Search Results for author:
Found 50 papers, 31 papers with code
3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation
Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks, yet they remain fundamentally limited in their understanding of 3D spatial structures.
Rethinking Direct Preference Optimization in Diffusion Models
While recent advances in this area have extended preference optimization techniques from large language models (LLMs) to the diffusion setting, they often struggle with limited exploration.
No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weather
We observed that adverse weather induces degradation of semantic-level features and both corruption of local features, leading to a misprediction of "things" as "stuff".
Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation
Open-Vocabulary Part Segmentation (OVPS) is an emerging field for recognizing fine-grained parts in unseen categories.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models
To address these challenges, we propose Distribution-aware Group Quantization (DGQ), a method that identifies and adaptively handles pixel-wise and channel-wise outliers to preserve image quality.
Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification
Multi-label classification is crucial for comprehensive image understanding, yet acquiring accurate annotations is challenging and costly.
Length-Aware DETR for Robust Moment Retrieval
Video Moment Retrieval (MR) aims to localize moments within a video based on a given natural language query.
Ranked #8 on
Moment Retrieval
on QVHighlights
Sampling Bag of Views for Open-Vocabulary Object Detection
Our approach groups contextually related ``concepts'' into a bag and adjusts the scale of concepts within the bag for more effective embedding alignment.
I0T: Embedding Standardization Method Towards Zero Modality Gap
Contrastive Language-Image Pretraining (CLIP) enables zero-shot inference in downstream tasks such as image-text retrieval and classification.
MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
Referring Image Segmentation (RIS) is an advanced vision-language task that involves identifying and segmenting objects within an image as described by free-form text descriptions.
Ranked #6 on
Referring Expression Segmentation
on RefCOCO testB
Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation
Additionally, we employ a dual-branch structure to mitigate performance degradation caused by data imbalance.
Ranked #1 on
Semi-Supervised Semantic Segmentation
on nuScenes
LIDAR Semantic Segmentation
Semi-Supervised Semantic Segmentation
Label-Augmented Dataset Distillation
Our label generation strategy can complement existing dataset distillation methods for significantly enhancing their training efficiency and performance.
Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering
Our evaluation protocols measure image hallucination by testing if images from existing TTI models can correctly respond to these questions.
TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder
Recent breakthroughs in text-to-image models have opened up promising research avenues in personalized image generation, enabling users to create diverse images of a specific subject using natural language prompts.
Scribble-Guided Diffusion for Training-free Text-to-Image Generation
Recent advancements in text-to-image diffusion models have demonstrated remarkable success, yet they often struggle to fully capture the user's intent.
DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation
Score distillation sampling (SDS) has emerged as an effective framework in text-driven 3D editing tasks, leveraging diffusion models for 3D-consistent editing.
Addressing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval
Depending on the nature of the hallucination, we employ off-the-shelf image editing tools, either InstructPix2Pix or IP-Adapter, to leverage factual information from the retrieved image.
Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather
Motivated by this issue, we identified key factors of adverse weather and conducted a toy experiment to pinpoint the main causes of performance degradation: (1) Geometric perturbation due to refraction caused by fog or droplets in the air and (2) Point drop due to energy absorption and occlusions.
Ranked #1 on
LIDAR Semantic Segmentation
on SemanticSTF
Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation
We further extend our ensemble method to CAMs from AMN (ResNet-like) and MCTformer (ViT-like) models, achieving performance benefits in advanced WSSS models.
Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
Open-vocabulary part segmentation (OVPS) is an emerging research area focused on segmenting fine-grained entities using diverse and previously unseen vocabularies.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
Latent Inversion with Timestep-aware Sampling for Training-free Non-rigid Editing
In this work, we propose a training-free approach for non-rigid editing with Stable Diffusion, aimed at improving the identity preservation quality without compromising editability.
Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels
This study demonstrates a cost-effective approach to semantic segmentation using self-supervised vision transformers (SSVT).
Memory-Efficient Fine-Tuning for Quantized Diffusion Model
The emergence of billion-parameter diffusion models such as Stable Diffusion XL, Imagen, and DALL-E 3 has significantly propelled the domain of generative AI.
Weakly Supervised Semantic Segmentation for Driving Scenes
Notably, the proposed method achieves 51. 8\% mIoU on the Cityscapes test dataset, showcasing its potential as a strong WSSS baseline on driving scene datasets.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
SeiT++: Masked Token Modeling Improves Storage-efficient Training
A recent breakthrough by SeiT proposed the use of Vector-Quantized (VQ) feature vectors (i. e., tokens) as network inputs for vision classification.
Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data
Since our synthesizer only considers the generic properties of natural images, the single model pretrained on our dataset can be consistently transferred to various target datasets, and even outperforms the previous methods pretrained with the natural images in terms of Fr'echet inception distance.
Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds
Existing WSSS methods commonly argue that the sparse coverage of CAM incurs the performance bottleneck of WSSS.
Ranked #18 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Weakly supervised segmentation
Weakly supervised Semantic Segmentation
+1
S-Walk: Accurate and Scalable Session-based Recommendationwith Random Walks
Session-based recommendation (SR) predicts the next items from a sequence of previous items consumed by an anonymous user.
Few-shot Font Generation with Weakly Supervised Localized Representations
Existing methods learn to disentangle style and content elements by developing a universal style representation for each font style.
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation
Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects.
Ranked #24 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts
MX-Font extracts multiple style features not explicitly conditioned on component labels, but automatically by multiple experts to represent different local concepts, e. g., left-side sub-glyph.
Session-aware Linear Item-Item Models for Session-based Recommendation
Session-based recommendation aims at predicting the next item given a sequence of previous items consumed in the session, e. g., on e-commerce or multimedia streaming services.
Logit As Auxiliary Weak-supervision for More Reliable and Accurate Prediction
When a person identifies objects, he or she can think by associating objects to many classes and conclude by taking inter-class relations into account.
GridMix: Strong regularization through local context mapping
Recently developed regularization techniques improve the networks generalization by only considering the global context.
Waste not, Want not: All-Alive Pruning for Extremely Sparse Networks
We demonstrate that AAP equipped with existing pruning methods (i. e., iterative pruning, one-shot pruning, and dynamic pruning) consistently improves the accuracy of original methods at 128× - 4096× compression ratios on three benchmark datasets.
Few-shot Font Generation with Localized Style Representations and Factorization
However, learning component-wise styles solely from reference glyphs is infeasible in the few-shot font generation scenario, when a target script has a large number of components, e. g., over 200 for Chinese.
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets
In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.
Rethinking the Truly Unsupervised Image-to-Image Translation
To this end, we propose a truly unsupervised image-to-image translation model (TUNIT) that simultaneously learns to separate image domains and translates input images into the estimated domains.
Evaluating Weakly Supervised Object Localization Methods Right
In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.
Collaborative Distillation for Top-N Recommendation
Knowledge distillation (KD) is a well-known method to reduce inference latency by compressing a cumbersome teacher model to a small student model.
Attention-based Dropout Layer for Weakly Supervised Object Localization
Weakly Supervised Object Localization (WSOL) techniques learn the object location only using image-level labels, without location annotations.
Depth Reconstruction of Translucent Objects from a Single Time-of-Flight Camera using Deep Residual Networks
We propose a novel approach to recovering the translucent objects from a single time-of-flight (ToF) depth camera using deep residual networks.
Recycling the discriminator for improving the inference mapping of GAN
In order to analyze the real data in the latent space of GANs, it is necessary to investigate the inverse generation mapping from the data to the latent vector.
Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
Also, we show that our model can achieve the competitive performance with the state-of-the-art attribute editing technique in terms of attribute editing quality.
Resembled Generative Adversarial Networks: Two Domains with Similar Attributes
We propose a novel algorithm, namely Resembled Generative Adversarial Networks (GAN), that generates two different domain data simultaneously where they resemble each other.
Generative Adversarial Networks for Unsupervised Object Co-localization
Our important finding is that high image diversity of GAN, which is a main goal in GAN research, is ironically disadvantageous for object localization, because such discriminators focus not only on the target object, but also on the various objects, such as background objects.
Discriminator Feature-based Inference by Recycling the Discriminator of GANs
Various studies assert that the latent space of a GAN is semanticallymeaningful and can be utilized for advanced data analysis and manipulation.
MGGAN: Solving Mode Collapse using Manifold Guided Training
Mode collapse is a critical problem in training generative adversarial networks.
Improved Techniques For Weakly-Supervised Object Localization
To this end, we employ an effective data augmentation for improving the accuracy of the object localization.
Improved Training of Generative Adversarial Networks Using Representative Features
Because the AE learns to minimize forward KL divergence, our GAN training with representative features is influenced by both reverse and forward KL divergence.
