Related papers: Multi-task Image Classification via Collaborative,…
Spike-and-slab priors are popular Bayesian solutions for high-dimensional linear regression problems. Previous theoretical studies on spike-and-slab methods focus on specific prior formulations and use prior-dependent conditions and…
Scene coordinate regression (SCR) models have proven to be powerful implicit scene representations for 3D vision, enabling visual relocalization and structure-from-motion. SCR models are trained specifically for one scene. If training…
Unsupervised representation learning for image clustering is essential in computer vision. Although the advancement of visual models has improved image clustering with efficient visual representations, challenges still remain. Firstly,…
In this paper, we propose a novel semi-supervised feature selection framework by mining correlations among multiple tasks and apply it to different multimedia applications. Instead of independently computing the importance of features for…
Sparse and noisy images (SNIs), like those in spatial gene expression data, pose significant challenges for effective representation learning and clustering, which are essential for thorough data analysis and interpretation. In response to…
Scene parsing aims to recognize the object category of every pixel in scene images, and it plays a central role in image content understanding and computer vision applications. However, accurate scene parsing from unconstrained real-world…
Structural magnetic resonance imaging (sMRI) provides accurate estimates of the brain's structural organization and learning invariant brain representations from sMRI is an enduring issue in neuroscience. Previous deep representation…
Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both time-intensive…
We consider the problem of robust face recognition in which both the training and test samples might be corrupted because of disguise and occlusion. Performance of conventional subspace learning methods and recently proposed sparse…
The recognition of texts existing in camera-captured images has become an important issue for a great deal of research during the past few decades. This give birth to Scene Character Recognition (SCR) which is an important step in scene…
How do computers and intelligent agents view the world around them? Feature extraction and representation constitutes one the basic building blocks towards answering this question. Traditionally, this has been done with carefully engineered…
Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…
We propose a scheme for multi-layer representation of images. The problem is first treated from an information-theoretic viewpoint where we analyze the behavior of different sources of information under a multi-layer data compression…
Computer vision tasks are traditionally defined and evaluated using semantic categories. However, it is known to the field that semantic classes do not necessarily correspond to a unique visual class (e.g. inside and outside of a car).…
Recent advances in generative models have highlighted the need for robust detectors capable of distinguishing real images from AI-generated images. While existing methods perform well on known generators, their performance often declines…
Explainable object recognition using vision-language models such as CLIP involves predicting accurate category labels supported by rationales that justify the decision-making process. Existing methods typically rely on prompt-based…
Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks. Such approaches employ data…
Face recognition has been widely studied due to its importance in different applications; however, most of the proposed methods fail when face images are occluded or captured under illumination and pose variations. Recently several low-rank…
Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task with many real-world applications. Recent work learns an alignment between textual and visual spaces to compensate for insufficient image labels,…
Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification, segmentation and detection. The low-shot learning…