Search Results for author:
Found 39 papers, 22 papers with code
Content-Consistent Matching for Domain Adaptive Semantic Segmentation
The target of CCM is to acquire those synthetic images that share similar distribution with the real ones in the target domain, so that the domain gap can be naturally alleviated by employing the content-consistent synthetic images for training.
Ranked #12 on
Semantic Segmentation
on GTAV-to-Cityscapes Labels
Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese Dishes
In general cases, existing text-to-image generation models excel in producing high-quality images; however, they struggle to capture diverse characteristics and faithful details of specific domains, particularly Chinese dishes.
FreeInv: Free Lunch for Improving DDIM Inversion
It is motivated from a statistical perspective that an ensemble of DDIM inversion processes for multiple trajectories yields a smaller trajectory mismatch error on expectation.
Rethinking the Global Knowledge of CLIP in Training-Free Open-Vocabulary Semantic Segmentation
As the representation of each patch is finally determined by the attention weights and the Value embeddings, we propose to reshape the last-block attention and Value embeddings to aggregate useful global context into final features.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+1
Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion Models
Extensive experiments demonstrate that compared to previous works, our method can generate videos with appearance more aligned with the text descriptions and motion more consistent with the reference videos.
Normalizing Batch Normalization for Long-Tailed Recognition
Differently, in this paper, we identify that the bias towards the frequent class may be encoded into features, i. e., the rare-specific features which play a key role in discriminating the rare class are much weaker than the frequent-specific features.
Attention Head Purification: A New Perspective to Harness CLIP for Domain Generalization
In this paper, we propose a new perspective to harness CLIP for DG, i. e., attention head purification.
Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection
In this work, we propose an Exemplar-Guided Reflection with Memory mechanism (ERM) to realize more efficient and accurate prompt optimization.
PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting
In this paper, we propose a new method called PLGS that enables 3DGS to generate consistent panoptic segmentation masks from noisy 2D segmentation masks while maintaining superior efficiency compared to NeRF-based methods.
SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training
Considering that the overly fast representation learning and the biased classification layer constitute this particular problem, we introduce the advanced Slow Learner with Classifier Alignment (SLCA++) framework to unleash the power of Seq FT, serving as a strong baseline approach for CLPT.
ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
In this paper, we propose to explicitly model and rectify the bias existing in CLIP to facilitate the unsupervised semantic segmentation task.
VISA: Reasoning Video Object Segmentation via Large Language Models
In this paper, we introduce a new task, Reasoning Video Object Segmentation (ReasonVOS).
Ranked #3 on
Referring Video Object Segmentation
on ReVOS
Mining Open Semantics from CLIP: A Relation Transition Perspective for Few-Shot Learning
Specifically, we adopt a transformer module which takes the visual feature as "Query", the text features of the anchors as "Key" and the similarity matrix between the text features of anchor and target classes as "Value".
Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
In this paper we propose to explicitly model and rectify the bias existing in CLIP to facilitate the unsupervised semantic segmentation.
Tuning-Free Inversion-Enhanced Control for Consistent Image Editing
Consistent editing of real images is a challenging task, as it requires performing non-rigid edits (e. g., changing postures) to the main objects in the input image without changing their identity or attributes.
LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video Translation
As a result, the corresponding regions across the adjacent frames can share closely-related query tokens and attention outputs, which can further improve latent-level consistency to enhance visual temporal coherence of generated videos.
AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning
Text consists of a category name and a fixed number of learnable parameters which are selected from our designed attribute word bank and serve as attributes.
PiClick: Picking the desired mask from multiple candidates in click-based interactive segmentation
Click-based interactive segmentation aims to generate target masks via human clicking, which facilitates efficient pixel-level annotation and image editing.
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data.
Adversarially Masking Synthetic To Mimic Real: Adaptive Noise Injection for Point Cloud Segmentation Adaptation
With the help of adversarial training, the masking module can learn to generate source masks to mimic the pattern of irregular target noise, thereby narrowing the domain gap.
Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
Based on this observation, we propose a simple strategy, i. e., increasing the number of training shots, to mitigate the loss of intrinsic dimension caused by robustness-promoting regularization.
VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer
To the best of our knowledge, this is the first time quantization has been incorporated into ViT acceleration on FPGAs with the help of a fully automatic framework to guide the quantization strategy on the software side and the accelerator implementations on the hardware side given the target frame rate.
Domain Consensus Clustering for Universal Domain Adaptation
To better exploit the intrinsic structure of the target domain, we propose Domain Consensus Clustering (DCC), which exploits the domain consensus knowledge to discover discriminative clusters on both common samples and private ones.
Ranked #4 on
Partial Domain Adaptation
on Office-31
Few-Shot Segmentation via Cycle-Consistent Transformer
Directly performing cross-attention may aggregate these features from support to query and bias the query features.
Ranked #59 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
The conventional solution to this task is to minimize the discrepancy between source and target to enable effective knowledge transfer.
Ranked #27 on
Synthetic-to-Real Translation
on SYNTHIA-to-Cityscapes
Argus: Efficient Activity Detection System for Extended Video Analysis
We propose an Efficient Activity Detection System, Argus, for Extended Video Analysis in the surveillance scenario.
Training-free Monocular 3D Event Detection System for Traffic Surveillance
To deal with the aforementioned problems, in this paper, we propose a training-free monocular 3D event detection system for traffic surveillance.
Attract or Distract: Exploit the Margin of Open Set
In this paper, we exploit the semantic structure of open set data from two aspects: 1) Semantic Categorical Alignment, which aims to achieve good separability of target known classes by categorically aligning the centroid of target with the source.
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items.
Ranked #1 on
Information Retrieval
on Amazon
Shakeout: A New Approach to Regularized Deep Neural Network Training
Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training.
Contrastive Adaptation Network for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain.
Ranked #9 on
Domain Adaptation
on Office-31
Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
With asymptotic pruning, the information of the training set would be gradually concentrated in the remaining filters, so the subsequent training and pruning process would be stable.
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
Therefore, the network trained by our method has a larger model capacity to learn from the training data.
Self-produced Guidance for Weakly-supervised Object Localization
A stagewise approach is proposed to incorporate high confident object regions to learn the SPG masks.
Ranked #1 on
Weakly-Supervised Object Localization
on ILSVRC 2015
Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
Second, we estimate the posterior label distribution of the unlabeled data for target network training.
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
To this end, we propose to preserve two types of unsupervised similarities, 1) self-similarity of an image before and after translation, and 2) domain-dissimilarity of a translated source image and a target image.
EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks
For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer.
Ranked #11 on
Image Classification
on SVHN
Random Erasing Data Augmentation
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).
Ranked #2 on
Image Classification
on Fashion-MNIST
PatchShuffle Regularization
This paper focuses on regularizing the training of the convolutional neural network (CNN).
