Search Results for author:
Found 16 papers, 11 papers with code
Language-only Efficient Training of Zero-shot Composed Image Retrieval
Our LinCIR (Language-only training for CIR) can be trained only with text datasets by a novel self-supervision named self-masking projection (SMP).
CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion.
Ranked #3 on
Zero-Shot Composed Image Retrieval (ZS-CIR)
on CIRCO
Group Generalized Mean Pooling for Vision Transformer
As ViT groups the channels via a multi-head attention mechanism, grouping the channels by GGeM leads to lower head-wise dependence while amplifying important channels on the activation maps.
Granularity-aware Adaptation for Image Retrieval over Multiple Tasks
We address it with the proposed Grappa, an approach that starts from a strong pretrained model, and adapts it to tackle multiple retrieval tasks concurrently, using only unlabeled images from the different task domains.
Large-scale Bilingual Language-Image Contrastive Learning
This paper is a technical report to share our experience and findings building a Korean and English bilingual multimodal model.
Deep Hash Distillation for Image Retrieval
To mitigate this issue, data augmentation can be applied during training.
Towards Light-weight and Real-time Line Segment Detection
In this paper, we propose a real-time and light-weight line segment detector for resource-constrained environments named Mobile LSD (M-LSD).
Ranked #6 on
Line Segment Detection
on York Urban Dataset
RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network
In this paper, we study the compositional learning of images and texts for image retrieval.
Ranked #14 on
Image Retrieval
on Fashion IQ
Learning with Memory-based Virtual Classes for Deep Metric Learning
This can be undesirable for DML, where training and test data exhibit entirely different classes.
Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning
One of the main purposes of deep metric learning is to construct an embedding space that has well-generalized embeddings on both seen (training) classes and unseen (test) classes.
Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
Meanwhile, post-processing techniques, such as query expansion and database augmentation, have proposed the combination of feature points to obtain additional semantic information.
Symmetrical Synthesis for Deep Metric Learning
Secondly, it performs hard negative pair mining within the original and synthetic points to select a more informative negative pair for computing the metric learning loss.
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs).
Ranked #1 on
Fine-Grained Image Classification
on SOP
Fine-Grained Image Classification
Fine-Grained Visual Recognition
+4
A Benchmark on Tricks for Large-scale Image Retrieval
Many studies have been performed on metric learning, which has become a key ingredient in top-performing methods of instance-level image retrieval.
Dynamics Transfer GAN: Generating Video by Transferring Arbitrary Temporal Dynamics from a Source Video to a Single Target Image
The spatial constructs of a generated video sequence are acquired from the target image.
Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data
through a generative model is helpful in addressing the lack of training data.
