Tianyi Zhao

Tianyi Zhao, Jiawen Xi, Linhui Xiao et al.

Visual Grounding (VG) aims to localize specific objects in an image according to natural language expressions, serving as a fundamental task in vision-language understanding. However, existing VG benchmarks are mostly derived from datasets collected under clean environments, such as COCO, where scene diversity is limited. Consequently, they fail to reflect the complexity of real-world conditions, such as changes in illumination, weather, etc., that are critical to evaluating model robustness and generalization in safety-critical applications. To address these limitations, we present RGBT-Ground, the first large-scale visual grounding benchmark built for complex real-world scenarios. It consists of spatially aligned RGB and Thermal infrared (TIR) image pairs with high-quality referring expressions, corresponding object bounding boxes, and fine-grained annotations at the scene, environment, and object levels. This benchmark enables comprehensive evaluation and facilitates the study of robust grounding under diverse and challenging conditions. Furthermore, we establish a unified visual grounding framework that supports both uni-modal (RGB or TIR) and multi-modal (RGB-TIR) visual inputs. Based on it, we propose RGBT-VGNet, a simple yet effective baseline for fusing complementary visual modalities to achieve robust grounding. We conduct extensive adaptations to the existing methods on RGBT-Ground. Experimental results show that our proposed RGBT-VGNet significantly outperforms these adapted methods, particularly in nighttime and long-distance scenarios. All resources will be publicly released to promote future research on robust visual grounding in complex real-world environments.

Tianyi Zhao, Jun Yu, Zhenzhong Kuang et al.

In this paper, a deep mixture of diverse experts algorithm is developed for seamlessly combining a set of base deep CNNs (convolutional neural networks) with diverse outputs (task spaces), e.g., such base deep CNNs are trained to recognize different subsets of tens of thousands of atomic object classes. First, a two-layer (category layer and object class layer) ontology is constructed to achieve more effective solution for task group generation, e.g., assigning the semantically-related atomic object classes at the sibling leaf nodes into the same task group because they may share similar learning complexities. Second, one particular base deep CNNs with $M+1$ ($M \leq 1,000$) outputs is learned for each task group to recognize its $M$ atomic object classes effectively and identify one special class of "not-in-group" automatically, and the network structure (numbers of layers and units in each layer) of the well-designed AlexNet is directly used to configure such base deep CNNs. A deep multi-task learning algorithm is developed to leverage the inter-class visual similarities to learn more discriminative base deep CNNs and multi-task softmax for enhancing the separability of the atomic object classes in the same task group. Finally, all these base deep CNNs with diverse outputs (task spaces) are seamlessly combined to form a deep mixture of diverse experts for recognizing tens of thousands of atomic object classes. Our experimental results have demonstrated that our deep mixture of diverse experts algorithm can achieve very competitive results on large-scale visual recognition.