Related papers: Fuzzy Logic Visual Network (FLVN): A neuro-symboli…

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared…

Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i.e., attributes) or…

In this paper, we introduce Interval Real Logic (IRL), a two-sorted logic that interprets knowledge such as sequential properties (traces) and event properties using sequences of real-featured data. We interpret connectives using fuzzy…

Vision-Language Navigation (VLN) aims to enable agents to navigate to a target location based on language instructions. Traditional VLN often follows a close-set assumption, i.e., training and test data share the same style of the input…

Existing FNNs are mostly developed under a shallow network configuration having lower generalization power than those of deep structures. This paper proposes a novel self-organizing deep FNN, namely DEVFNN. Fuzzy rules can be automatically…

We present Florence-VL, a new family of multimodal large language models (MLLMs) with enriched visual representations produced by Florence-2, a generative vision foundation model. Unlike the widely used CLIP-style vision transformer trained…

Visual target navigation in unknown environments is a crucial problem in robotics. Despite extensive investigation of classical and learning-based approaches in the past, robots lack common-sense knowledge about household objects and…

Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require…

Word embeddings can reflect the semantic representations, and the embedding qualities can be comprehensively evaluated with human natural reading-related cognitive data sources. In this paper, we proposed the CogniFNN framework, which is…

Conventional centralised deep learning paradigms are not feasible when data from different sources cannot be shared due to data privacy or transmission limitation. To resolve this problem, federated learning has been introduced to transfer…

Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations. Although typical attempts focus on ameliorating the inevitable error-prone pseudo-labeling, we think differently and…

The Forward-Forward Learning (FFL) algorithm is a recently proposed solution for training neural networks without needing memory-intensive backpropagation. During training, labels accompany input data, classifying them as positive or…

Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…

Interpretability has become a necessary feature for machine learning models deployed in critical scenarios, e.g. legal system, healthcare. In these situations, algorithmic decisions may have (potentially negative) long-lasting effects on…

Deep learning (DL) based language models achieve high performance on various benchmarks for Natural Language Inference (NLI). And at this time, symbolic approaches to NLI are receiving less attention. Both approaches (symbolic and DL) have…

State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded…

Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes. It inevitably requires consistent visual-semantic alignment. Existing approaches…

Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common semantic characteristics between the visual modality and…

Convolutional neural network (CNN) has achieved state-of-the-art performance in many different visual tasks. Learned from a large-scale training dataset, CNN features are much more discriminative and accurate than the hand-crafted features.…

Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we…