Search Results for author:
Found 78 papers, 50 papers with code
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.
K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs
Recent studies have explored combining different LoRAs to jointly generate learned style and content.
LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
In this paper, we introduce LLaVA-Octopus, a novel video multimodal large language model.
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).
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.
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.
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.
Multi-Task Dense Prediction via Mixture of Low-Rank Experts
Furthermore, to control the parameters and computational cost brought by the increase in the number of experts, we take inspiration from LoRA and propose to leverage the low-rank format of a vanilla convolution in the expert network.
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
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)
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.
Fast Window-Based Event Denoising with Spatiotemporal Correlation Enhancement
Previous deep learning-based event denoising methods mostly suffer from poor interpretability and difficulty in real-time processing due to their complex architecture designs.
Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
However, these models struggle to effectively suppress the generation of undesired content, which is explicitly requested to be omitted from the generated image in the prompt.
MCANet: Medical Image Segmentation with Multi-Scale Cross-Axis Attention
To process the significant variations of lesion regions or organs in individual sizes and shapes, we also use multiple convolutions of strip-shape kernels with different kernel sizes in each axial attention path to improve the efficiency of the proposed MCA in encoding spatial information.
Polyper: Boundary Sensitive Polyp Segmentation
We present a new boundary sensitive framework for polyp segmentation, called Polyper.
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.
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.
ChatAnything: Facetime Chat with LLM-Enhanced Personas
For MoV, we utilize the text-to-speech (TTS) algorithms with a variety of pre-defined tones and select the most matching one based on the user-provided text description automatically.
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.
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
MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask
In this work, we identify that a crucial factor leading to the text-image mismatch issue is the inadequate cross-modality relation learning between the prompt and the output image.
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.
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.
AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
It is based on two essential designs.
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
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
Traffic Scene Parsing through the TSP6K Dataset
To date, most existing datasets focus on autonomous driving scenes.
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.
Deep Negative Correlation Classification
Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm.
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.
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
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.
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.
L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation
Our framework conducts the global network to learn the captured rich object detail knowledge from a global view and thereby produces high-quality attention maps that can be directly used as pseudo annotations for semantic segmentation networks.
Ranked #17 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
VOLO: Vision Outlooker for Visual Recognition
Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their performance is still inferior to that of the latest SOTA CNNs if no extra data are provided.
Ranked #1 on
Image Classification
on VizWiz-Classification
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.
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.
LV-BERT: Exploiting Layer Variety for BERT
In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by exploiting layer variety from two aspects: the layer type set and the layer order.
Refiner: Refining Self-attention for Vision Transformers
Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs.
Ranked #174 on
Image Classification
on ImageNet
All Tokens Matter: Token Labeling for Training Better Vision Transformers
In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs).
Ranked #3 on
Efficient ViTs
on ImageNet-1K (With LV-ViT-S)
FakeMix Augmentation Improves Transparent Object Detection
However, these methods usually encounter boundary-related imbalance problem, leading to limited generation capability.
DeepViT: Towards Deeper Vision Transformer
In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the performance of ViTs saturate fast when scaled to be deeper.
Ranked #463 on
Image Classification
on ImageNet
AutoSpace: Neural Architecture Search with Less Human Interference
Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction.
Coordinate Attention for Efficient Mobile Network Design
Recent studies on mobile network design have demonstrated the remarkable effectiveness of channel attention (e. g., the Squeeze-and-Excitation attention) for lifting model performance, but they generally neglect the positional information, which is important for generating spatially selective attention maps.
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.
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.
Rotate to Attend: Convolutional Triplet Attention Module
In this paper, we investigate light-weight but effective attention mechanisms and present triplet attention, a novel method for computing attention weights by capturing cross-dimension interaction using a three-branch structure.
Rethinking Bottleneck Structure for Efficient Mobile Network Design
In this paper, we rethink the necessity of such design changes and find it may bring risks of information loss and gradient confusion.
Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation
In this paper, we propose a novel multi-miner framework to perform a region mining process that adapts to diverse object sizes and is thus able to mine more integral and finer object regions.
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.
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
Semantic Domain Adversarial Networks for Unsupervised Domain Adaptation
To successfully align the multi-modal data structures across domains, the following works exploit discriminative information in the adversarial training process, e. g., using multiple class-wise discriminators and introducing conditional information in input or output of the domain discriminator.
Cross-layer Feature Pyramid Network for Salient Object Detection
Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective in salient object detection.
PROTOTYPE-ASSISTED ADVERSARIAL LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION
Previous adversarial learning methods condition domain alignment only on pseudo labels, but noisy and inaccurate pseudo labels may perturb the multi-class distribution embedded in probabilistic predictions, hence bringing insufficient alleviation to the latent mismatch problem.
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
Neural Epitome Search for Architecture-Agnostic Network Compression
The recent WSNet [1] is a new model compression method through sampling filterweights from a compact set and has demonstrated to be effective for 1D convolutionneural networks (CNNs).
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
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)
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.
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.
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.
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
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.
