Search Results for author:
Found 10 papers, 5 papers with code
Shatter and Gather: Learning Referring Image Segmentation with Text Supervision
Referring image segmentation, the task of segmenting any arbitrary entities described in free-form texts, opens up a variety of vision applications.
Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer
In this paper, we propose a simple transfer learning scheme that maintains input patch sizes, unlike previous methods, to avoid input discrepancies.
Ranked #5 on
Audio captioning
on AudioCaps
Extending CLIP's Image-Text Alignment to Referring Image Segmentation
Referring Image Segmentation (RIS) is a cross-modal task that aims to segment an instance described by a natural language expression.
Ranked #3 on
Referring Expression Segmentation
on RefCOCO testA
(using extra training data)
Improving Cross-Modal Retrieval with Set of Diverse Embeddings
It seeks to encode a sample into a set of different embedding vectors that capture different semantics of the sample.
Self-Taught Metric Learning without Labels
At the heart of our framework lies an algorithm that investigates contexts of data on the embedding space to predict their class-equivalence relations as pseudo labels.
ReSTR: Convolution-free Referring Image Segmentation Using Transformers
Most of existing methods for this task rely heavily on convolutional neural networks, which however have trouble capturing long-range dependencies between entities in the language expression and are not flexible enough for modeling interactions between the two different modalities.
Ranked #12 on
Referring Expression Segmentation
on RefCoCo val
Embedding Transfer with Label Relaxation for Improved Metric Learning
Our method exploits pairwise similarities between samples in the source embedding space as the knowledge, and transfers them through a loss used for learning target embedding models.
Embedding Transfer via Smooth Contrastive Loss
To this end, we design a new loss called smooth contrastive loss, which pulls together or pushes apart a pair of samples in a target embedding space with strength determined by their semantic similarity in the source embedding space; an analysis of the loss reveals that this property enables more important pairs to contribute more to learning the target embedding space.
Proxy Anchor Loss for Deep Metric Learning
The former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high training complexity.
Ranked #10 on
Metric Learning
on CUB-200-2011
(using extra training data)
Fine-Grained Image Classification
Fine-Grained Vehicle Classification
+1
Semi-supervised Learning with Deep Generative Models for Asset Failure Prediction
This work presents a novel semi-supervised learning approach for data-driven modeling of asset failures when health status is only partially known in historical data.
