Search Results for author:
Found 14 papers, 7 papers with code
Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning
We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field.
Position Embedding Needs an Independent Layer Normalization
By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find that the default PE joining method (simply adding the PE and patch embedding together) operates the same affine transformation to token embedding and PE, which limits the expressiveness of PE and hence constrains the performance of VTs.
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
Most video-and-language representation learning approaches employ contrastive learning, e. g., CLIP, to project the video and text features into a common latent space according to the semantic similarities of text-video pairs.
Ranked #2 on
Video Retrieval
on LSMDC
(text-to-video Mean Rank metric)
Fuzzy Positive Learning for Semi-supervised Semantic Segmentation
Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations.
ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation
Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e. g., unsupervised semantic segmentation (USS).
Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering
Under this setting, these 2D spatial reasoning approaches cannot distinguish the fine-grain spatial relations between visual objects and scene texts on the same image plane, thereby impairing the interpretability and performance of TextVQA models.
Locality Guidance for Improving Vision Transformers on Tiny Datasets
Therefore, our locality guidance approach is very simple and efficient, and can serve as a basic performance enhancement method for VTs on tiny datasets.
$L_2$BN: Enhancing Batch Normalization by Equalizing the $L_2$ Norms of Features
In this paper, we analyze batch normalization from the perspective of discriminability and find the disadvantages ignored by previous studies: the difference in $l_2$ norms of sample features can hinder batch normalization from obtaining more distinguished inter-class features and more compact intra-class features.
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
Visual appearance is considered to be the most important cue to understand images for cross-modal retrieval, while sometimes the scene text appearing in images can provide valuable information to understand the visual semantics.
Ranked #10 on
Cross-Modal Retrieval
on Flickr30k
(using extra training data)
CDNet: Centripetal Direction Network for Nuclear Instance Segmentation
Specifically, we define the centripetal direction feature as a class of adjacent directions pointing to the nuclear center to represent the spatial relationship between pixels within the nucleus.
Learning fragment self-attention embeddings for image-text matching
In this paper, we propose Self-Attention Embeddings (SAEM) to exploit fragment relations in images or texts by self-attention mechanism, and aggregate fragment information into visual and textual embeddings.
Harmonized Multimodal Learning with Gaussian Process Latent Variable Models
Multimodal learning aims to discover the relationship between multiple modalities.
Multimodal Gaussian Process Latent Variable Models With Harmonization
We incorporate the harmonization mechanism into the learning process of multimodal GPLVMs.
Similarity Gaussian Process Latent Variable Model for Multi-Modal Data Analysis
Data from real applications involve multiple modalities representing content with the same semantics and deliver rich information from complementary aspects.
