InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding.

Multi-task scene understanding aims to design models that can simultaneously predict several scene understanding tasks with one versatile model. Previous studies typically process multi-task features in a more local way, and thus cannot effectively learn spatially global and cross-task interactions, which hampers the models' ability to fully leverage the consistency of various tasks in multi-task learning. To tackle this problem, we propose an Inverted Pyramid multi-task Transformer, capable of modeling cross-task interaction among spatial features of different tasks in a global context. Specifically, we first utilize a transformer encoder to capture task-generic features for all tasks. And then, we design a transformer decoder to establish spatial and cross-task interaction globally, and a novel UP-Transformer block is devised to increase the resolutions of multi-task features gradually and establish cross-task interaction at different scales. Furthermore, two types of Cross-Scale Self-Attention modules, i.e., Fusion Attention and Selective Attention, are proposed to efficiently facilitate cross-task interaction across different feature scales. An Encoder Feature Aggregation strategy is further introduced to better model multi-scale information in the decoder. Comprehensive experiments on several 2D/3D multi-task benchmarks clearly demonstrate our proposal's effectiveness, establishing significant state-of-the-art performances. The codes are publicly available https://github.com/prismformore/Multi-Task-Transformer/tree/main/InvPT.

Bi-Directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification.

RGB-Infrared person re-identification (RGB-IR Re-ID) is a cross-modality matching problem, where the modality discrepancy is a big challenge. Most existing works use Euclidean metric based constraints to resolve the discrepancy between features of images from different modalities. However, these methods are incapable of learning angularly discriminative feature embedding because Euclidean distance cannot measure the included angle between embedding vectors effectively. As an angularly discriminative feature space is important for classifying the human images based on their embedding vectors, in this paper, we propose a novel ranking loss function, named Bi-directional Exponential Angular Triplet Loss, to help learn an angularly separable common feature space by explicitly constraining the included angles between embedding vectors. Moreover, to help stabilize and learn the magnitudes of embedding vectors, we adopt a common space batch normalization layer. The quantitative and qualitative experiments on the SYSU-MM01 and RegDB dataset support our analysis. On SYSU-MM01 dataset, the performance is improved from 7.40% / 11.46% to 38.57% / 38.61% for rank-1 accuracy / mAP compared with the baseline. The proposed method can be generalized to the task of single-modality Re-ID and improves the rank-1 accuracy / mAP from 92.0% / 81.7% to 94.7% / 86.6% on the Market-1501 dataset, from 82.6% / 70.6% to 87.6% / 77.1% on the DukeMTMC-reID dataset.

Drug-Free ROS Sponge Polymeric Microspheres Reduce Tissue Damage from Ischemic and Mechanical Injury.

The inherent antioxidant function of poly(propylene sulfide) (PPS) microspheres (MS) was dissected for different reactive oxygen species (ROS), and therapeutic benefits of PPS-MS were explored in models of diabetic peripheral arterial disease (PAD) and mechanically induced post-traumatic osteoarthritis (PTOA). PPS-MS (∼1 µm diameter) significantly scavenged hydrogen peroxide (H2O2), hypochlorite, and peroxynitrite but not superoxide in vitro in cell-free and cell-based assays. Elevated ROS levels (specifically H2O2) were confirmed in both a mouse model of diabetic PAD and in a mouse model of PTOA, with greater than 5- and 2-fold increases in H2O2, respectively. PPS-MS treatment functionally improved recovery from hind limb ischemia based on ∼15-25% increases in hemoglobin saturation and perfusion in the footpads as well as earlier remodeling of vessels in the proximal limb. In the PTOA model, PPS-MS reduced matrix metalloproteinase (MMP) activity by 30% and mitigated the resultant articular cartilage damage. These results suggest that local delivery of PPS-MS at sites of injury-induced inflammation improves the vascular response to ischemic injury in the setting of chronic hyperglycemia and reduces articular cartilage destruction following joint trauma. These results motivate further exploration of PPS as a stand-alone, locally sustained antioxidant therapy and as a material for microsphere-based, sustained local drug delivery to inflamed tissues at risk of ROS damage.