Search Results for author:
Found 24 papers, 15 papers with code
VarSR: Variational Super-Resolution Network for Very Low Resolution Images
As is well known, single image super-resolution (SR) is an ill-posed problem where multiple high resolution (HR) images can be matched to one low resolution (LR) image due to the difference of their representation capabilities.
Diversity-aware Channel Pruning for StyleGAN Compression
Specifically, by assessing channel importance based on their sensitivities to latent vector perturbations, our method enhances the diversity of samples in the compressed model.
Noise-free Optimization in Early Training Steps for Image Super-Resolution
To tackle this issue, we propose a novel optimization method that can effectively remove the inherent noise term in the early steps of vanilla training by estimating the optimal centroid and directly optimizing toward the estimation.
VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting
Zero-Shot Object Counting (ZSOC) aims to count referred instances of arbitrary classes in a query image without human-annotated exemplars.
Ranked #2 on
Zero-Shot Counting
on FSC147
Towards Squeezing-Averse Virtual Try-On via Sequential Deformation
In this paper, we first investigate a visual quality degradation problem observed in recent high-resolution virtual try-on approach.
Task-Disruptive Background Suppression for Few-Shot Segmentation
Based on these two scores, we define a query background relevant score that captures the similarity between the backgrounds of the query and the support, and utilize it to scale support background features to adaptively restrict the impact of disruptive support backgrounds.
Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer
Despite the impressive generative capabilities of diffusion models, existing diffusion model-based style transfer methods require inference-stage optimization (e. g. fine-tuning or textual inversion of style) which is time-consuming, or fails to leverage the generative ability of large-scale diffusion models.
Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Grounding
Dummy tokens conditioned by text query take portions of the attention weights, preventing irrelevant video clips from being represented by the text query.
Ranked #1 on
Highlight Detection
on TvSum
Self-Feedback DETR for Temporal Action Detection
In this paper, we point out the problem in the self-attention of DETR for TAD; the attention modules focus on a few key elements, called temporal collapse problem.
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification
While TDM influences high-level feature maps by task-adaptive calibration of channel-wise importance, we further introduce Instance Attention Module (IAM) operating in intermediate layers of feature extractors to instance-wisely highlight object-relevant channels, by extending QAM.
Leveraging Hidden Positives for Unsupervised Semantic Segmentation
Specifically, we add the loss propagating to local hidden positives, semantically similar nearby patches, in proportion to the predefined similarity scores.
Ranked #2 on
Unsupervised Semantic Segmentation
on Potsdam-3
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection
As we observe the insignificant role of a given query in transformer architectures, our encoding module starts with cross-attention layers to explicitly inject the context of text query into video representation.
Ranked #2 on
Highlight Detection
on TvSum
Disentangled Representation Learning for Unsupervised Neural Quantization
The inverted index is a widely used data structure to avoid the infeasible exhaustive search.
Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognition
A dramatic increase in real-world video volume with extremely diverse and emerging topics naturally forms a long-tailed video distribution in terms of their categories, and it spotlights the need for Video Long-Tailed Recognition (VLTR).
Tailoring Self-Supervision for Supervised Learning
Our exhaustive experiments validate the merits of LoRot as a pretext task tailored for supervised learning in terms of robustness and generalization capability.
Ranked #9 on
Data Augmentation
on ImageNet
Difficulty-Aware Simulator for Open Set Recognition
Furthermore, moderate- and easy-difficulty samples are also yielded by our modified GAN and Copycat, respectively.
Task Discrepancy Maximization for Fine-grained Few-Shot Classification
Specifically, TDM learns task-specific channel weights based on two novel components: Support Attention Module (SAM) and Query Attention Module (QAM).
Ranked #9 on
Few-Shot Image Classification
on CUB 200 5-way 5-shot
(using extra training data)
Local Attention Pyramid for Scene Image Generation
To address this, we propose a novel attention module, Local Attention Pyramid (LAP) module tailored for scene image synthesis, that encourages GANs to generate diverse object classes in a high quality by explicit spread of high attention scores to local regions, since objects in scene images are scattered over the entire images.
Pixel-Level Kernel Estimation for Blind Super-Resolution
Furthermore, based on this assumption, there have been attempts to estimate the blur kernel of a given LR image, since correct kernel priors are known to be helpful in super-resolution.
Ranked #5 on
Blind Super-Resolution
on DIV2KRK - 4x upscaling
Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency
The proposed tasks enable the discriminators to learn representations of appearance and temporal context, and force the generator to synthesize videos with consistent appearance and natural flow of motions.
Product Quantizer Aware Inverted Index for Scalable Nearest Neighbor Search
To address the raised question, we suggest a joint optimization of the coarse and fine quantizers by substituting the original objective of the coarse quantizer to end-to-end quantization distortion.
Collaborative Learning With Disentangled Features for Zero-Shot Domain Adaptation
In such a case, we can capture the domain shift between the source domain and target domain from an unseen task and transfer it to the task of interest, which is known as zero-shot domain adaptation (ZSDA).
Shortlist Selection With Residual-Aware Distance Estimator for K-Nearest Neighbor Search
We have tested the proposed method with the inverted index and multi-index on a diverse set of benchmarks including up to one billion data points with varying dimensions, and found that our method robustly improves the accuracy of shortlists (up to 127% relatively higher) over the state-of-the-art techniques with a comparable or even faster computational cost.
Distance Encoded Product Quantization
This result is achieved mainly because our method accurately estimates distances between two data points with the new binary codes and distance metric.
