Related papers: Interpreting Object-level Foundation Models via Vi…

Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often struggle in scenarios requiring precise spatial…

Vision-Language-Action (VLA) models have emerged as a promising framework for enabling generalist robots capable of perceiving, reasoning, and acting in the real world. These models usually build upon pretrained Vision-Language Models…

We investigate the problem of explainability for visual object detectors. Specifically, we demonstrate on the example of the YOLO object detector how to integrate Grad-CAM into the model architecture and analyze the results. We show how to…

Precise spatial understanding in Earth Observation is essential for translating raw aerial imagery into actionable insights for critical applications like urban planning, environmental monitoring and disaster management. However, Multimodal…

In this paper, we propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target…

This study aims to analyze the benefits of improved multi-scale reasoning for object detection and localization with deep convolutional neural networks. To that end, an efficient and general object detection framework which operates on…

While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often infeasible due to computational constraints and…

Face Anti-Spoofing (FAS) remains challenging due to the requirement for robust domain generalization across unseen environments. While recent trends leverage Vision-Language Models (VLMs) for semantic supervision, these multimodal…

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely opaque. While explainable AI has advanced significantly in…

Referring expression segmentation (RES) aims at segmenting the foreground masks of the entities that match the descriptive natural language expression. Previous datasets and methods for classic RES task heavily rely on the prior assumption…

We aim to localize objects in images using image-level supervision only. Previous approaches to this problem mainly focus on discriminative object regions and often fail to locate precise object boundaries. We address this problem by…

The success of large pre-trained object detectors hinges on their adaptability to diverse downstream tasks. While fine-tuning is the standard adaptation method, specializing these models for challenging fine-grained domains necessitates…

Interpreting the decisions of deep learning models has been actively studied since the explosion of deep neural networks. One of the most convincing interpretation approaches is salience-based visual interpretation, such as Grad-CAM, where…

Accurate and generalizable object segmentation in ultrasound imaging remains a significant challenge due to anatomical variability, diverse imaging protocols, and limited annotated data. In this study, we propose a prompt-driven…

Aerial Remote Sensing (ARS) vision tasks present significant challenges due to the unique viewing angle characteristics. Existing research has primarily focused on algorithms for specific tasks, which have limited applicability in a broad…

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Software vulnerability detection can be formulated as a binary classification problem that determines whether a given code snippet contains security defects. Existing multimodal methods typically fuse Natural Code Sequence (NCS)…

Large foundation models trained on large-scale vision-language data can boost Open-Vocabulary Object Detection (OVD) via synthetic training data, yet the hand-crafted pipelines often introduce bias and overfit to specific prompts. We…

What does it mean for a visual system to truly understand affordance? We argue that this understanding hinges on two complementary capacities: geometric perception, which identifies the structural parts of objects that enable interaction,…