Search

Transformer is a potentially powerful architecture for vision tasks. Although equipped with more parameters and attention mechanism, its performance is not as dominant as CNN currently. CNN is usually computationally cheaper and still the leading competitor in various vision tasks. One research direction is to adopt the successful ideas of CNN and improve transformer, but it often relies on elaborated and heuristic network design. Observing that transformer and CNN are complementary in representation learning and convergence speed, we propose an efficient training framework called Vision Pair Learning (VPL) for image classification task. VPL builds up a network composed of a transformer branch, a CNN branch and pair learning module. With multi-stage training strategy, VPL enables the branches to learn from their partners during the appropriate stage of the training process, and makes them both achieve better performance with less time cost. Without external data, VPL promotes the top-1 accuracy of ViT-Base and ResNet-50 on the ImageNet-1k validation set to 83.47% and 79.61% respectively. Experiments on other datasets of various domains prove the efficacy of VPL and suggest that transformer performs better when paired with the differently structured CNN in VPL. we also analyze the importance of components through ablation study.

Collecting amounts of distorted/clean image pairs in the real world is non-trivial, which seriously limits the practical applications of these supervised learning-based methods on real-world image super-resolution (RealSR). Previous works usually address this problem by leveraging unsupervised learning-based technologies to alleviate the dependency on paired training samples. However, these methods typically suffer from unsatisfactory texture synthesis due to the lack of supervision of clean images. To overcome this problem, we are the first to have a close look at the under-explored direction for RealSR, i.e., few-shot real-world image super-resolution, which aims to tackle the challenging RealSR problem with few-shot distorted/clean image pairs. Under this brand-new scenario, we propose Distortion Relation guided Transfer Learning (DRTL) for the few-shot RealSR by transferring the rich restoration knowledge from auxiliary distortions (i.e., synthetic distortions) to the target RealSR under the guidance of distortion relation. Concretely, DRTL builds a knowledge graph to capture the distortion relation between auxiliary distortions and target distortion (i.e., real distortions in RealSR). Based on the distortion relation, DRTL adopts a gradient reweighting strategy to guide the knowledge transfer process between auxiliary distortions and target distortions. In this way, DRTL could quickly learn the most relevant knowledge from the synthetic distortions for the target distortion. We instantiate DRTL with two commonly-used transfer learning paradigms, including pre-training and meta-learning pipelines, to realize a distortion relation-aware Few-shot RealSR. Extensive experiments on multiple benchmarks and thorough ablation studies demonstrate the effectiveness of our DRTL., Comment: 12 pages, first paper for few-shot real image super-resolution

Hypoxia-inducible factors enhance glioma stemness, and glioma stem cells have an amplified hypoxic response despite residing within a perivascular niche. Still, little is known about differential HIF regulation in stem versus bulk glioma cells. We show that the intracellular domain of stem cell marker CD44 (CD44ICD) is released at hypoxia, binds HIF-2α (but not HIF-1α), enhances HIF target gene activation, and is required for hypoxia-induced stemness in glioma. In a glioma mouse model, CD44 was restricted to hypoxic and perivascular tumor regions, and in human glioma, a hypoxia signature correlated with CD44. The CD44ICD was sufficient to induce hypoxic signaling at perivascular oxygen tensions, and blocking CD44 cleavage decreased HIF-2α stabilization in CD44-expressing cells. Our data indicate that the stem cell marker CD44 modulates the hypoxic response of glioma cells and that the pseudo-hypoxic phenotype of stem-like glioma cells is achieved by stabilization of HIF-2α through interaction with CD44, independently of oxygen.