Related papers: Make it SING: Analyzing Semantic Invariants in Cla…
Linear probes and sparse autoencoders consistently recover meaningful structure from transformer representations -- yet why should such simple methods succeed in deep, nonlinear systems? We show this is not merely an empirical regularity…
We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground…
The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic…
A discriminatively trained neural net classifier can fit the training data perfectly if all information about its input other than class membership has been discarded prior to the output layer. Surprisingly, past research has discovered…
Zero-shot learning (ZSL) recognizes the unseen classes by conducting visual-semantic interactions to transfer semantic knowledge from seen classes to unseen ones, supported by semantic information (e.g., attributes). However, existing ZSL…
Text images are unique in their dual nature, encompassing both visual and linguistic information. The visual component encompasses structural and appearance-based features, while the linguistic dimension incorporates contextual and semantic…
We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed method augments the state-of-the-art bilinear compatibility model…
Semantic communication, as a revolutionary communication architecture, is considered a promising novel communication paradigm. Unlike traditional symbol-based error-free communication systems, semantic-based visual communication systems…
We propose a novel approach to improve a visual-semantic embedding model by incorporating concept representations captured from an external structured knowledge base. We investigate its performance on image classification under both…
Deformable shapes provide important and complex geometric features of objects presented in images. However, such information is oftentimes missing or underutilized as implicit knowledge in many image analysis tasks. This paper presents…
Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge. Since the missing hole in a mixed scene of a corrupted image often contains various semantic information,…
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference. However, since the unseen objects are never…
While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and…
We present a novel multi-view training framework and CNN architecture for combining information from multiple overlapping satellite images and noisy training labels derived from OpenStreetMap (OSM) to semantically label buildings and roads…
We propose a novel Generalized Zero-Shot learning (GZSL) method that is agnostic to both unseen images and unseen semantic vectors during training. Prior works in this context propose to map high-dimensional visual features to the semantic…
Recognizing precise geometrical configurations of groups of objects is a key capability of human spatial cognition, yet little studied in the deep learning literature so far. In particular, a fundamental problem is how a machine can learn…
We introduce SENT-Map, a semantically enhanced topological map for representing indoor environments, designed to support autonomous navigation and manipulation by leveraging advancements in foundational models (FMs). Through representing…
One method for obtaining generalizable solutions to machine learning tasks when presented with diverse training environments is to find \textit{invariant representations} of the data. These are representations of the covariates such that…
Zero-shot learning aims to recognize unseen objects using their semantic representations. Most existing works use visual attributes labeled by humans, not suitable for large-scale applications. In this paper, we revisit the use of documents…
Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not…