171 citations · 410 across the 21 of their papers we have counts for
25 papers
Elastic Token Compression for Pixel-Space Diffusion Transformers
Eduard Zamfir, Christian Reisswig, Zongwei Wu +2
Natural images concentrate their detail in a small fraction of the frame, yet diffusion models spend a full token on every patch, in every layer and at every timestep. The waste is…
Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs
Sanghwan Kim, Rui Xiao, Stephan Alaniz +2
Multimodal Large Language Models (MLLMs) often struggle with fine-grained perception, such as identifying small objects in high-resolution images or detecting key moments in long v…
Detecting Adversarial Faces Using Only Real Face Self-Perturbations
Qian Wang, Yongqin Xian, Hefei Ling +5
Adversarial attacks aim to disturb the functionality of a target system by adding specific noise to the input samples, bringing potential threats to security and robustness when ap…
Learning Prototype Classifiers for Long-Tailed Recognition
Saurabh Sharma, Yongqin Xian, Ning Yu +1
The problem of long-tailed recognition (LTR) has received attention in recent years due to the fundamental power-law distribution of objects in the real-world. Most recent works in…
Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation
Anurag Das, Yongqin Xian, Yang He +2
For best performance, today's semantic segmentation methods use large and carefully labeled datasets, requiring expensive annotation budgets. In this work, we show that coarse anno…
I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification
Muhammad Ferjad Naeem, Muhammad Gul Zain Ali Khan, Yongqin Xian +4
Recent works have shown that unstructured text (documents) from online sources can serve as useful auxiliary information for zero-shot image classification. However, these methods…
CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution
Jiezhang Cao, Qin Wang, Yongqin Xian +7
Learning continuous image representations is recently gaining popularity for image super-resolution (SR) because of its ability to reconstruct high-resolution images with arbitrary…
I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification
Muhammad Ferjad Naeem, Yongqin Xian, Luc Van Gool +1
Despite the tremendous progress in zero-shot learning(ZSL), the majority of existing methods still rely on human-annotated attributes, which are difficult to annotate and scale. An…
Attribute Prototype Network for Any-Shot Learning
Wenjia Xu, Yongqin Xian, Jiuniu Wang +2
Any-shot image classification allows to recognize novel classes with only a few or even zero samples. For the task of zero-shot learning, visual attributes have been shown to play…
VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
Wenjia Xu, Yongqin Xian, Jiuniu Wang +2
Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current u…
3D Compositional Zero-shot Learning with DeCompositional Consensus
Muhammad Ferjad Naeem, Evin Pınar Örnek, Yongqin Xian +2
Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. To…
Learning Graph Embeddings for Open World Compositional Zero-Shot Learning
Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian +1
Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions of state and object visual primitives seen during training. A problem with standard CZSL is the assump…
Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
Yanbei Chen, Yongqin Xian, A. Sophia Koepke +2
Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to t…
A Closer Look at Self-training for Zero-Label Semantic Segmentation
Giuseppe Pastore, Fabio Cermelli, Yongqin Xian +3
Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation…
Learning Graph Embeddings for Compositional Zero-shot Learning
Muhammad Ferjad Naeem, Yongqin Xian, Federico Tombari +1
In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) i…
Open World Compositional Zero-Shot Learning
Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian +1
Compositional Zero-Shot learning (CZSL) requires to recognize state-object compositions unseen during training. In this work, instead of assuming prior knowledge about the unseen c…
Prototype-based Incremental Few-Shot Semantic Segmentation
Fabio Cermelli, Massimiliano Mancini, Yongqin Xian +2
Semantic segmentation models have two fundamental weaknesses: i) they require large training sets with costly pixel-level annotations, and ii) they have a static output space, cons…
Attribute Prototype Network for Zero-Shot Learning
Wenjia Xu, Yongqin Xian, Jiuniu Wang +2
From the beginning of zero-shot learning research, visual attributes have been shown to play an important role. In order to better transfer attribute-based knowledge from known to…
Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation
Yongqin Xian, Bruno Korbar, Matthijs Douze +3
Few-shot learning aims to recognize novel classes from a few examples. Although significant progress has been made in the image domain, few-shot video classification is relatively…
Analyzing the Dependency of ConvNets on Spatial Information
Yue Fan, Yongqin Xian, Max Maria Losch +1
Intuitively, image classification should profit from using spatial information. Recent work, however, suggests that this might be overrated in standard CNNs. In this paper, we are…
f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
Yongqin Xian, Saurabh Sharma, Bernt Schiele +1
When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditiona…
Feature Generating Networks for Zero-Shot Learning
Yongqin Xian, Tobias Lorenz, Bernt Schiele +1
Suffering from the extreme training data imbalance between seen and unseen classes, most of existing state-of-the-art approaches fail to achieve satisfactory results for the challe…
Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly
Yongqin Xian, Christoph H. Lampert, Bernt Schiele +1
Due to the importance of zero-shot learning, i.e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadi…
Zero-Shot Learning -- The Good, the Bad and the Ugly
Yongqin Xian, Bernt Schiele, Zeynep Akata
Due to the importance of zero-shot learning, the number of proposed approaches has increased steadily recently. We argue that it is time to take a step back and to analyze the stat…