6 accepted papers
Integration of Large Language Models (LLMs) into visual domain tasks resulting in visual-LLMs (V-LLMs) has enabled exceptional performance in vision-language tasks particularly for visual question answering (VQA). However existing V-LLMs (e.g. BLIP-2 LLaVA) demonstrate weak spatial reasoning and loc…
We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder. With such an alignment, a model can identify regions of an imag…
The ability to detect anomaly has long been recognized as an inherent human ability, yet to date, practical AI solutions to mimic such capability have been lacking. This lack of progress can be attributed to several factors. To begin with, the distribution of ``abnormalities'' is intractable. Anythi…
Aggregated second-order features extracted from deep convolutional networks have been shown to be effective for texture generation, fine-grained recognition, material classification, and scene understanding. In this paper we study a class of orderless aggregation functions designed to minimize emph{…
A number of recent approaches have used deep convolutional neural networks (CNNs) to build texture representations. Nevertheless, it is still unclear how these mod- els represent texture and invariances to categorical variations. This work conducts a systematic evaluation of recent CNN-based texture…
We propose bilinear models, a recognition architecture that consists of two feature extractors whose outputs are multiplied using outer product at each location of the image and pooled to obtain an image descriptor. This architecture can model local pairwise feature interactions in a translationally…