us to omit encoder computation at certain adjacent time-steps and reuse encoder features of previous time-steps as input to the decoder in multiple time-steps.
MaTe3D: Mask-guided Text-based 3D-aware Portrait Editing
This enhances masked-based editing in local areas; second, we present a novel distillation strategy: Conditional Distillation on Geometry and Texture (CDGT).
A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation
Effectively modeling discriminative spatio-temporal information is essential for segmenting activities in long action sequences.
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
Recent advances in text-to-image generation have made remarkable progress in synthesizing realistic human photos conditioned on given text prompts.
Ranked #6 on
Diffusion Personalization Tuning Free
on AgeDB
Diffusion Personalization Tuning Free
Text-to-Image Generation
TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes
Particularly, a cross-modal graph is constructed to align the object points accurately and noun phrases decoupled from the 3D mesh and textual description.
Class Incremental Learning with Pre-trained Vision-Language Models
We also propose a method for parameter retention in the adapter layers that uses a measure of parameter importance to better maintain stability and plasticity during incremental learning.
Zone Evaluation: Revealing Spatial Bias in Object Detection
A fundamental limitation of object detectors is that they suffer from "spatial bias", and in particular perform less satisfactorily when detecting objects near image borders.
Low-Resolution Self-Attention for Semantic Segmentation
Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction.
Enhancing Representations through Heterogeneous Self-Supervised Learning
Thus, we propose Heterogeneous Self-Supervised Learning (HSSL), which enforces a base model to learn from an auxiliary head whose architecture is heterogeneous from the base model.
DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks.
Ranked #1 on
RGB-D Salient Object Detection
on DES
Masked Autoencoders are Efficient Class Incremental Learners
Moreover, MAEs can reliably reconstruct original input images from randomly selected patches, which we use to store exemplars from past tasks more efficiently for CIL.
YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection
We aim at providing the object detection community with an efficient and performant object detector, termed YOLO-MS.
Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model
However, these methods are impeded by several critical limitations: a) the explicit calibration process is both labor- and time-intensive, b) challenge exists in transferring denoisers across different camera models, and c) the disparity between synthetic and real noise is exacerbated by digital gain.
Ranked #1 on
Image Denoising
on SID SonyA7S2 x300
Revisiting Computer-Aided Tuberculosis Diagnosis
This dataset enables the training of sophisticated detectors for high-quality CTD.
CrossKD: Cross-Head Knowledge Distillation for Object Detection
Moreover, as mimicking the teacher's predictions is the target of KD, CrossKD offers more task-oriented information in contrast with feature imitation.
Referring Camouflaged Object Detection
We consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects.
CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
Motivated by these, we aim to improve the use efficiency of unlabeled data by designing two novel label propagation strategies.
Delving Deeper into Data Scaling in Masked Image Modeling
The study reveals that: 1) MIM can be viewed as an effective method to improve the model capacity when the scale of the training data is relatively small; 2) Strong reconstruction targets can endow the models with increased capacities on downstream tasks; 3) MIM pre-training is data-agnostic under most scenarios, which means that the strategy of sampling pre-training data is non-critical.
Multi-Space Neural Radiance Fields
Existing Neural Radiance Fields (NeRF) methods suffer from the existence of reflective objects, often resulting in blurry or distorted rendering.
RGB-D Indiscernible Object Counting in Underwater Scenes
We further advance the frontier of this field by systematically studying a new challenge named indiscernible object counting (IOC), the goal of which is to count objects that are blended with respect to their surroundings.
Advances in Deep Concealed Scene Understanding
Concealed scene understanding (CSU) is a hot computer vision topic aiming to perceive objects exhibiting camouflage.
AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
It is based on two essential designs.
Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections
To remedy this issue, we present a novel surface reconstruction framework, NeuS-HSR, based on implicit neural rendering.
SAM Struggles in Concealed Scenes -- Empirical Study on "Segment Anything"
Segmenting anything is a ground-breaking step toward artificial general intelligence, and the Segment Anything Model (SAM) greatly fosters the foundation models for computer vision.
StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing
A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images. They either finetune the model, or invert the image in the latent space of the pretrained model.
Ranked #9 on
Text-based Image Editing
on PIE-Bench
MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
To solve this issue, we propose a Masked Diffusion Transformer (MDT) that introduces a mask latent modeling scheme to explicitly enhance the DPMs' ability to contextual relation learning among object semantic parts in an image.
Ranked #16 on
Image Generation
on ImageNet 256x256
SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution
Without any bells and whistles, we show that our SRFormer achieves a 33. 86dB PSNR score on the Urban100 dataset, which is 0. 46dB higher than that of SwinIR but uses fewer parameters and computations.
Large Selective Kernel Network for Remote Sensing Object Detection
To the best of our knowledge, this is the first time that large and selective kernel mechanisms have been explored in the field of remote sensing object detection.
Ranked #2 on
Oriented Object Detection
on DOTA 1.0
Co-Salient Object Detection with Co-Representation Purification
Such irrelevant information in the co-representation interferes with its locating of co-salient objects.
Traffic Scene Parsing through the TSP6K Dataset
To date, most existing datasets focus on autonomous driving scenes.
QR-CLIP: Introducing Explicit Open-World Knowledge for Location and Time Reasoning
Daily images may convey abstract meanings that require us to memorize and infer profound information from them.
CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition
Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition.
Towards Spatial Equilibrium Object Detection
In this paper, we study the spatial disequilibrium problem of modern object detectors and propose to quantify this ``spatial bias'' by measuring the detection performance over zones.
SLAN: Self-Locator Aided Network for Vision-Language Understanding
By aggregating vision-language information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance.
Endpoints Weight Fusion for Class Incremental Semantic Segmentation
In our method, the model containing old knowledge is fused with the model retaining new knowledge in a dynamic fusion manner, strengthening the memory of old classes in ever-changing distributions.
class-incremental learning
Class-Incremental Semantic Segmentation
+2
Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
EFCIL is of interest because it mitigates concerns about privacy and long-term storage of data, while at the same time alleviating the problem of catastrophic forgetting in incremental learning.
SLAN: Self-Locator Aided Network for Cross-Modal Understanding
By aggregating cross-modal information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance.
Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition
This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features.
Towards Sustainable Self-supervised Learning
In this work, we explore a sustainable SSL framework with two major challenges: i) learning a stronger new SSL model based on the existing pretrained SSL model, also called as "base" model, in a cost-friendly manner, ii) allowing the training of the new model to be compatible with various base models.
Ranked #1 on
Semantic Segmentation
on ImageNet-S
Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis
The goal of semantic image synthesis is to generate photo-realistic images from semantic label maps.
Long-Tailed Class Incremental Learning
However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of long-tailed distributions in the real world.
SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation
Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90. 6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it.
Ranked #1 on
Semantic Segmentation
on iSAID
Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes
Current efficient LiDAR-based detection frameworks are lacking in exploiting object relations, which naturally present in both spatial and temporal manners.
Contrastive Masked Autoencoders are Stronger Vision Learners
The momentum encoder, fed with the full images, enhances the feature discriminability via contrastive learning with its online counterpart.
Designing An Illumination-Aware Network for Deep Image Relighting
Lighting is a determining factor in photography that affects the style, expression of emotion, and even quality of images.
Class-Specific Semantic Reconstruction for Open Set Recognition
In this study, we propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of AE and prototype learning.
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combinations further.
Ranked #2 on
Instance Segmentation
on COCO 2017 val
(AP metric)
SERE: Exploring Feature Self-relation for Self-supervised Transformer
Specifically, instead of conducting self-supervised learning solely on feature embeddings from multiple views, we utilize the feature self-relations, i. e., spatial/channel self-relations, for self-supervised learning.
Ranked #2 on
Semantic Segmentation
on ImageNet-S
VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
Equipped with the VQ codebook as a facial detail dictionary and the parallel decoder design, the proposed VQFR can largely enhance the restored quality of facial details while keeping the fidelity to previous methods.
Localization Distillation for Object Detection
Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years.
Towards An End-to-End Framework for Flow-Guided Video Inpainting
Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories.
Ranked #2 on
Seeing Beyond the Visible
on KITTI360-EX
Interactive Style Transfer: All is Your Palette
Our IST method can serve as a brush, dip style from anywhere, and then paint to any region of the target content image.
Representation Compensation Networks for Continual Semantic Segmentation
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting.
Ranked #1 on
Domain 1-1
on Cityscapes
Class Incremental Learning
Continual Semantic Segmentation
+16
Visual Attention Network
In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings.
Ranked #1 on
Panoptic Segmentation
on COCO panoptic
Deeply Explain CNN via Hierarchical Decomposition
The proposed framework can generate a deep hierarchy of strongly associated supporting evidence for the network decision, which provides insight into the decision-making process.
FocusCut: Diving Into a Focus View in Interactive Segmentation
However, the global view makes the model lose focus from later clicks, and is not in line with user intentions.
Ranked #5 on
Interactive Segmentation
on SBD
Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching
Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model.
Knowledge Distillation
Weakly supervised Semantic Segmentation
+1
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition
Then, a Teacher-Assistant-Student (TAS) framework is further established to disentangle pixel distillation into the model compression stage and input compression stage, which significantly reduces the overall complexity of pixel distillation and the difficulty of distilling intermediate knowledge.
Attention Mechanisms in Computer Vision: A Survey
Humans can naturally and effectively find salient regions in complex scenes.
Personalized Image Semantic Segmentation
In this paper, we address the problem of personalized image segmentation.
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition
By realizing the importance of the positional information carried by 2D feature representations, unlike recent MLP-like models that encode the spatial information along the flattened spatial dimensions, Vision Permutator separately encodes the feature representations along the height and width dimensions with linear projections.
P2T: Pyramid Pooling Transformer for Scene Understanding
A popular solution to this problem is to use a single pooling operation to reduce the sequence length.
Ranked #7 on
RGB Salient Object Detection
on DUTS-TE
(max F-measure metric)
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization
To evaluate the quality of the class activation maps produced by LayerCAM, we apply them to weakly-supervised object localization and semantic segmentation.
Representative Batch Normalization With Feature Calibration
We propose to add a simple yet effective feature calibration scheme into the centering and scaling operations of BatchNorm, enhancing the instance-specific representations with the negligible computational cost.
On the Connection between Local Attention and Dynamic Depth-wise Convolution
Sparse connectivity: there is no connection across channels, and each position is connected to the positions within a small local window.
Large-scale Unsupervised Semantic Segmentation
In this work, we propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to help the research progress.
Ranked #1 on
Unsupervised Semantic Segmentation
on ImageNet-S-300
Unsupervised Scale-consistent Depth Learning from Video
We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time.
Salient Objects in Clutter
This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets.
Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
To well exploit the temporal information, we propose a Locally-temporal Feature Comparison (LFC) module, along with the Bi-directional Deformable ConvLSTM, to extract short-term and long-term motion cues in videos.
Low-Light Image and Video Enhancement Using Deep Learning: A Survey
Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination.
Localization Distillation for Dense Object Detection
Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of mimicking classification logit due to its inefficiency in distilling localization information and trivial improvement.
Concealed Object Detection
We present the first systematic study on concealed object detection (COD), which aims to identify objects that are "perfectly" embedded in their background.
Ranked #5 on
Camouflaged Object Segmentation
on CHAMELEON
Camouflaged Object Segmentation
Dichotomous Image Segmentation
+2
Global2Local: Efficient Structure Search for Video Action Segmentation
Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combination patterns further.
Ranked #16 on
Action Segmentation
on Breakfast
iNAS: Integral NAS for Device-Aware Salient Object Detection
Existing salient object detection (SOD) models usually focus on either backbone feature extractors or saliency heads, ignoring their relations.
MobileSal: Extremely Efficient RGB-D Salient Object Detection
Therefore, we propose an implicit depth restoration (IDR) technique to strengthen the mobile networks' feature representation capability for RGB-D SOD.
Centralized Information Interaction for Salient Object Detection
Our approach can cooperate with various existing U-shape-based salient object detection methods by substituting the connections between the bottom-up and top-down pathways.
ICNet: Intra-saliency Correlation Network for Co-Saliency Detection
Intra-saliency and inter-saliency cues have been extensively studied for co-saliency detection (Co-SOD).
Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images
Despite the remarkable advances in visual saliency analysis for natural scene images (NSIs), salient object detection (SOD) for optical remote sensing images (RSIs) still remains an open and challenging problem.
Delving Deep into Label Smoothing
Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets.
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
DOTS: Decoupling Operation and Topology in Differentiable Architecture Search
DARTS mainly focuses on the operation search and derives the cell topology from the operation weights.
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation
For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph.
Image-level Supervised Instance Segmentation
Multiple Instance Learning
+3
Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow
Recent generative methods formulate GZSL as a missing data problem, which mainly adopts GANs or VAEs to generate visual features for unseen classes.
Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels.
Geometric Style Transfer
Our contribution is to introduce a neural architecture that supports transfer of geometric style.
Semi-Supervised Learning with Meta-Gradient
In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning.
Re-thinking Co-Salient Object Detection
CoSOD is an emerging and rapidly growing extension of salient object detection (SOD), which aims to detect the co-occurring salient objects in a group of images.
Ranked #7 on
Co-Salient Object Detection
on CoCA
Interactive Knowledge Distillation
Knowledge distillation is a standard teacher-student learning framework to train a light-weight student network under the guidance of a well-trained large teacher network.
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation
Despite the capabilities of these approaches in capturing temporal dependencies, their predictions suffer from over-segmentation errors.
Ranked #6 on
Action Segmentation
on Assembly101
Dependency Aware Filter Pruning
Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference.
Gradient-Induced Co-Saliency Detection
Co-saliency detection (Co-SOD) aims to segment the common salient foreground in a group of relevant images.
Ranked #7 on
Co-Salient Object Detection
on CoSOD3k
Conditional Variational Image Deraining
In this paper, we propose a Conditional Variational Image Deraining (CVID) network for better deraining performance, leveraging the exclusive generative ability of Conditional Variational Auto-Encoder (CVAE) on providing diverse predictions for the rainy image.
Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton
To evaluate the performance of our proposed network on these tasks, we conduct exhaustive experiments on multiple representative datasets.
JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation
The chest CT scan test provides a valuable complementary tool to the RT-PCR test, and it can identify the patients in the early-stage with high sensitivity.
Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation
S-Conv is competent to infer the sampling offset of the convolution kernel guided by the 3D spatial information, helping the convolutional layer adjust the receptive field and adapt to geometric transformations.
Ranked #23 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing.
Ranked #32 on
Semantic Segmentation
on Cityscapes test
Highly Efficient Salient Object Detection with 100K Parameters
Salient object detection models often demand a considerable amount of computation cost to make precise prediction for each pixel, making them hardly applicable on low-power devices.
Deep Hough Transform for Semantic Line Detection
In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task.
Ranked #2 on
Line Detection
on NKL
Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle
Recent advances in convolutional neural networks(CNNs) usually come with the expense of excessive computational overhead and memory footprint.
Ordered or Orderless: A Revisit for Video based Person Re-Identification
Specifically, with a diagnostic analysis, we show that the recurrent structure may not be effective to learn temporal dependencies than what we expected and implicitly yields an orderless representation.
AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning
The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first sample intra-class patches (positives) from the dataset for batch construction and then mine in-batch negatives to form triplets.
Towards Disentangling Non-Robust and Robust Components in Performance Metric
Then, we show by experiments that DNNs under standard training rely heavily on optimizing the non-robust component in achieving decent performance.
Image Inpainting with Learnable Bidirectional Attention Maps
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness.
Ranked #2 on
Image Inpainting
on Paris StreetView
Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
To the best of our knowledge, this is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a long video sequence.
Ranked #4 on
Camera Pose Estimation
on KITTI Odometry Benchmark
An Evaluation of Feature Matchers for Fundamental Matrix Estimation
According to this, we propose three high-quality matching systems and a Coarse-to-Fine RANSAC estimator.
Robust Regression via Deep Negative Correlation Learning
Nonlinear regression has been extensively employed in many computer vision problems (e. g., crowd counting, age estimation, affective computing).
EGNet:Edge Guidance Network for Salient Object Detection
In the second step, we integrate the local edge information and global location information to obtain the salient edge features.
Scoot: A Perceptual Metric for Facial Sketches
In this paper, we design a perceptual metric, called Structure Co-Occurrence Texture (Scoot), which simultaneously considers the block-level spatial structure and co-occurrence texture statistics.
Image Formation Model Guided Deep Image Super-Resolution
We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution.
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
The use of RGB-D information for salient object detection has been extensively explored in recent years.
Ranked #4 on
RGB-D Salient Object Detection
on RGBD135
Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image
A simple but useful observation on our NAC is: as long as the noise is weak, it is feasible to learn a self-supervised network only with the corrupted image, approximating the optimal parameters of a supervised network learned with pairs of noisy and clean images.
Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric
Despite many previous works studying the reason behind such adversarial behavior, the relationship between the generalization performance and adversarial behavior of DNNs is still little understood.
LSANet: Feature Learning on Point Sets by Local Spatial Aware Layer
We design a novel Local Spatial Aware (LSA) layer, which can learn to generate Spatial Distribution Weights (SDWs) hierarchically based on the spatial relationship in local region for spatial independent operations, to establish the relationship between these operations and spatial distribution, thus capturing the local geometric structure sensitively. We further propose the LSANet, which is based on LSA layer, aggregating the spatial information with associated features in each layer of the network better in network design. The experiments show that our LSANet can achieve on par or better performance than the state-of-the-art methods when evaluating on the challenging benchmark datasets.
A Simple Pooling-Based Design for Real-Time Salient Object Detection
We further design a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway.
Ranked #1 on
RGB Salient Object Detection
on SOD
Res2Net: A New Multi-scale Backbone Architecture
We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e. g., CIFAR-100 and ImageNet.
Ranked #2 on
Image Classification
on GasHisSDB
DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs).
Simultaneous Subspace Clustering and Cluster Number Estimating based on Triplet Relationship
In this paper we propose a unified framework to simultaneously discover the number of clusters and group the data points into them using subspace clustering.
Salient Object Detection via High-to-Low Hierarchical Context Aggregation
In this paper, we observe that the contexts of a natural image can be well expressed by a high-to-low self-learning of side-output convolutional features.
Self-Erasing Network for Integral Object Attention
To test the quality of the generated attention maps, we employ the mined object regions as heuristic cues for learning semantic segmentation models.
Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation
We also combine our method with Mask R-CNN for instance segmentation, and demonstrated for the first time the ability of weakly supervised instance segmentation using only keyword annotations.
Ranked #6 on
Image-level Supervised Instance Segmentation
on COCO test-dev
(using extra training data)
MatchBench: An Evaluation of Feature Matchers
This leads to a critical absence in this field that there is no standard datasets and evaluation metrics to evaluate different feature matchers fairly.
Hifi: Hierarchical feature integration for skeleton detection
In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts.
Crowd Counting With Deep Negative Correlation Learning
Deep convolutional networks (ConvNets) have achieved unprecedented performances on many computer vision tasks.
Ranked #9 on
Crowd Counting
on WorldExpo’10
Enhanced-alignment Measure for Binary Foreground Map Evaluation
The existing binary foreground map (FM) measures to address various types of errors in either pixel-wise or structural ways.
Learning Pixel-wise Labeling from the Internet without Human Interaction
Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation.
Optimizing the F-measure for Threshold-free Salient Object Detection
By reformulating the standard F-measure we propose the relaxed F-measure which is differentiable w. r. t the posterior and can be easily appended to the back of CNNs as the loss function.
Semantic Edge Detection with Diverse Deep Supervision
Semantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation, object proposal generation, and object recognition.
Face Sketch Synthesis Style Similarity:A New Structure Co-occurrence Texture Measure
However, human perception of the similarity of two sketches will consider both structure and texture as essential factors and is not sensitive to slight ("pixel-level") mismatches.
WebSeg: Learning Semantic Segmentation from Web Searches
In this paper, we improve semantic segmentation by automatically learning from Flickr images associated with a particular keyword, without relying on any explicit user annotations, thus substantially alleviating the dependence on accurate annotations when compared to previous weakly supervised methods.
Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction
Although these tasks are inherently very different, we show that our unified approach performs very well on all of them and works far better than current single-purpose state-of-the-art methods.
Review of Visual Saliency Detection with Comprehensive Information
With the acquisition technology development, more comprehensive information, such as depth cue, inter-image correspondence, or temporal relationship, is available to extend image saliency detection to RGBD saliency detection, co-saliency detection, or video saliency detection.
Revisiting Video Saliency: A Large-scale Benchmark and a New Model
Existing video saliency datasets lack variety and generality of common dynamic scenes and fall short in covering challenging situations in unconstrained environments.
Hi-Fi: Hierarchical Feature Integration for Skeleton Detection
In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts, making object skeleton detection a challenging problem.
Ranked #2 on
Object Skeleton Detection
on SK-LARGE
S4Net: Single Stage Salient-Instance Segmentation
Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch.
Image Matching: An Application-oriented Benchmark
To this end, we present a uniform benchmark with novel evaluation metrics and a large-scale dataset for evaluating the overall performance of image matching methods.
Structure-measure: A New Way to Evaluate Foreground Maps
Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a SM and a GT map.
GMS: Grid-based Motion Statistics for Fast, Ultra-Robust Feature Correspondence
Incorporating smoothness constraints into feature matching is known to enable ultra-robust matching.
Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
We investigate a principle way to progressively mine discriminative object regions using classification networks to address the weakly-supervised semantic segmentation problems.
Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation
We focus on the following three aspects of EM: (i) initialization; (ii) latent posterior estimation (E-step) and (iii) the parameter update (M-step).
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Richer Convolutional Features for Edge Detection
Using VGG16 network, we achieve \sArt results on several available datasets.
Ranked #5 on
Edge Detection
on BIPED
FLIC: Fast Linear Iterative Clustering with Active Search
It also has drawbacks on convergence rate as a result of both the fixed search region and separately doing the assignment step and the update step.
Deeply supervised salient object detection with short connections
Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs).
Ranked #4 on
RGB Salient Object Detection
on SBU / SBU-Refine
Sequential Optimization for Efficient High-Quality Object Proposal Generation
We propose a novel object proposal algorithm, BING++, which inherits the virtue of good computational efficiency of BING but significantly improves its proposal localization quality.
SemanticPaint: A Framework for the Interactive Segmentation of 3D Scenes
We present an open-source, real-time implementation of SemanticPaint, a system for geometric reconstruction, object-class segmentation and learning of 3D scenes.
STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
Then, a better network called Enhanced-DCNN is learned with supervision from the predicted segmentation masks of simple images based on the Initial-DCNN as well as the image-level annotations.
Salient Object Detection: A Benchmark
We extensively compare, qualitatively and quantitatively, 40 state-of-the-art models (28 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over 6 challenging datasets for the purpose of benchmarking salient object detection and segmentation methods.
Salient Object Detection: A Survey
Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision.
Salient Object Detection: A Discriminative Regional Feature Integration Approach
Our method, which is based on multi-level image segmentation, utilizes the supervised learning approach to map the regional feature vector to a saliency score.
BING: Binarized Normed Gradients for Objectness Estimation at 300fps
Training a generic objectness measure to produce a small set of candidate object windows, has been shown to speed up the classical sliding window object detection paradigm.
Dense Semantic Image Segmentation with Objects and Attributes
The concepts of objects and attributes are both important for describing images precisely, since verbal descriptions often contain both adjectives and nouns (e. g. "I see a shiny red chair').
ImageSpirit: Verbal Guided Image Parsing
This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images.
Sketch2Photo: Internet Image Montage
The composed picture is generated by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet.
