Search Results for author:
Found 29 papers, 15 papers with code
Continual Vision-Language Representation Learning with Off-Diagonal Information
Moreover, we empirically and theoretically demonstrate how SD leads to a performance decline for CLIP on cross-modal retrieval tasks.
Learning Transferable Pedestrian Representation from Multimodal Information Supervision
Recent researches on unsupervised person re-identification~(reID) have demonstrated that pre-training on unlabeled person images achieves superior performance on downstream reID tasks than pre-training on ImageNet.
Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models
Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen pre-training models.
Lformer: Text-to-Image Generation with L-shape Block Parallel Decoding
To better accelerate the generative transformers while keeping good generation quality, we propose Lformer, a semi-autoregressive text-to-image generation model.
Integrally Pre-Trained Transformer Pyramid Networks
In this paper, we present an integral pre-training framework based on masked image modeling (MIM).
Fine-Grained Semantically Aligned Vision-Language Pre-Training
Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks.
Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos
In this paper, we introduce a new task, named Temporal Emotion Localization in videos~(TEL), which aims to detect human emotions and localize their corresponding temporal boundaries in untrimmed videos with aligned subtitles.
DE-Net: Dynamic Text-guided Image Editing Adversarial Networks
To solve these limitations, we propose: (i) a Dynamic Editing Block (DEBlock) which composes different editing modules dynamically for various editing requirements.
MVP: Multimodality-guided Visual Pre-training
Recently, masked image modeling (MIM) has become a promising direction for visual pre-training.
Learning To Learn by Jointly Optimizing Neural Architecture and Weights
Existing NAS-based meta-learning methods apply a two-stage strategy, i. e., first searching architectures and then re-training meta-weights on the searched architecture.
Revisiting Catastrophic Forgetting in Class Incremental Learning
After investigating existing strategies, we observe that there is a lack of study on how to prevent the inter-phase confusion.
Rectifying the Shortcut Learning of Background for Few-Shot Learning
The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL).
Exploring the Diversity and Invariance in Yourself for Visual Pre-Training Task
By simply pulling the different augmented views of each image together or other novel mechanisms, they can learn much unsupervised knowledge and significantly improve the transfer performance of pre-training models.
Visformer: The Vision-friendly Transformer
The past year has witnessed the rapid development of applying the Transformer module to vision problems.
Ranked #455 on
Image Classification
on ImageNet
Spatiotemporal Transformer for Video-based Person Re-identification
Recently, the Transformer module has been transplanted from natural language processing to computer vision.
UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains.
Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation.
Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning.
Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
Neural architecture search (NAS) has attracted increasing attentions in both academia and industry.
GOLD-NAS: Gradual, One-Level, Differentiable
There has been a large literature of neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility.
Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks
We alleviate this issue by training a graph convolutional network to fit the performance of sampled sub-networks so that the impact of random errors becomes minimal.
Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio
Automatic designing computationally efficient neural networks has received much attention in recent years.
Circumventing Outliers of AutoAugment with Knowledge Distillation
AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper setting may degenerate network optimization.
Ranked #171 on
Image Classification
on ImageNet
Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization
The fundamental difficulty in person re-identification (ReID) lies in learning the correspondence among individual cameras.
Ranked #15 on
Unsupervised Domain Adaptation
on Duke to Market
Direct Transfer Person Re-identification
Domain Adaptive Person Re-Identification
+2
Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters
Our approach bridges the gap from two aspects, namely, amending the estimation on the architectural gradients, and unifying the hyper-parameter settings in the search and re-training stages.
Single Camera Training for Person Re-identification
Differently, this paper investigates ReID in an unexplored single-camera-training (SCT) setting, where each person in the training set appears in only one camera.
Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e. g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network.
Ranked #10 on
Unsupervised Person Re-Identification
on DukeMTMC-reID
(Rank-10 metric)
GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
Targeting to solve these problems, this work proposes a Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework, respectively.
Ranked #86 on
Person Re-Identification
on Market-1501
